Systems, devices, and method for determining and monitoring sleep disorders based on determined arousals and arousal-associated events using non-brain body signals or without requiring brain signals

Abstract

Systems, devices, and methods are provided for performing a sleep study of a subject. The methods include obtaining data from one or more body signals, the one or more body signals being non-brain signals, and determining an arousal or arousal-associated event of the subject using the data from one or more body signals. In a preferred embodiment, the one or more body signals include data obtained from one or more RIP belts.

Description

SYSTEMS, DEVICES, AND METHOD FOR DETERMINING AND MONITORING SLEEP DISORDERS BASED ON DETERMINED AROUSALS AND AROUSAL- ASSOCIATED EVENTS USING NON-BRAIN BODY SIGNALS OR WITHOUT REQUIRING BRAIN SIGNALS

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of and priority to United States Provisional Patent Application Serial No. 63 / 819,266, filed on June 6, 2025, and to United States Application No. 18 / 889,280, filed at the United States Patent Office on September 18, 2024, which is a continuation in part of United States Application No. 18 / 608,526, filed at the United States Patent Office on March 18, 2024, and PCT / IB2024 / 052615, filed at the International Bureau of WIPO on March 18, 2024, which each claim priority to United States Provisional Patent Applications Serial Nos. 63 / 490,984, filed on March 17, 2023, and 63 / 613,562, filed on December 21, 2023, all of which are incorporated herein by reference in their entirety.

[0003] FIELD OF THE DISCLOSURE

[0004] The present disclosure relates to systems, apparatuses, and methods for determining arousals and sleep stages of a subject, and particularly for determining arousals and sleep stages based on signals obtained from the body of the subject without necessarily being signals obtained from the brain or heart of the subject.

[0005] BACKGROUND

[0006] Clinical sleep studies of different types have been developed. Such studies have either focused on measuring or identifying a specific sleep disorder or have been more general for measuring the overall sleep profile along with the signals necessary to confirm or exclude different sleep disorders.

[0007] Polysomnography (PSG) is a general sleep study that records various physiological signals. A PSG is generally considered a complicated study and usually requires professional assistance by certified or credential technologists to setup, perform, and monitor the PSG. PSG includes simultaneous recording of multiple signals, such as Electroencephalography (EEG), Electrooculography (EOG), Electromyography (EMG), Electrocardiography (ECG), Respiratory Flow, Respiratory Effort, Oximetry, Body Position, and / or more to achieve the required accuracy.

[0008] During a PSG the electroencephalography (EEG) signals are obtained from the head of a subject for determining sleep stages of the subject. The time people spend in bed can normally be divided into certain periods or stages of Rapid Eye Movement (REM) sleep,Non-rapid eye movement sleep (Non-REM or NREM) sleep, and occasional Wake periods. Standard PSG allows further classification of the NREM periods on different levels of sleep including Nl, N2, and N3, with N1 being the shallowest, then N2, and finally N3. The N3 period is often referred to as deep sleep or Slow Wave Sleep due to the slow EEG signals that are characteristic of this period. The sleep stages are often presented in a graph with the X axis labeled with the time of day and the Y axis showing 5 values, Wake, REM, Nl, N2, N3. A line may then be plotted showing the sleep stage of the subject at different times of the night or sleep study period. Such a graph is called hypnogram and is the standard presentation of the sleep profile used in PSG studies.

[0009] The sleep indexes, which are derived directly from the sleep study signals, often include an expansive collection of indices derived from the sleep study. These indices may include, but are not limited to:• Arousal Index: The number of arousals per hour of sleep.• Apnea-Hypopnea Index: The number of complete breathing cessations (apneas), and severely restricted breathing (hypopnea) events per hour of sleep.• Oxygen Desaturation Index: The number of blood oxygen desaturation events per hour of sleep.• Limb Movement Index: The number of limb movement events per hour of sleep.• Periodic Limb Movement Index: The number of periodic limb movement events per hour of sleep.• Total Sleep Time: The total time duration of sleep during the sleep study.• Wake After Sleep Onset: The total time duration of wake periods from the first moment of sleep to the last moment of sleep.• Position: A measurement of the periods a patient is sleeping in a supine, prone, left-side, or right-side positions.

[0010] Electroencephalography (EEG) is typically based on electrodes placed on the scalp of the subject. The clinical standards for PSG require that the recording of EEG signals is done with electrodes located on parts of the head typically covered in hair. But a patient or subject generally can’t or has difficulty applying the sleep study electrodes on himself, or at least has difficulty applying the sleep study electrodes on himself correctly. Therefore the patient must be assisted by a nurse or technician. For this reason, most PSG studies are done in a clinic, as the patient needs to be prepared for the sleep study around the time he goes to bed.

[0011] Another common type of sleep study is Home Sleep Apnea Testing (HSAT). HSAT generally only focuses on respiratory parameters and oxygen saturation for diagnosing sleep apnea and sleep disordered breathing. HSAT does however not require EEG electrodes on the head or sensors that the patient can’t place on him himself. Therefore, the most common practice in HSAT is to hand the HSAT system to the patient over-the-counter in the clinic or send the HSAT system by mail to the patient and have the patient handle the hookup or placement of the HSAT system to himself. This is a highly cost-efficient process for screening for sleep apnea. However, this practice has the drawback that the sleep stages, including time of sleep / wake periods is missing. It is therefore the risk of HSAT not performed in a clinic that the patient was indeed not sleeping during the whole recording time. But as this may not be known to the technician scoring the data from the HST after the study, there is the risk that this could affect the clinical decision on the severity of the sleep apnea. It would therefore be preferred to have some prediction or determination of the sleep stages of the subject to improve the accuracy of the diagnoses. But as noted above, doing a standard EEG on the patient during the HSAT would be impractical or impossible in a hometype setting, or too expensive. Although current HSAT systems and methods can provide an accurate indication of total sleep time (TST), for example, as described in US 2021 / 0085242A1, as described below they suffer from the significant inability to determine arousal or arousal-associated events, and therefore current HSAT systems and methods are not able to correctly classify all three types of apnea / hypopnea events of a respiratory event index (REI).

[0012] The American Academy of Sleep Medicine (AASM) defines what signals are recorded in each type of sleep studies and how the signals are interpreted to make a diagnosis. To diagnose sleep apnea the main outcome of interest is the apnea hypopnea index (AHI), which is a number that counts the number of apnea and hypopnea events occurring during sleep. According to the AASM, an “apnea” is a respiratory event that is defined by a 90% reduction in airflow from baseline lasting at least 10 seconds. Further, according to the AASM, a “hypopnea” is defined as respiratory events where the reduction in airflow is between 30% and 90% from baseline and the reduction in airflow is associated with a 3% or 4% drop in blood oxygen saturation and / or a cortical arousal.

[0013] For example, the published “Rules for Scoring Respiratory Events in Sleep”, as updated in 2007, the AASM further defines an apnea event, stating: “Hypopnea in adults is scored when the peak signal excursions drop by > 30% of pre-event baseline using nasal pressure (diagnostic study), PAP device flow (titration study), or an alternative sensor, for >10 seconds in association with either > 3% arterial oxygen desaturation or an arousal.” (Berry RB; Budhiraja R; et al. Rules for scoring respiratory events in sleep: update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. J Clin Sleep Med 2012;8(5):597-619, at 597 (emphasis added); see also Malhotra RK, et al.; American Academy of Sleep Medicine Board of Directors. Polysomnography for obstructive sleep apnea should include arousal -based scoring: an American Academy of Sleep Medicine position statement. J Clin Sleep Med. 2018;14(7): 1245-1247; Rosen IM, et al.; American Academy of Sleep Medicine Board of Directors. Clinical use of a home sleep apnea test: an updated American Academy of Sleep Medicine position statement. J Clin Sleep Med. 2018;14(12):2075-2077; and Riha RL, et al. ERS technical standards for using type III devices (limited channel studies) in the diagnosis of sleep disordered breathing in adults and children. Eur Respir J 2023; 61 : 2200422 [DOI: 10.1183 / 13993003.00422-2022],

[0014] To aid in the understanding of current scoring rules for respiratory events in sleep studies that are used and accepted in the field and promulgated by authorities, current and relevant scoring rules of the AASM are provided below.

[0015] AASM Scoring of Apneas (PSG)

[0016] From the AASM manual for the scoring of sleep and associated events polysomnography (PSG) scoring rules for apneas (v2.6, “C. Scoring of Apneas”):

[0017] Scoring of Apneas1. Score a respiratory event as an apnea when BOTH of the following criterial are met: a. There is a drop in the peak signal excursion by >90% of pre-event baseline using an oronasal thermal sensor (diagnostic study), PAP device flow (titration study) or an alternative apnea sensor (diagnostic study). b. The duration of the >90% drop in sensor signal is >10 seconds.2. Score an apnea as “obstructive” if it meets apnea criteria and is associated with continued or increased inspiratory effort throughout the entire period of absent airflow.3. Score an apnea as “central” if it meets apnea criteria and is associated with absent inspiratory effort throughout the entire period of absent airflow.4. Score an apnea as “mixed” if it meets apnea criteria and is associated with absent inspiratory effort in the initial portion of the event, followed by resumption of inspiratory effort in the second portion of the event.

[0018] With reference to FIG. 1, the relevant section of the AASM manual for the scoring of apneas notes:Note 1 : Identification of an apnea does not require a minimum desaturation criterion.Note 2: If a portion of a respiratory event that would otherwise meet criteria for a hypopnea meets criterial for apnea, the entire event should be scored as an apnea. (For example, as shown in FIG. 1, the longer duration, depicted by the white arrows in the nasal pressure channel, meets airflow criteria for a hypopnea, whereas the shorter duration, depicted by the black arrows in the oronasal thermal airflow channel, meets airflow criteria for an apnea. The even would be scored as an apnea.)Note 3: If the apnea or hypopnea event begins or ends during an epoch that is scored as sleep, then the corresponding respiratory event can be scored and included in the computation of the apnea-hypopnea index (AHI). This situation usually occurs when an individual has a high AHI with events occurring so frequently that sleep is severely disrupted, and epochs may end up being scored as wake even though <15 seconds of sleep is present during the epoch containing that portion of the respiratory event. However, if the apnea of hypopnea occurs entirely during an epoch scored as wake, it should not be scored or counted towards the apnea-hypopnea index because of the difficulty of defining a denominator in this situation. If these occurrences are a prominent feature of the polysomnogram and / or interfere with sleep onset, their presence should be mentioned in the narrative summary of the study.Note 4: For alternative apnea sensors see Technical Specifications for adults (A.2).Note 5: There is not sufficient evidence to support a specific duration of the central and obstructive components of a mixed apnea; thus, specific durations of these components are not recommended.

[0019] AASM Scoring of Hypopneas (PSG)

[0020] From the AASM manual for the scoring of sleep and associated events polysomnography (PSG) scoring rules for hypopneas (v2.6, “D. Scoring of Hypopneas”)

[0021] Scoring of HypopneasScoring hypopneas as central or obstructive events is option as noted in Parameters to be Reported (ILF)1 A. Score a respiratory event as a hypopnea if ALL of the following criteria are met: a. The peak signal excursions drop by >30% of pre-event baseline using nasal pressure (diagnostic study), PAP device flow (titration study), or an alternative hypopnea sensor (diagnostic study). b. The duration of the >30% drop in signal excursion is >10 seconds.c. There is a >3% oxygen desaturation from pre-event baseline or the event is associated with an arousal.IB. Score a respiratory event as a hypopnea if ALL of the following criterial are met: a. The peak signal excursions drop by >30% of pre-event baseline using nasal pressure (diagnostic study), PAP device flow (titration study), or an alternative hypopnea sensor (diagnostic study). b. The duration of the >30% drop in signal excursions is >10 seconds. c. There is a >4% oxygen desaturation from pre-event baseline.2. If electing to score obstructive hypopneas, score a hypopnea as obstructive if ANY of the following criteria are met: a. There is snoring during the event. b. There is increased inspiratory flattening of the nasal pressure or PAP device flow signal compared to baseline breathing. c. There is an associated thoracoabdominal paradox that occurs during the event but not during pre-event breathing.3. If electing to score central hypopneas, score a hypopnea as central if NONE Of the following criteria are met: a. There is snoring during the event. b. There is increased inspiratory flattening of the nasal pressure or PAP device flow signal compared to baseline breathing. c. There is an associated thoracoabdominal paradox that occurs during the event but not during pre-event breathing.

[0022] The relevant section of the AASM manual for the scoring of apneas notes the following:Note 1 : The criteria used to score a respiratory event as a hypopnea (either rule 1 A or IB) should be specified in the PSG report. It is the responsibility of the individual practitioner to confirm and follow the criterial that should be used for reporting to the patient’s payer in order to be reimbursed and qualify the patient for therapy.Note 2: For alternative hypopnea sensors see Technical Specifications for adults (A.4).Note 3 : Supplemental oxygen may blunt desaturation. There are currently no scoring guidelines for when a patient is on supplemental oxygen and no desaturation is noted. If the diagnostic study is performed while the individual is on supplemental oxygen, its presence should be mentioned in the narrative summary of the study.

[0023] AASM Scoring Arousals

[0024] From the AASM manual for the scoring of sleep and associated events scoring rules for arousals (v2.6, “V. Arousal Rule”):

[0025] Scoring Arousals1. Score arousal during sleep stages Nl, N2, N3, or R if there is an abrupt shift of EEG frequency including alpha, theta and / or frequencies greater than 16 Hz (but not spindles) that lasts at least 3 seconds, with at least 10 seconds of stable sleep preceding the change. Scoring of arousal during REM requires a concurrent increase in submental EMG lasting at least 1 second.

[0026] The relevant section of the AASM manual for the scoring of apneas notes the following:Note 1 : Arousal scoring should incorporate information from the frontal, central, and occipital derivations.Note 2: Arousal scoring can be improved by the use of additional information in the recording such as respiratory events and / or additional EEG channels. Scoring of arousals, however, cannot be based on this additional information alone and such information does not modify any of the arousal scoring rules.Note 3: Arousals meeting all scoring criteria but occurring during an awake epoch in the recorded time between “lights out” and “lights on” should be scored and used for computation of the arousal index.Note 4: The 10 seconds of stable sleep required prior to scoring an arousal may begin in the preceding epoch, including a preceding epoch that is scored as stage W.Note 5: An arousal may still be scored if it immediately precedes a transition to stage W. That is, both the arousal and transition to wake are scored.

[0027] AASM HSAT Scoring Apneas

[0028] From the AASM manual for the scoring of sleep and associated events, home sleep apnea test (HSAT) scoring rules for apneas (v2.6, “G. HSAT Respiratory Events Rules: Scoring Apnea Utilizing Respiratory Flow and / or Effort Sensors”):1. Score a respiratory event as an apnea when BOTH of the following criteria are met: a. There is a drop in the peak signal excursions by >90% of pre-event baseline using a recommended or alternative airflow sensor. b. The duration of the >90% drop in sensor signal is >10 seconds.2. Score an apnea as “obstructive” if it meets apnea criteria and is associated with continued or increased inspiratory effort throughout the entire period of absent airflow.3. Score an apnea as “central” if it meets apnea criteria and is associated with absent inspiratory effort throughout the entire period of absent airflow.4. Score an apnea as “mixed” if it meets apnea criteria and is associated with absent inspiratory effort in the initial portion of the event, followed by resumption of inspiratory effort in the second portion of the event.

[0029] The relevant section of the AASM manual for the scoring of apneas notes the following:Note 1 : Identification of an apnea does not require a minimum desaturation criterion.Note 2: If a portion of a respiratory event that would otherwise meet criteria for a hypopnea meets criteria for apnea, the entire event should be scored as an apnea.Note 3: There is not sufficient evidence to support a specific duration of the central and obstructive components of a mixed apnea; thus, the specific durations of these components are not recommended.Note 4: Some devices may not differentiate between different types of apneas.

[0030] AASM HSAT Scoring Hypopneas

[0031] From the AASM manual for the scoring of sleep and associated events, home sleep apnea test (HSAT) scoring rules for hypopneas (v2.6, “H. HSAT Respiratory Events Rules: Scoring Hypopnea Utilizing Respiratory Flow and / or Effort Sensors”):1 A. If sleep is NOT recorded, score a respiratory event as a hypopnea if ALL of the following criteria are met: a. The peak signal excursions drop by >30% of pre-event baseline using a recommended or alternative airflow sensor. b. The duration of the >30% drop in signal excursions is >10 seconds. c. There is a >3% oxygen desaturation from pre-event baseline.IB. If sleep is NOT recorded, score a respiratory event as a hypopnea if ALL of the following criteria are met: a. The peak signal excursions drop by >30% of pre-event baseline using a recommended or alternative airflow sensor. b. The duration of the >30% drop in signal excursions is >10 seconds. c. There is a >4% oxygen desaturation from pre-event baseline.2A. If sleep IS recorded, score a respiratory event as a hypopnea if ALL of the following criteria are met: a. The peak signal excursions drop by >30% of pre-event baseline using a recommended or alternative airflow sensor.b. The duration of the >30% drop in signal excursions is >10 seconds. c. There is a >3% oxygen desaturation from pre-event baseline or the event is associated with an arousal.2B. If sleep IS recorded, score a respiratory event as a hypopnea if ALL of the following criteria are met: a. The peak signal excursions drop by >30% of pre-event baseline using a recommended or alternative airflow sensor. b. The duration of the >30% drop in signal excursions is >10 seconds. c. There is a >4% oxygen desaturation from pre-event baseline.

[0032] The relevant section of the AASM manual for the scoring of apneas notes the following:Note 1 : The criteria used to score a respiratory event as a hypopnea should be s specified in the report.Note 2: Scoring a hypopnea based on arousals is only possible if sleep is recorded.

[0033] In standard Polysomnography (PSG), a cortical arousal is currently detected as an abrupt change in electroencephalography (EEG) signals.

[0034] FIG. 2 shows an example of a scored apnea followed by a desaturation and an arousal. It is not necessary to have desaturations or arousals to score an apnea. However, it is very common that apneas are followed by a desaturation and / or an arousal. In FIG. 2 the apnea is marked with the orange square labeled “apnea” on top of the flow signal. The apnea is determined by the reduction in the amplitude of the flow signal. The desaturation event is marked by the sea green square on top of the SpO2 signal and labeled as “desaturation event”, and the arousals are the sea green squares on top of the O2-M1 signal.

[0035] FIG. 3 shows examples of scored hypopneas followed by desaturations and arousals. The hypopnea events are marked with bars drawn above the flow signal and labeled “hypopnea”, which correspond to the reduction in flow during the hypopneas is marked by the reduction in the flow signal amplitude. Desaturation events are marked on top of the SpO2 signal in the first half of the figure, and are labeled as “desaturation event”. The arousal events (labeled “arousal”) are labeled in the squares on top of the C4-M1 and C3-M2 signals.

[0036] Respiratory Related Arousal (RERA)

[0037] Traditionally the respiratory events of apnea, hypopnea, and respiratory related arousal (RERA) are scored when diagnosing sleep apnea. Apneas are defined by the AASM as a 90% reduction in airflow. Hypopneas are defined as a 30% or more decrease in airflow followed by a 3 or 4% drop in blood oxygen saturation measured with a pulse oximeter or anarousal. RERAs are respiratory events that do not fulfill the criteria of apneas or hypopneas, and terminate in an arousal.

[0038] SUMMARY

[0039] The inventors of the present application have identified a significant problem that the scoring of hypopnea events in a conventional Home Apnea Sleep Testing (HSAT) sleep study is limited by the fact that electroencephalography (EEG) signals are not recorded. Therefore, no cortical arousals can be directly detected, and hypopneas that end with an arousal and not a desaturation have not been detected. The inventors of the present application have found that this results in a systematic underestimation of the apnea hypopnea index (AHI), respiratory event index (REI), or respiratory disturbance index (RDI) indices from HSAT studies and may result in patients having to undergo a second sleep study or worse, being mis-diagnosed as not having sleep apnea when a more thorough sleep study such as a standard Polysomnography (PSG) would have revealed that they indeed do have sleep apnea or hypopneas.

[0040] As the popularity of home sleep apnea tests (HSAT) grows, so too does the importance of ensuring that they provide the best information possible to facilitate patient diagnosis and treatment. The inventors of the present application have identified the significant challenge to estimate a patient’s Apnea Hypopnea Index (AHI) when no electroencephalography (EEG) is available. Until now, an EEG has been considered necessary to detect arousals which can influence hypopnea scoring and thus not using it can lead to a lower AHI for HSAT compared to polysomnography (PSG), potentially resulting in a patient’s misdiagnosis. To address this issue, according to one embodiment, the inventors of the present application have developed and disclose herein methods and systems that predict sleep arousals using non-brain signal groups, or in other words using signals not obtained from a brain-machine-interface (BMI), or methods and systems that predict sleep arousals or arousal-associated events, including but not limited to arousal-associated hypopnea, without requiring brain signal groups.

[0041] According to one embodiment, methods and systems are disclosed herein that predict sleep arousals or arousal-associated events using non-EEG signal groups. Methods and systems are disclosed herein that predict sleep arousals without requiring EEG signal groups. Also provided, as embodiments, are methods and systems using on an effective Al model tailored for HSAT, that can predict or identify sleep arousals using non-brain signal groups, or in other words using signals not obtained from a brain-machine-interface (BMI). Also provided, as embodiments, are methods and systems using on an effective Al model tailoredfor HSAT, that can predict sleep arousals or arousal -associated events using only non-EEG signal groups. And even further are provided, as further embodiments, methods and systems using on an effective Al model tailored for HSAT, that can predict sleep arousals using only two non-EEG signal groups. And in preferred embodiments, methods and systems are provided that predict sleep arousals or arousal-associated events using respiratory signals without requiring brain signal groups.

[0042] A non-invasive method and system are provided for determining an arousal or arousal-associated events of a subject. The method includes (1) obtaining one or more respiratory signals, the one or more respiratory signals being an indicator of a respiratory activity of the subject, (2) extracting features from the one or more respiratory signals, and (3) determining an arousal or an arousal-associated event of the subject based on the extracted features.

[0043] A method and system is provided for determining an arousal or an arousal-associated event in a sleep study of a subject, the method comprising: obtaining data from one or more body signals, the one or more body signals being non-brain signals; and determining an arousal or an arousal-associated event of the subject using the data from one or more body signals.

[0044] BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG. 1 shows an example of a hypopnea event.

[0046] FIG. 2 shows an example of a scored apnea followed by a desaturation and an arousal.

[0047] FIG. 3 shows examples of scored hypopneas followed by desaturations and arousals.

[0048] FIGS. 4a and 4b illustrate an example of respiratory inductance plethysmograph (RIP) belts.

[0049] FIG. 5 shows an example of a scored apnea followed by a desaturation and an arousal as determined according to a preferred embodiment.

[0050] FIG. 6 shows examples of scored hypopneas followed by desaturations and arousals as determined according to a preferred embodiment.

[0051] FIGS. 7A, 7B, and 7C show schematics of a subject sleeping with HSAT sleep study devices.

[0052] FIG. 8 illustrates a computing device configured to perform the method of determining arousals based on received data obtained from the subject of the sleep study.

[0053] FIG. 9 shows a structure of a single gated recurrent unit (GRU) unit.

[0054] FIG. 10 shows a diagram of the neural network.

[0055] FIG. 11 shows a flowchart depicting the various exclusion criteria and the final dataset values for validation of the disclosed method.

[0056] FIG. 12 shows a visual representation of how test and reference AHI were obtained in the validation of the disclosed method.

[0057] FIG. 13 shows a Bland Altman plot for the whole cohort.

[0058] FIGS. 14A and 14B show Bland Altman plots of the reference and test AHI for a) males (FIG. 14 A) and b) females (FIG. 14B).

[0059] FIGS. 15 A, 15B, 15C, 15D, 15E, and 15F show Bland Altman plot of the reference and test AHI for all the different age groups: a) 18-25 years (FIG. 15 A), b) 26-35 years (FIG. 15B), c) 36-45 years (FIG. 15C), d) 46-55 years (FIG. 15D), e) 56-65 years (FIG. 15E), and f) 65+ years (FIG. 15F).

[0060] FIGS. 16 A, 16B, and 16C show Bland Altman plot of the reference and test AHI for the different BMI groups: a) Normal (BMI < 25) (FIG. 16A), b) Overweight (25 < BMI < 30) (FIG. 16B), and c) Obese (BMI > 30) (FIG. 16C).

[0061] FIGS. 17A and 17B show that the majority of data points were centered around the zero difference line for both groups with comorbidity and the group without a known comorbidity.

[0062] FIGS. 18A and 18B show a Bland-Altman plot showing agreement for individuals taking medication (FIG. 18A) and individuals not taking medication (FIG. 18B).

[0063] FIG. 19 show a flowchart used for defining the medication study population.

[0064] FIG. 20 shows an example of how the thoracic RIP signal changes in a period of REM sleep interrupted by an awakening and a period of non-REM sleep.

[0065] FIGS. 21 A and 21C show the systematic underestimation of Home Apnea Sleep Testing (HSAT) Respiratory Event Index (REI) using current HSAT methods compared to Polysomnography (PSG) Apnea Hypopnea Index (AHI), and FIGS. 21B and 21D show the significant improvement to accuracy of the Home Apnea Sleep Testing (HSAT) Respiratory Event Index (REI) using an embodiment of the non-brain, BodySleep analysis method as described herein.

[0066] FIG. 22 shows a method of obtaining results from a home sleep study (HSS) that are significantly improved to level of accuracy comparable to a PSG study.

[0067] FIG. 23 A and 23B show sleep studies with examples of periodic arousal or arousal- associated events and subject activity identifying Periodic Limb Movement during Sleep (PLMS) in a sleep study of a subject using one or more body signals, preferably respiratory signals.

[0068] FIG. 24A shows a schematic showing a subset of physiological signals from a sleep recording.

[0069] FIG. 24B shows how a recording would be scored if it were a type III recording.

[0070] FIG. 24C shows how a recording would be scored if it were a type III recording scored by some embodiments of DeepRESPusAT.

[0071] FIG. 24D shows as a reference how a recording would be scored manually if it were a type I recording.

[0072] FIG. 25A shows a graph of the PPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for AHI > 5 and AHI > 15.

[0073] FIG. 25B shows a graph of the NPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for AHI > 5 and AHI > 15.

[0074] FIG. 25C shows a graph of the OPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for AHI > 5 and AHI > 15.

[0075] FIG. 25D shows a graph of the PPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for sleep states (Wake, NREM, REM).

[0076] FIG. 25E shows a graph of the NPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for sleep states (Wake, NREM, REM).

[0077] FIG. 25F shows a graph of the OPA paired median difference between agreement of the embodiment and predicate device compared to manual scoring for sleep states (Wake, NREM, REM).

[0078] FIG. 25G shows a graph of the PPA, NPA, and OPA paired median difference between agreement of the embodiment and primary predicate device compared to manual scoring for respiratory events.

[0079] FIG. 26A shows a histogram depicting a comparison of the number and distribution of the AHI values for the Gender Unknown subgroup and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0080] FIG. 26B shows a histogram depicting a comparison of the number and distribution of the AHI values for the Gender Unknown subgroup and the number and distribution of incorrectly classified recordings for a predicate device.

[0081] FIG. 27A shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI Missing subgroup and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0082] FIG. 27B shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI Missing subgroup and the number and distribution of incorrectly classified recordings for a predicate device.

[0083] FIG. 28A shows a histogram depicting a comparison of the number and distribution of the AHI values for the Black / African American subgroup and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0084] FIG. 28B shows a histogram depicting a comparison of the number and distribution of the AHI values for the Black / African American subgroup and the number and distribution of incorrectly classified recordings for a predicate device.

[0085] FIG. 29A shows a histogram depicting a comparison of the number and distribution of the AHI values for the Other subgroup and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0086] FIG. 29B shows a histogram depicting a comparison of the number and distribution of the AHI values for the Other subgroup and the number and distribution of incorrectly classified recordings for a predicate device.

[0087] FIG. 30A shows a histogram depicting a comparison of the number and distribution of the AHI values for the Female subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0088] FIG. 30B shows a histogram depicting a comparison of the number and distribution of the AHI values for the Female subgroup for AHI > 15and the number and distribution of incorrectly classified recordings for a predicate device.

[0089] FIG. 31 A shows a histogram depicting a comparison of the number and distribution of the AHI values for the 22-35 Only subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0090] FIG. 3 IB shows a histogram depicting a comparison of the number and distribution of the AHI values for the 22-35 Only subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for a predicate device.

[0091] FIG. 32A shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI < 25 Only subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0092] FIG. 32B shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI < 25 Only subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for a predicate device.

[0093] FIG. 33A shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI Missing subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for an embodiment described herein.

[0094] FIG. 33B shows a histogram depicting a comparison of the number and distribution of the AHI values for the BMI Missing subgroup for AHI > 15 and the number and distribution of incorrectly classified recordings for a predicate device.

[0095] FIGS. 34A, 34B, 34C, 34D, 34E, 34F, 34G, 34H, and 341 show the results of a Bland- Altman Analysis with the following types of sleep recordings per figure - for the analysis shown in FIGS. 34A - 34D, Type I and Type II sleep recordings were used: AHI (FIG. 34A), apnea index (Al) (FIG. 34B), hypopnea index (HI) (FIG. 34C), and oxygen desaturation index (ODI) (FIG. 34D), and for the analysis in FIGS. 34E - 341, Type I sleep recordings were used: arousal index (Ari) (FIG. 34E), sleep efficiency (SE) (FIG. 34F), sleep latency (FIG. 34G), REM latency (FIG. 34H), and estimated Total Sleep Time (TST) (FIG. 341).

[0096] FIGS. 35A, 35B, 35C, 35D, 35E, 35F, 35G, 35H, and 351 show the results of the Deming regression with the following types of sleep recordings per figure- for the Deming regression shown in FIGS. 35A - 35D, Type I and Type II sleep recordings were used: AHI (FIG. 35 A), apnea index (Al) (FIG. 35B), hypopnea index (HI) (FIG. 35C), and oxygen desaturation index (ODI) (FIG. 35D), and for the analysis in FIGS. 35E - 351 Type I sleep recordings were used: arousal index (Ari) (FIG. 35E), sleep efficiency (SE) (FIG. 35F), sleep latency (FIG. 35G), REM latency (FIG. 35H), and estimated Total Sleep Time (TST) (FIG. 351).

[0097] FIG. 36 illustrates an example residual block of an Al model according to some embodiments described herein.

[0098] FIGS. 37A and 37B illustrate an example architecture of an Al model according to some embodiments described herein.

[0099] FIG. 38 shows a histogram of a distribution of arousal durations across a dataset of (n=1299) patients.

[0100] FIG. 39 shows a Bland- Altman plot of log-transformed Arousal Index (Ari) values for a validation study of an embodiment described herein.

[0101] FIG. 40 shows one example of a snap connector that may be used according to some embodiments described herein.

[0102] DETAILED DESCRIPTION OF VARIOUS EMBODIMENTS

[0103] As noted above, the inventors of the present application have found it would be highly advantageous to have some prediction or determination of an arousal or an arousal-associatedevent, such as an arousal-associated hypopnea, during a sleep study of a subject to improve the accuracy of a sleep-related diagnoses. But doing an electroencephalography (EEG) on a patient during a Home Apnea Sleep Testing (HSAT) is often impractical or impossible in a home-type setting, or is too expensive. Preferably, in a home setting, the patient is able to apply to himself the sensors needed for the HSAT, which simply is not practical with EEG.

[0104] Additionally, a sleep study including an arousal prediction, determination, or classification based on cardio or heart-related signals or body movement signals are often inaccurate, due to the dependency of cardio or heart-related signals to unrelated factors, such as cardiac condition, blood pressure, medication and other individual specific factors.

[0105] What would be highly advantageous is that an arousal or an arousal-associated event determination be performed in what may be termed a “body sleep study”, meaning a sleep study performed without using or at least without requiring features derived directly from the brain, that is without using or at least without requiring features obtained by a brain-machine interface (BMI), that translates neuronal activity of the brain into signals, such as an electroencephalogram (EEG). Further, it would be highly advantageous to perform an arousal or an arousal-associated event determination in a HSAT or sleep study not including EEG without using or at least without requiring features derived from the heart. Further, it would also be preferred that a HSAT or sleep study not including EEG to perform an arousal determination based on measuring one or more features other than body movement signals, as an arousal or an arousal-associated event determination of a sleep study based on body movement signals can be inaccurate. Such a sleep study, based on or using non-brain signals, and even more preferably non-brain and non-cardiac signals would allow the sleep study to be performed with improved certainty and accuracy on patients, and particularly in a home environment, and would greatly reduce the risk of wrong clinical decisions or requiring of a further non-home-based sleep study, such as a general Polysomnography (PSG).

[0106] As used herein, an “arousal-associated event” or “arousal-associated events” are events that occur in a relation with or are correlated with an arousal. Such events can occur prior to an arousal, simultaneously with an arousal, or post or after an arousal. An event is associated with an arousal when an arousal causes the associated event, the associated event causes the arousal, or the arousal and the arousal associated event have a mutual cause. Such events can include, but are not limited to: a transition from sleep to awake state, when a transition from sleep to wake is preceded by an arousal or occurs at the same time as an arousal; a transition from NREM2 sleep to NREM1 sleep or a period of time within a transition from NREM2 sleep to NREM1 sleep, for example a 10 second epoch, a 20 secondepoch, a 30 second epoch, or up to a 60 second epoch; a transition from REM sleep to NREM1 sleep; when an arousal interrupts stage REM sleep; a period limb movement of sleep (PLMS) or limb movement (LM) associated arousal; an arousal and a limb movement that occur in a periodic limb movement (PLM) series could be considered associated with each other if they occur simultaneously, overlap, or when they occur within a certain period of time of each other, such as <0.1 seconds, <0.25 seconds, <0.5 seconds, <0.75 second, <1.0 seconds, <1.5 seconds ,<2.0 seconds ,<5.0 seconds, <10.0, <30.0 seconds, <45.0 seconds, <60.0 seconds, <90.0 seconds, or <120.0 seconds, or <180.0 seconds between the end of one event and the onset of the other event; a hypopnea that terminates in an arousal; the arousal starts during or shortly after the hypopnea; a respiratory effort related arousal (RERA); an arousal due to an external stimulus; a reduction in airflow that does not meet the criteria for hypopnea (>= 30% reduction in flow) or apnea (>= 90% reduction in flow) ends in an arousal; or as described by the AASM Manual for the Scoring of Sleep and Associated Events cited above and incorporated herein by reference, when an arousal interrupts stage N2 sleep; when an arousal interrupts stage R sleep; when an arousal interrupts stage R sleep followed by a low-amplitude, mixed frequency EEG without posterior dominant rhythm and with slow eye movements; or for a hypopnea if the peak signal excursions drop by >30% of pre-event baseline, the duration of the >30% drop is signal excursion is >10 seconds, and there is a >3% oxygen desaturation from pre-event baseline; and / or in the case of a respiratory effort related arousal (RERA, if there is a sequence of breaths lasting >10 seconds characterized by increasing respiratory effort or by flattening of the inspiratory portion the nasal pressure or PAP device flow waveform leading to an arousal from sleep when the sequence of breaths does not meet criterial for an apnea or hypopnea.

[0107] OVERVIEW OF DISCLOSURESection 1 Introduction to Body SignalsSubsection 1.1 Introduction to Respiratory Inductive Plethysmography (RIP) Subsection 1.2 Examples and Discussion of Certain Embodiments Subsection 1.3 Performance of Preferred Embodiments in First ValidationSection 2 Further System and Device EmbodimentsSection 3 Further Models, Classifiers, and Artificial Neural Networks According to Some Embodiments Described HereinSubsection 3.1 Feature Extraction According to Some EmbodimentsSubsection 3.2 Activity Features According to Some EmbodimentsSubsection 3.3 Pre-Processing According to Some EmbodimentsSubsection 3.4 An Example Classifier According to Some EmbodimentsSubsection 3.4.1 An Example Architecture of A Classifier According to Some EmbodimentsSection 4 Additional Validation Study of An Example Embodiment of an Al Model of thisDisclosure for Predefined Patient GroupsSubsection 4.1 Introduction Material for Additional Validation StudySubsection 4.2 Embodiments termed “Bodysleep2.0”Subsection 4.3 Factors That May Affect the Effectiveness of Some Embodiments of the Present DisclosureSubsection 4.4 A Description of the StudySubsection 4.5 Additional Validation Study Design and Analysis PlanSubsection 4.6 Statistical Analysis of Additional Validation StudySubsection 4.7 Discussion of Additional Validation StudySubsection 4.7.1 Overview of the Complete DatasetSubsection 4.7.2 Long-Term Implications and Practical ApplicationsAccording to Some EmbodimentsSubsection 4.8 Conclusion of Additional Validation StudySection 5 Comparison Data of Embodiments of Body Sleep to other Sleep StudiesSubsection 5.1 Unexpected Results According to Some EmbodimentsSection 6 Methods for Providing a Sleep Study According to Some EmbodimentsSection 7 Additional or Alternative Embodiments of Methods, Systems, and / or DevicesSubsection 7.1 A New Type of Processing Signals from HSAT Devices According to Some EmbodimentsSubsection 7.2 Quality Assurance of HSAT Using Embodiments of Body Sleep Analysis Methods Described HereinSubsection 7.3 A New Type of Processing Signals From PSG According to Some EmbodimentsSubsection 7.4 Managing Treatment of Sleep Disorders According to Some EmbodimentsSubsection 7.5 Calibrating a Simple Sleep Study Device According to Some Embodiments Described HereinSubsection 7.6 Augmenting CPAP Data for Improved Therapy ManagementAccording to Some EmbodimentsSubsection 7.7 Using One or More RIP Belts (For Example, Two RIP Belts) to Diagnose Sleep Apnea According to Some EmbodimentsSubsection 7.8 Diagnosis of Sleep Disorders Other than Sleep Apnea According to Some EmbodimentsSubsection 7.8.1 Periodic Limb Movements of Sleep (PLMS)Subsection 7.8.2 Diagnosis of Narcolepsy According to Some Embodiments Subsection 7.8.3 Dementia Detection According to Some EmbodimentsSubsection 7.9 Advancing Sleep Diagnostics According to Some EmbodimentsSubsection 7.10 Body Position and Activity Using RIP Signals According to Some EmbodimentsSubsection 7.11 Augmenting HSAT Studies to Contain Full PSG Information According to Some EmbodimentsSubsection 7.12 Using Embodiments Described Herein (e.g., As Implemented in Embodiments of a Nox BodySleep2.0) for Augmenting CPAP Data for Improved Therapy ManagementSubsection 7.13 Using Embodiments Described Herein (e.g., As Implemented in Embodiments of a Nox BodySleep2.0) for Determining a Likelihood of Success of a Considered Sleep Disorder Treatment or Projecting a Likelihood of Success of Sleep Disorder TreatmentSubsection 7.14 Obesity and Sleep DisordersSubsection 7.15 The Future of Pharmacologic Therapies in Sleep ApneaSubsection 7.16 Monitoring_Treatment Efficacy and Dose Titration According to Some EmbodimentsSubsection 7.17 Further Embodiments Of Systems, Methods, and DevicesSubsection 7.17.1 Prediction / Proposed Outcome Based on Sleep Endotype According to Some EmbodimentsSubsection 7.17.2 Initial Dose Prediction for Single or Multi-Component Drugs According to Some EmbodimentsSubsection 7.17.3 Use of Multi-Night or Single-Night Sleep Studies for Dose Optimization According to Some EmbodimentsSubsection 7.17.4 Predictive Titration Embodiments to Accelerate Optimization According to Some EmbodimentsSection 8 Detecting Arousals and Sleep from Respiratory Inductance Plethysmography (RIP) and a Related StudySubsection 8.1 IntroductionSubsection 8.2 Materials and MethodsSubsection 8.3 Development of Certain EmbodimentsSubsection 8.4 Participants in the StudySubsection 8.5 Description of Certain EmbodimentsSubsection 8.6 Statistical Analysis of Certain Embodiments Subsection 8.7 Results of The Study Subsection 8.8 Discussion of Certain EmbodimentsSection 9 Clinical Validation of Embodiments Called DeepRespusAT Subsection 9.1 Introduction to Validation Study Subsection 9.2 Embodiments called DeepRespusAT Subsection 9.3 Validation Study Summary Subsection 9.4 Discussion of Validation Study Subsection 9.5 Results of Validation StudySection 10 Methods, Systems, and Embodiments that Include an Al modelSubsection 10.1 Discussion of Model Architecture of Certain Embodiments Subsection 10.2 Further Validation of Model EmbodimentsSection 11 Certain Example, Non-Limiting Embodiments That Include a Snap Connector Section 12 Combinability of Embodiments and FeaturesSection 13 Groups and Enumerated Embodiments of Systems, Devices, and Methods Section 14 Terminology

[0108] Section 1 Introduction to Body Signals

[0109] Preferably, body signals — for example, non-brain signals — may be obtained by non- invasive means or sensors. As used herein, a method, sensor, or procedure may be described as non-invasive when no break in the skin is created and there is no contact with the mucosa, or skin break, or internal body cavity beyond a natural body orifice. In the context of sleep studies or determining a sleep stage of a subject, the term invasive may be used to describe a measurement that requires a measurement device, sensor, cannula, or instrument that is placed within the body of the subject, either partially or entirely, or a measurement device, sensor, or instrument placed on the subject in a way that interferes with the sleep or the regular ventilation, inspiration, or expiration of the subject. For example, a measuring of esophageal pressure (Pes), which is considered the gold standard in measuring respiratory effort, may require the placement of a catheter or sensor inside the esophagus and may therefore be considered an invasive procedure and is not practical for general respiratorymeasures. Other known output values can be derived from invasive measurements, such as direct or indirect measure of intra thoracic pressure PIT and / or diaphragm and intercostal muscle EMG. as esophageal pressure (Pes) monitoring, epiglottic pressure monitoring (Pepi), chest wall electromyography (CW-EMG), and diaphragm electromyography (di-EMG). Each of these methods may suffer from being invasive.

[0110] Non-invasive methods to measure breathing movements and respiratory effort may include the use of respiratory effort bands or belts placed around the respiratory region of a subject. The sensor belt may be capable of measuring either changes in the band stretching or the area of the body encircled by the belt when placed around a subject’s body. A first belt may be placed around the thorax and second belt may be placed around the abdomen to capture respiratory movements caused by both the diaphragm and the intercostal-muscles. When sensors measuring only the stretching of the belts are used, the resulting signal may be a qualitative measure of the respiratory movement. This type of measurement may be used, for example, for measurement of sleep disordered breathing and may distinguish between reduced respiration caused by obstruction in the upper airway (obstructive apnea), where there can be considerable respiratory movement measured, or if it is caused by reduced effort (central apnea), where reduction in flow and reduction in the belt movement occur at the same time.[OHl] Unlike the stretch-sensitive respiratory effort belts, areal sensitive respiratory effort belts may provide detailed information on the actual form, shape and amplitude of the respiration taking place. If the areal changes of both the thorax and abdomen are known, by using a calibration, the continuous respiratory volume can be measured from those signals and therefore the respiratory flow can be derived.

[0112] The inventors have developed a method and system for determining arousals or arousal-associated events based on or using breathing features, body activity features, or a combination of breathing and body activity features but excluding or at least not requiring brain features or cardio features. For example, the method may be based on using only the signals from one or more respiratory inductance plethysmography (RIP) belts intended for measuring respiratory movements of the thorax and abdomen. FIGS. 4a and 4b illustrate an example of respiratory inductance plethysmograph (RIP) belts. FIG. 4a shows an example of the wave-shaped conductors in the belts, and FIG. 4b shows the cross-sectional area of each belt, which is proportional to the measured inductance.

[0113] Other Body Signals

[0114] In addition to or in place of RIP signals, embodiments of the method may include using other physiological signals to detect arousals or arousal-associated events. Other physiological signals may be used to confirm or corroborate arousals or arousal-associated events detected by respiratory inductance plethysmography (RIP), or other physiological signals may be used in combination with RIP signals to detect, determine, or predict arousals or arousal-associated events. Moreover, one or more other physiological signals, different than RIP signals, may alone be the basis of and used to determine arousals during a sleep study using a method similar to that relied on for the determination of arousals using RIP signals. For example, an oximetry signal (SpO2 signal) could be used as a lone or only signal from which an arousal or an arousal-associated event is determined. Other signals may include, but are not limited to, accelerometer signals, audio signals, cardiovascular signals, oximetry, non-cardiac electrode potentials, signals indicating body position, video signals, temperature signals, peripheral arterial tone (PAT) measurements pulse, heart rate, heart rate variability, changes in pulse wave amplitude (PWA), changes in pulse transit time (PTT), and other cardiovascular signals, or galvanic skin response (GSR) or combinations thereof to detect arousals.

[0115] Section 1.1 Introduction to Respiratory Inductive Plethysmography (RIP)

[0116] Respiratory Inductive Plethysmography (RIP) may be a method to measure respiratory related areal changes. As shown in FIGS. 4a and 4b, in RIP, stretchable belts 31, 32 may contain a conductor 34, 35 that when put on a subject 33, form a conductive loop that creates an inductance that is proportional to the absolute cross sectional area of the body part that is encircled by the loop. When such a belt is placed around the abdomen or thorax, the cross-sectional area may be modulated with the respiratory movements and therefore also the inductance of the belt. Conductors 34, 35 may be connected to signal processor 38 by leads 36, 37. Processor 38 may include a memory storage. By measuring the belt inductance, a value is obtained that is modulated directly proportional with the respiratory movements. RIP technology includes therefore an inductance measurement of conductive belts that encircle the thorax and abdomen of a subject. As used herein, a respiratory signal may be obtained by the respiratory signal being received by a processor directly from the RIP belts, by a processor receiving a pre-processed respiratory signal that had originally been obtained from the RIP belts, or a respiratory signal may be obtained by a processor by the processor receiving a respiratory signal that was previously obtained from a subject and stored on a memory storage, either in a raw unprocessed form or in a pre-processed form, and subsequently obtained or received by the processor from the memory storage. The memorystorage may be a separate device from the processor, may be hardwired to the processor, or the stored respiratory signal may be transmitted to the processor, for example, over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a computer system that includes the processor. Alternatively, the respiratory signals may be analyzed in real time.

[0117] In another embodiment, conductors may be connected to a transmission unit that transmits respiratory signals, for example raw unprocessed respiratory signals, or semiprocessed signals, from conductors to processing unit. Respiratory signals or respiratory signal data may be transmitted to the processor by hardwire, wireless, or by other means of signal transmission.

[0118] Resonance circuitry may be used for measuring the inductance and inductance change of the belt. In a resonance circuit, an inductance L and capacitance C can be connected together in parallel. With a fully charged capacitor C connected to the inductance L, the signal measured over the circuitry would swing in a damped harmonic oscillation with the following frequency:until the energy of the capacitor is fully lost in the circuit’s electrical resistance. By adding to the circuit an inverting amplifier, the oscillation can however be maintained at a frequency close to the resonance frequency. With a known capacitance C, the inductance L can be calculated by measuring the frequency f and thereby an estimation of the cross-sectional area can be derived.

[0119] The method for determining arousals or arousal-associated events, such as arousal- associated hypopneas, using breathing signals or breathing signals in combination with other body activity features but excluding or at least not requiring brain features or cardio features may also include using a signal from an activity sensor.

[0120] Section 1.2 Examples and Discussion of Certain Embodiments

[0121] As described below, some methods and systems described herein may be based on using devices such as a Nox HSAT recorder to record RIP or RIP and body activity signals during the night and then subsequently uploading recorded data signals to a computer after the study is completed. This disclosure is not limited to such recorders, and other HSAT recording devices may be used. According to some embodiments, software may be used to derive multiple respiratory parameters from those signals or to derive multiple respiratoryparameters activity parameters from those signals, such as respiratory rate, delay between the signals, stability of the respiration and ratio of amplitude between the two belts.

[0122] When the parameters have been derived, they may then be fed into a computing system. For example, in a first embodiment the parameters may be fed into an artificial neural network computing system that has been trained to predict arousals or arousal- associated events of the subject. An artificial neural network computing system may also be trained to predict the three sleep stages, Wake, REM and NREM, which may be used to plot a simplified hypnogram for the night. The classifier computing system might be different than an artificial neural network. For example, in another embodiment a support vector machine (SVM) method could be used, clustering methods could be used, and other classification methods exist which could be used to classify epochs of similar characteristics into one of several groups. In the first embodiment of the method, an artificial neural network, and preferably a convolutional neural network (CNN) was used. This method can be used on a standard HSAT, may not add any burden to the patient or subject, and may be provided in a fully automated way by the physician.

[0123] According to a preferred embodiment, the inventors have developed a method (referred to by the Applicant Nox as “BodySleep2.0” but is also referred to herein simply as “BodySleep”) of detecting sleep and arousals or arousal-associated events which may include using physiological signals other than EEG, or more generally physiological signals other than brain signals or using non-brain signal groups, or using physiological signals that are not obtained from a brain-machine-interface (BMI).

[0124] In a preferred embodiment of the method respiratory inductance plethysmography (RIP) or respiratory inductance plethysmography (RIP) in combination with one or more activity signals are used to detect arousals. This may be particularly useful to detect arousals following respiratory events, since one signature of the termination of a respiratory event may be large recovery breaths. Recovery breaths may be large breaths following a period of reduced breathing. These breaths typically result in a larger amplitude swing in the measured flow signal than baseline and the breaths flow signals may also have distinct shapes.

[0125] Other embodiments of the method may include using other physiological signals to detect arousals or arousal -associated events. Other physiological signals may be used to confirm or corroborate arousals detected by respiratory inductance plethysmography (RIP), or other physiological signals may be used in combination with RIP signals to detect, determine, or predict arousals. Such other signals may include, but are not limited to, accelerometer signals, Peripheral Arterial Tona (PAT) measurements pulse, heart rate, heartrate variability, changes in pulse wave amplitude (PWA), changes in pulse transit time (PTT), and other cardiovascular signals, or galvanic skin response (GSR) to detect arousals.

[0126] The methods, systems, and devices proposed herein may be used in combination with those described in Applicant’s US Patent Application No. 17 / 026,844, filed at the USPTO on September 21, 2020, and published on March 25, 2021 as US 2021 / 0085242A1, which describes system and method for determining sleep stages based on non-cardiac body signals (i.e., which has been referred to by the Applicant as the first “BodySleep”), the contents of which are herein incorporated by reference. Additionally, the methods, systems, and devices proposed herein may be used in combination with those described in Applicant’s US Patent Application No. 17 / 351,933, filed as the USPTO on June 18, 2021, and published on December 23, 2021 as US 2021 / 0393211 Al, which describes system and method for personalized sleep classifying methods and systems, the contents of which are herein incorporated by reference.

[0127] Although not necessary for the implementation of the arousal-determination method disclosed herein, according to an embodiment, non-cardiac signals can be used to detect sleep stages for every predetermined period of the sleep study, for example, preferably every 30 second period or what may termed an epoch. The resolution of the study, or the length of the periods of the sleep study can be varied. The predetermined periods can be 10 minutes, 5 minutes, 3 minutes, 2 minutes, 60 seconds, 45 seconds, 30 seconds, 20 seconds, or even 10 seconds. When detecting sleep stages every period (for example, 30 second period (epoch)) may be classified as one of Wake, NREM, or REM sleep stages. Other embodiments might classify different length periods into sleep stages, and the sleep stages of interest might be different such as Wake, light sleep, deep sleep, REM; or Wake, NREM 1, NREM 2, NREM 3, REM sleep, or any other sleep stages.

[0128] When detecting the arousals or arousal-associated events, such as an arousal- associated hypopnea, the method of the present disclosure may determine the probability of an arousal or an arousal-associated event occurring at a predetermined interval, such as at every second, and if the probability crosses a certain threshold for a given amount of time an arousal event is scored. The interval for the scoring of arousals may be varied, similar to the epochs for the sleep stage determinations, and may be 10 minutes, 5 minutes, 3 minutes, 2 minutes, 60 seconds, 45 seconds, 30 seconds, 20 seconds, or even 10 seconds, 5 seconds, 3 seconds, 2 seconds, 1 second, or less than 1 second, such as 3 / 4 second, 1 / 2 second, 1 / 4 second, or less. Different embodiments may implement this differently. The one secondinterval may be an arbitrary choice, and how long an interval or period the probability of an arousal has to be above a threshold can also be changed to meet the needs of the sleep study.

[0129] In a preferred embodiment, convolutional neural networks (CNN) may be deployed, which may be a type of artificial neural networks, which in turn may be a type of Al model. Other types of artificial neural networks and / or Al models may also be used. The raw recorded RIP and activity signals may be input into the CNNs and the events may be output. Different types of classifiers can also be used for this purpose and the inputs can be the raw signals or predetermined features of the signals.

[0130] FIG. 5 shows an example of a scored apnea followed by a desaturation and an arousal as determined according to a preferred embodiment. In FIG. 5 the apnea is marked with the orange square on top of the flow signal. The desaturation event is marked by the sea green square on top of the SpO2 signal, and the arousals are the sea green squares on top of the Activity signal. In FIG. 5 the arousals were scored with the current embodiment. FIG. 5 also shows that each of the epochs are classified as NREM, NREM, and Wake sleep stages. This is illustrated below the timeline and above the row of “S” characters. There NREM is painted in sea green and wake in yellow.

[0131] FIG. 6 shows examples of scored hypopneas followed by desaturations and arousals as determined according to a preferred embodiment. The hypopnea events are marked with cyan bars drawn above the flow signal. The reduction in flow during the hypopneas is marked by the reduction in the flow signal amplitude. Desaturation events are labeled and marked with sea green squares on top of the SpO2 signal in the first half of the figure. The arousal events are the sea green squares on top of the Activity signal. FIG. 6 also shows that each of the epochs are classified as NREM sleep stage. This is illustrated below the timeline and above the row of “L” characters. There NREM is painted in sea green.

[0132] Determining Respiratory Related Arousal (RERA) As noted above, a Respiratory Related Arousal (RERA) may be a respiratory event that does not fulfill the criteria of apneas or hypopneas, that terminates in an arousal. Changes in airflow may be determined using the abdomen and thoracic RIP signals as input to a model. Applying the method of the above-described preferred embodiments to score arousals may enable direct scoring of the respiratory events, without outputting the arousals.

[0133] Predicting apnea-hypopnea-index (AHI)

[0134] Using the examples of embodiments described herein, whether using RIP signals, an oximetry signal, or an activity signal, such as an accelerometer signal, either alone or in combination with other non-brain type body signals, one may be able to predict therespiratory events during a sleep study. Based on one described method, a method of outputting the apnea-hypopnea-index (AHI) may also be provided. The AHI is the clinical parameter used to determine if a patient is eligible for sleep apnea treatment. The number of apneas and hypopneas and an estimation of the sleep time may be used to calculate the AHI. One practice is to use the recording time as an estimate of the sleep time. This results in a parameter called the respiratory event index (REI). Using the body sleep method disclosed herein would allow the determination of the actual sleep time and in that case the calculation of an AHI. An index called the respiratory disturbance index (RDI) is the number of apneas, hypopneas, and RERAs per hour of sleep.

[0135] If the AHI is predicted, then directly predicting the AHI severity classification can also be performed. Traditionally there are cutoffs of the AHI that signify if a patient is healthy AHI < 5 events / hour, AHI >= 5 and AHI < 15 a patient may be eligible for treatment depending on other symptoms. A patient with AHI >= 15 is eligible for sleep apnea treatment.

[0136] So the preferred methods disclosed herein may be used to directly predict the AHI classification, the AHI, or the respiratory events.

[0137] Section 1.3 Performance of Preferred Embodiments in First Validation

[0138] According to some preferred embodiments, the method was first validated on 90 sleep recordings from a sleep clinic in the United States. Below are the results of the validation.

[0139] Sleep stage classification in first validation

[0140] As shown in Table 1-1 below, in a first validation process, two embodiments of the Nox BodySleep were validated. A first embodiment used the RIP, Activity, and signals from the pulse oximeter (Pulse Wave and SpO2) as inputs. A second embodiment used only the RIP and Activity signals as inputs. The outputs are labels for each 30 second period (epoch) in the sleep study. The performance of the embodiment was compared with the gold standard, manually scored polysomnography (PSG) sleep studies. A confusion matrix was constructed showing the epoch level agreement in the classification and the Sensitivity, Specificity, Accuracy, Matthews Correlation Coefficient (MCC), and Fl scores calculated.TABLE 1-1

[0141] As shown in Table 1-2 below, the performance of the arousal scoring was validated on data from a sleep clinic in the United States. The performance of the arousal scoring was done by calculating the Sensitivity, Specificity, and Accuracy for the presence or absence of an arousal event within a 30 second epoch. The gold standard manual scoring of PSG sleep studies was used as the reference. The performance was validated for different detection thresholds of the arousal scoring. The performance of the method of this preferred embodiment was compared to the performance of the Noxturnal™ PSG arousal scoring model, which is a released medical device in Europe.TABLE 1-2

[0142] Table 1-3 shows the arousal scoring was used to determine if a reduction in airflow during sleep is considered a Hypopnea. The impact of the arousal scoring from the this preferred embodiment on hypopnea scoring was validated TABLE 1-3

[0143] As shown in Tables 1-4 and 1-5, below, the hypopnea scoring was used to calculate the Apnea-Hypopnea Index (AHI) which is an index of how many apneas and hypopneas occur during each hour of sleep (events / hour). Sleep apnea severity is classified using the AHI index. The impact of the arousal scoring on the sleep apnea severity was investigated for the AHI cutoff values of AHI >= 5 events / hour (Table 1-4), and AHI >= 15 events / hour (Table 1-5). These cutoff values were chosen since they represent the clinical cutoff values used by the Centers for Medicare and Medicaid in the United States to determine if a patient is eligible for sleep apnea treatment.TABLE 1-4TABLE 1-5

[0144] Further, the results show that the method of this preferred embodiment improves the clinical outcomes of patients who undergo HSAT sleep studies by improving the sensitivityand accuracy of the sleep apnea diagnosis. This may therefore be significant as it may indicate that an HSAT sleep study with improved sensitivity and accuracy of the apnea diagnosis may be provided according to the disclosed methods and systems herein without requiring a pulse oximeter, which is a relatively expensive device, adds complexity to the sleep study, is prone to failure, and decreases comfort.

[0145] As shown in Table 1-6 below, in a different embodiment only the thoracic and abdominal RIP signals (RIP Only) may be used to predict the sleep stages and arousals. A third embodiment may use only the activity signals (Activity Only) to predict the sleep stages and arousals. The results again show that the method of this preferred embodiment with only the thoracic and abdominal RIP signals (RIP Only) improves the clinical outcomes of patients who undergo HSAT sleep studies by improving the sensitivity and accuracy of the sleep apnea diagnosis.TABLE 1-6

[0146] Further Tables 1-7 and 1-8 below show a further validation of show that using examples of the preferred methods and systems described herein, very accurate results for determining arousals and arousal -associated events in over 2000 sleep studies can be provided using only RIP belt signals without an activity signal. The performance of the arousal scoring was done by calculating the Sensitivity, Specificity, and Accuracy for the presence or absence of an arousal event within a 30 second epoch. The gold standard manualscoring of PSG sleep studies was used as the reference. The performance was validated for different detection thresholds of the arousal scoring. The performance of the method of this preferred embodiment was compared to the performance of the Noxtumal™ PSG arousal scoring model. These results show that the method of this preferred embodiment improves the clinical outcomes of patients who undergo HS AT sleep studies that are based only on RIP signals (wherein no activity signal and no pulse oximeter signal is required or used) by improving the sensitivity and accuracy of the sleep apnea diagnosis. This may therefore be significant as it may indicate that an HSAT sleep study with improved sensitivity and accuracy of the apnea diagnosis may be provided according to the disclosed methods and systems herein without requiring an activity signal such as an accelerometer or a pulse oximeter, which is a relatively expensive device, adds complexity to the sleep study, is prone to failure, and decreases comfort.

[0147] Table 1-7Table 1-8

[0148] Further Performance and Validation

[0149] According to further embodiments, a deep learning model may be developed to predict arousals, using only respiratory inductance plethysmography (RIP) and activity signal groups. According to some embodiments, the deep learning model may perform a prediction for each recorded second (1 -second intervals) and aggregate those results to score arousal events. In one example embodiment, to train and validate the model, a total of 2216 manually scored PSG sleep recordings were employed from various sleep centers in five countries. The model’s robustness and accuracy was tested, using recordings from a separate sleep center that was not included in training or validation. Additionally, the inventors ensured that the recordings covered all categorical severities of sleep apneas; i.e., normal, mild, moderate, and severe.

[0150] In this performance evaluation, compared with manual arousal scoring, using epochlevel agreement, the model exhibited a sensitivity, specificity, and accuracy of 62%, 86%, and 81%, respectively. The difference in AHI was investigated when using the model’s arousals or no arousals. For AHI>=5, the sensitivity, specificity, and accuracy was 95%, 100%, and 96%, respectively, with arousals, but 68%, 100%, 75% without. Similarly, for AHI>=15, the metrics were 95%, 100%, and 96%, respectively, with arousals, but 54%, 100%, 80%, without. Moreover, for hypopneas, the metrics were 86%, 96%, 94%, respectively, with arousals, a 24% increase in sensitivity compared with not using arousals.

[0151] The embodiments provided herein show that respiratory disturbance related arousals can be detected from the RIP belts. The reason for this is that the breathing in the pre-apnea period may be too shallow to ventilate the CO2 released in the blood, causing acidification in the blood, increasing respiratory effort and finally causing arousal with large recovery breaths to neutralize the blood gassing of CO2. This effect may cause that the recovery breaths can be detected from the RIP bands.

[0152] However, further research and modeling using the above-noted data by the inventors has shown that not only may the arousal detection method detect those respiratory disturbance related arousals correctly, but may also correctly predict other arousals as well. This was entirely unexpected and surprising to the inventors. This is confirmed by what has been called "respiratory response to arousals" occurs that is somehow linked to change of control over the respiration between sleep and wake. This can be determined also in the methods disclosed herein as it may show up in the belt signals as well based on the BodySleep2 validation results and may increase the opportunities of usage dramatically.

[0153] In sum, the detection model performed well, showing that a HSAT without a brainbased signal can be sufficient in order to predict arousals effectively. Additionally, the inventors’ findings show that using the predicted arousals improve the scoring of hypopneas and AHI and that indeed an EEG or brain-based signal may not be necessary for an accurate determination of arousals during a sleep study. Further, as described herein, the inventors have developed a method and system that may accurately detect respiratory and non- respiratory associated arousals by processing respiratory signals, and particularly in a preferred embodiment, RIP signals. This may be achieved by using an artificial neural network (ANN) based analysis that integrates information from both the effect of the change of respiratory control from autonomic to somatic during arousal and the amplitude response at the end of respiratory disorder event. Using this method and a corresponding system, the accuracy for apnea hypopnea index (AHI) analysis from HSAT study may be on par and comparable with PSG results, even if only the RIP signals are being used for the AHI diagnoses.

[0154] It is further noted that the detection of arousals and arousal -associated events based on a RIP based signals may determine or may be used to measure a change from automatic to somatic respiratory control, which may cause respiratory response to arousal. While recovery breaths are a consequence of arousal caused by apnea, the respiratory response to arousal in unrelated of the respiratory condition. This effect in the respiratory signal obtained from the RIP signal and used in the arousal and arousal -associated events as described herein is a "more direct" measure of the arousal than the recovery breath. This is for example the basis for why the method may work for PLMS arousals as described below, in that in these cases there may be no associated recovery breath. Based on this combinational method of detecting respiratory response to arousal and recovery breaths, the arousal and arousal-associated events detection methods described herein may elevate the accuracy of respiratory analysis of arousals from being considered unusable without EEG reference, to provide accuracy on par with PSG scored arousals. Further, the disclosed method and system may provide an effective way for detection for arousals and arousal-associated events that are not apnea or hypopnea based nor based on sleep disordered breathing, but can be based on non-respiratory events such as PLMS or even external stimuli that arouse the subject.

[0155] Section 2 Further System and Device Embodiments

[0156] Although the subject matter of this disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the described features or actsdescribed above, or the order of the acts described above. Rather, the described features and acts are disclosed as example forms of implementing the claims.

[0157] As described at least in Section 1.2 above, Respiratory Inductive Plethysmography (RIP) may be a method to measure respiratory related areal changes based on stretchable belts 31, 32. FIGS. 7A, 7B, and 7C show schematics of a subject 400 sleeping with HSAT sleep study devices. The devices worn by the subject in such as study may include respiratory inductance plethysmography (RIP) belts 451, 452, arranged about the thoracic region and an abdominal region of the subject, respectively. The RIP belts 451 and 452 may transmit, e.g., wireless or through a wired connection, to a recording device 455 which obtains and stores the data of the RIP signals through the study. As shown in FIG. 7A, a further sensor 490, such as an accelerometer or other activity sensor may be applied to a limb or body portion of the subject, such as on the leg. Data obtained by the further sensor 490, such as activity, motion, or accelerometer data can also be transmitted to and recorded by recording device 455. These sensors and devices may be provided to the subject in such a way that the subject can easily and consistently apply the sensors and devices himself (or herself). Belts 451 and 452 may be disposable devices that would be disposed of by the subject after the sleep study is performed. The belts 451,452 may be configured to be worn for multiple nights, after which the belts can be disposed. Further sensor 490 may also be a disposable device.Recording device 455 need not necessarily be attached to belt 451. Recording device 455 may be returned to the home sleep study administrator and the RIP sleep data and the further sensor data obtained and stored therein may be downloaded or otherwise retrieved by the computer of the sleep study administrator. Alternatively, the recording device 455 may further include a memory and a memory storage, and may be provided with a mobile application to interact with and control the RIP belts 451, 452, and to receive data obtained by the belts and the further sensor. The recording device may further be configured to transmit the data in real time, or at the conclusion of the sleep study, or at a later time, through a network or otherwise wireless connection or over the internet, to a data receiving device of the sleep study administrator.

[0158] As shown in FIG. 7B, separate recording devices 471, 472 may be provided to record the signals of the thoracic RIP belt 451 and the abdomen RIP belt 451, respectively. Accordingly, similar to recording device 455, each separate recording device 471, 472 may be configured to record the data obtained from the respectively RIP belt 451,452 and may be either delivered physically or mailed back to the sleep study administrator. Alternatively, the recording devices 471,472 may be configured to transmit the data in real time, or at theconclusion of the sleep study, or at a later time, through a network or otherwise wireless connection or over the internet, to a data receiving device of the sleep study administrator. One or both of recording devices 471,472 may also receive and record and / or transmit data obtained from the signal of the further sensor 490.

[0159] Recording device 455 or separate recording devices 471,472 may be power the RIP belts and may be rechargeable by the subject or patient. Belts 451,452 may be activated when the RIP belts are snapped around the patient or a seal is removed from the belts, and are deactivated when unsnapped or otherwise removed from the subject.

[0160] Lastly, in the embodiment of FIG. 7C, the home sleep study is administered to the subject without a further sensor 490, but with RIP belts 451, 452 only.

[0161] FIG. 8 illustrates a computing device 1000 configured to perform the method of determining arousals of the subject during the sleep study and process the body-signal data (e.g., RIP data). The device 1000 can perform some or all of the steps discussed above. The device 1000 may perform arousal determination method using a utility application, background daemon, or component of an operating system, or combination thereof, executing in conjunction with CPU 1001 and an operating system such as Microsoft Windows 7, UNIX, Solaris, LINUX, Apple MAC-OS and other systems known to those skilled in the art.

[0162] CPU 1001 may be a Xenon or Core processor from Intel of America or an Opteron processor from AMD of America, or may be other processor types that would be recognized by one of ordinary skill in the art. Alternatively, the CPU 1001 may be implemented on an FPGA, ASIC, PLD or using discrete logic circuits as a processor. Further, CPU 1001 may be implemented as multiple processors cooperatively working in parallel to perform the instructions of the inventive processes described above.

[0163] The device 1000 in FIG. 8 also may include a network controller 1006, such as an Intel Ethernet PRO network interface card from Intel Corporation of America, for interfacing with a network 1030. The network 1030 can be a public network, such as the Internet, or a private network such as an LAN or WAN network, or any combination thereof and can also include PSTN or ISDN sub-networks. The network 1030 can also be wired, such as an Ethernet network, or can be wireless such as a cellular network including EDGE, 3G and 4G wireless cellular systems. The network 1030 can also be Wi-Fi, Bluetooth, or any other wireless form of a communication that is known.

[0164] The device 1000 further may include a display controller 1008 for interfacing with a display 1010. A general purpose EO interface 1012 interfaces with input devices 1014 as well as peripheral devices 1016. The general purpose EO interface also can connect to a variety ofactuators 1018. The input devices 1014 can include the various sensors, although additional sensors are not necessary for the system. The input devices 1014 may include an interface to receive data from a recording device 455 in FIG. 7 A, for example.

[0165] A sound controller 1020 may also be provided in the device 1000 to interface with speakers / microphone 1022 thereby providing sounds and / or music.

[0166] A general purpose storage controller 1024 may connect the storage medium disk 1004 with a communication bus 1026, which may be an ISA, EISA, VESA, PCI, or similar, for interconnecting all of the components of the device 1000. Descriptions of general features and functionality of the display 1010, input devices 1014 (e.g., a keyboard and / or mouse), as well as the display controller 1008, storage controller 1024, network controller 1006, sound controller 1020, and general purpose VO interface 1012 are omitted herein for brevity as these features are known.

[0167] Instructions for the performance of the arousal determination method can be stored on computer storage media and performed using a computation / logic circuitry. For example, instructions for the arousal determining method may be performed on a central processing unit (CPU). Computer storage media are physical storage media that store computerexecutable instructions and / or data structures. Physical storage media include computer hardware, such as RAM, ROM, EEPROM, solid state drives (“SSDs”), flash memory, phasechange memory (“PCM”), optical disk storage, magnetic disk storage or other magnetic storage devices, or any other hardware storage device(s) which can be used to store program code in the form of computer-executable instructions or data structures, which can be accessed and executed by a general-purpose or special-purpose computer system to implement the disclosed functionality of the disclosure.

[0168] Transmission media can include a network and / or data links which can be used to carry program code in the form of computer-executable instructions or data structures, and which can be accessed by a general-purpose or special-purpose computer system. A “network” may be defined as one or more data links that enable the transport of electronic data between computer systems and / or modules and / or other electronic devices. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a computer system, the computer system may view the connection as transmission media. Combinations of the above should also be included within the scope of computer-readable media.

[0169] Further, upon reaching various computer system components, program code in the form of computer-executable instructions or data structures can be transferred automaticallyfrom transmission media to computer storage media (or vice versa). For example, computerexecutable instructions or data structures received over a network or data link can be buffered in RAM within a network interface module (e.g., a “NIC”), and then eventually transferred to computer system RAM and / or to less volatile computer storage media at a computer system. Thus, it should be understood that computer storage media can be included in computer system components that also (or even primarily) utilize transmission media.

[0170] Computer-executable instructions may comprise, for example, instructions and data which, when executed by one or more processors, cause a general -purpose computer system, special-purpose computer system, or special-purpose processing device to perform a certain function or group of functions. Computer-executable instructions may be, for example, binaries, intermediate format instructions such as assembly language, or even source code.

[0171] The disclosure of the present application may be practiced in network computing environments with many types of computer system configurations, including, but not limited to, personal computers, desktop computers, laptop computers, message processors, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile telephones, PDAs, tablets, pagers, routers, switches, and the like. The disclosure may also be practiced in distributed system environments where local and remote computer systems, which are linked (either by hardwired data links, wireless data links, or by a combination of hardwired and wireless data links) through a network, both perform tasks. As such, in a distributed system environment, a computer system may include a plurality of constituent computer systems. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0172] The disclosure of the present application may also be practiced in a cloud-computing environment. Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environments may be distributed internationally within an organization and / or have components possessed across multiple organizations. In this description and the following claims, “cloud computing” is defined as a model for enabling on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when properly deployed.

[0173] A cloud-computing model can be composed of various characteristics, such as on- demand self-service, broad network access, resource pooling, rapid elasticity, measuredservice, and so forth. A cloud-computing model may also come in the form of various service models such as, for example, Software as a Service (“SaaS”), Platform as a Service (“PaaS”), and Infrastructure as a Service (“laaS”). The cloud-computing model may also be deployed using different deployment models such as private cloud, community cloud, public cloud, hybrid cloud, and so forth.

[0174] Some embodiments, such as a cloud-computing environment, may comprise a system that includes one or more hosts that are each capable of running one or more virtual machines. During operation, virtual machines emulate an operational computing system, supporting an operating system and perhaps one or more other applications as well. In some embodiments, each host includes a hypervisor that emulates virtual resources for the virtual machines using physical resources that are abstracted from view of the virtual machines. The hypervisor also provides proper isolation between the virtual machines. Thus, from the perspective of any given virtual machine, the hypervisor provides the illusion that the virtual machine is interfacing with a physical resource, even though the virtual machine only interfaces with the appearance (e.g., a virtual resource) of a physical resource. Examples of physical resources including processing capacity, memory, disk space, network bandwidth, media drives, and so forth.

[0175] Section 3 Further Models, Classifiers, and Artificial Neural Networks According to Some Embodiments Described Herein

[0176] Section 3.1 Feature Extraction According to Some Embodiments

[0177] The determination of arousal may be based on or include inputting and / or receiving the raw non-brain signal into a neural network as described above. Additionally or alternatively, determination of arousal may be a two-part problem with the first step in the process being the extraction of features from the raw recordings. In an embodiment, a feature extractor may be written, for example in Python 3.5.5, to perform this task. The extractor may rely on NumPy and / or SciPy. The output of the feature extractor may be a comma-separated values (CSV) file where the rows represent each epoch and the columns contains the features.

[0178] In a first embodiment, the signals used may be those derived from the abdomen and thorax RIP belts. These may include the Abdomen Volume, Thorax Volume, RIPSum, RIPFlow, Phase, and RespRate signals. Additionally, an activity signal from an accelerometer may be used. All the features may be calculated over a 60, 30, 20, 10, 5, or 1 second interval.

[0179] As used herein, Abdomen Volume and Thorax Volume are the RIP signals recorded during the sleep study. The signals may be recorded using the respiratory inductanceplethysmography (RIP) bands placed around or on the thorax and abdomen of the subject under study. The RIP signals may represent volume in the abdomen and thorax during breathing.

[0180] RIPSum is a signal created by adding the samples of Abdomen Volume and Thorax Volume signals. The RIPSum signal is a time series signal of the same number of samples and duration in time as the Abdomen Volume and Thorax Volume signals.

[0181] RIPFlow is the time derivative of the RIPSum signal. The RIPSum signal represents volume and the time derivative represents changes in volume which is flow.

[0182] Phase is a signal that represents the apparent time delay between the recorded Abdomen and Thoracic volume signals. During normal unobstructed breathing the Abdomen and Thorax move together out and in during inhalation and exhalation. When the upper airway becomes partially obstructed the Abdomen and Thorax start to move out of phase, where either the Abdomen or the Thorax will start expanding while pulling the other back. During complete obstruction of the upper airway the Abdomen and Thorax will start moving completely out of phase, whereas one moves out the other one is pulled inwards. In this case the Phase is 180 degrees, measuring the phase difference between the two signals.

[0183] RespRate represents the respiratory rate of the subject under study. The respiratory rate is a measure of the number of breaths per minute and is derived from the Abdomen Volume and Thorax Volume signals.

[0184] The feature extractor and the features extracted by the feature extractor are explained herein below. According to some embodiments, the feature extractor may receive, as an input, the recorded signals of Abdomen RIP, Thorax RIP, and accelerometers. The feature extractor may also receive, as an input, signals derived from those signals, such as the above mentioned RIPSum, RIPFlow, Phase, RespRate, and Activity. The feature extractor may split the signals into epochs of a given second length. For example, the epochs may be 60 seconds, 45 seconds, 30 seconds, 20 seconds, 10 seconds, 5 seconds, one second, and / or any number of seconds between one and sixty long. The feature extractor may output results as a CSV file, and the results may include one or more features that were extracted by the feature extractor. The respiration features are calculated from the RIPSum, RIPFlow and RespRate signals. The features calculated may be designed to give information about changes in the respiratory rate with various methods.

[0185] The first harmonic and DC ratio may be used to estimate respiratory rate variability. The first harmonic and the DC component may be found in the frequency spectrum of a flow signal. For one embodiment of the classifier the RIPFlow was used but some preprocessingrequired. Such preprocessing included before taking the Fourier transform of the signal, all positive values are made 0, which results in the signal being more periodic as the exhalation is more regular. This can be seen in FIG. 3.

[0186] The fast Fourier transform may be applied on the resulting signal and the DC component and the first harmonic peak are located. The DC component is defined as the magnitude at 0 Hz and the first harmonic peak is the largest peak of the frequency spectrum after the DC ratio.

[0187] The respiratory rate variability with this method may be defined as:100 - DCj %Where Hi is the magnitude of the first harmonic peak and DC is the magnitude of the DC component. It has been showed that the RRv is larger in wake and that this size gets smaller as the sleep gets deeper but is larger again in REM sleep. The feature implemented in the final version is just the first harmonic to DC ratio but not the RRv value, since after normalization these values would still be the same.

[0188] There may be 4 features that are extracted from the respiratory rate. These features are calculated using mean, standard deviation and difference between epochs. The RespRate signal is used for these calculations. The mean and standard deviation of the respiratory rate is calculated for each epoch. The root means square successive difference (RMSSD) is calculated with3.2

[0189] The difference mean ratio is then calculated as the ratio of the mean respiratory rate of the current epoch and the previous epoch.

[0190] The breath-by-breath features are based on features which are calculated for each breath. The final features are then calculated by taking the mean, median or standard deviation of the breath features for each epoch. The breaths may be located by running a breath-by-breath analysis on the RIPsum signal of the whole recording to identify all the breaths. The breaths may then be divided between the 30s epochs, with breaths that overlap two epochs being placed in the epoch that contains the end of the exhalation of the breath. The signals used for the feature calculations are the RIPsum, RIPflow, Abdomen Volume and Thorax Volume.

[0191] In a second embodiment, the breath-by-breath analysis may be based on a start of inhalation being marked as the start of a breath and the end of exhalation being marked as theend of a breath. By adding the correctly calibrated abdomen and thorax RIP signal (as, for example, described in U.S. patent application 14 / 535,093, filed November 6, 2014, and published as US 2015 / 0126879; U.S. patent application 15 / 680,910, filed August 18, 2017, and published as US 2018 / 0049678; and U.S. patent application 16 / 126,689, filed September 10, 2018, and published as US 2019 / 0274586, each of which is incorporated herein by reference in their entirety), calculating a time derivative of the resulting calibrated RIP volume signal results in a flow signal representing breathing airflow. The start of inhalation can be determined by finding points in time where the flow signal crosses a zero value from having negative values to having positive values. The end of exhalation can be determined by finding points in time where the flow signal crosses a zero value from having negative values to having positive values.

[0192] In other words, when the RIP flow signal has a positive value air may be flowing into the body, inhalation, and when the RIP flow signal has a negative value air may be flowing out of the body, exhalation.

[0193] It may be noted that high frequency noise in the signal may cause the signal to oscillate, causing multiple zero crossings in periods where the flow rate is low. However, normal breathing frequency may be around 0.3 Hz, so low pass filtering the signal at a frequency around 1-3 Hz can be applied to remove high frequency noise.

[0194] Detecting individual breaths in a sleep recording can be done by using the abdomen RIP signal, the thorax RIP signal, or their sum (RIPsum). Breath onset is defined as the moment when the lungs start filling with air from their functional residual capacity (FRC) causing the chest and abdomen to move and their combined movement corresponding to the increase in volume of the lungs. Functional Residual Capacity is the volume of air present in the lungs at the end of passive expiration and when the chest and abdomen are in a neutral position.

[0195] A RIPsum signal of breathing during sleep may be obtained. The RIPsum starts at a lower bound, End / Start, and rises to an upper bound, Midway point, before it falls back down. The rise of the signal indicates the breath onset. A naive or simple method of detecting the breath onset is to look for points where the derivative of the signal changes sign from negative to positive, or when the derivative crosses the zero value from negative to positive and label them as End / Start. Points where the sign of the derivative changes from positive to negative are the Midway points. However, this naive or simple method suffers from misidentification of End / Start points and Midway points in the presence of noise.

[0196] In the presence of noise, too many points can be identified as End / Start points or Midway points. To mitigate this one can low-pass filter the signal at a frequency high enough to capture the breathing movement and low enough to remove most noise. A cutoff frequency of, for example, 3 Hz could be used, as it is around ten times higher than the breathing frequency. A second mitigation strategy is to investigate the End / Start points and Midway points and identify points which represent noise. One strategy to combine points is to define a threshold value in the signal amplitude which needs to be passed before defining a new End / Start point or a new Midway point.

[0197] A correlation feature is based on the similarity of adjacent breaths. To evaluate their similarity the cross-correlation is used with the coefficient scaling method. The coefficient scaling method normalizes the input signals, so their auto-correlation is 1 at the zero lag. The cross-correlation is calculated for each adjacent pair of breaths and the correlation of the breaths is found as the maximum value of the cross-correlation. The last breath of the previous epoch is included for the correlation calculation of the first breath of the current epoch. The mean and standard deviation are then calculated over each epoch. The RIPSum signal is used for these calculations.

[0198] The breath length for each breath is calculated along with the inhalation and exhalation durations. This may be done using the start, end and peak values returned by the breath finder. For each epoch then the mean and standard deviation of these lengths was calculated. The median peak amplitude of the RIPsum signal is also calculated for each breath over an epoch.

[0199] The median volume and flow of the inhalation, exhalation and the whole breath are calculated for each breath and then the median of all breaths within each epoch is calculated. Along with that, the median of the amplitude of each breath is calculated and the median value of all breaths within each epoch is calculated. This results in 6 features.

[0200] The zero-flow ratio is calculated by locating the exhalation start of each breath. The difference of the amplitude at exhalation and inhalation start is calculated for the abdomen and thorax volume signals and the ratio of the abdomen and thorax values are calculated for each breath. The mean and standard deviation of these values are then calculated for each epoch.

[0201] Section 3.2 Activity Features According to Some Embodiments

[0202] For the activity features the standard deviation over 30, 20, 10, 5, and 1 second interval is calculated and the maximum and minimum difference over 30, 20, 10, 5, and 1second interval is as well calculated. The activity features may be calculated using the activity signal. The activity signal is calculated byWhere x and y are the x and y component, moving in the horizontal plane, of the 3D accelerometer signal.

[0203] Some of the features use the Abdomen and Thorax Flow signals which were calculated by numerical differentiation from the volume signals. The features that use the breath-by-breath analysis use it in the same way as the breath features in the chapter 3.2.

[0204] The mean and standard deviation of the RIPphase signal are calculated over each 30, 20, 10, 5, and 1 second interval.

[0205] Skewness is a measurement on the asymmetry in a statistical distribution. This can be used to look at if the breaths are more skewed to the inhalation part or the exhalation part. It can be seen that the breathing patterns change or how the breathing rhythm changes. The skewness is the 3rd standardized moment and is defined as ki = >3-3

[0206] To calculate the skewness of the breath it is interpreted as a histogram. The signal is digitized somehow, for example, by scaling it between 0-100 (a higher number can be used for more precision) and converted to integers. The skewness may be calculated by at least two ways at this point. The first method is to construct a signal that has the given histogram and then use built-in skewness functions. The second method is based on calculating the skewness directly by calculating the third moment and the standard deviation using the histogram as weights. First, a signal is made x = (1, 2, . . ., n-1, n) where n is the length of the original signal. Then the weighted average is calculated with3.4 where k is the original signal Nis the weighted length of x. The weighted third moment is then calculated with3.5 and the weighted standard deviation with3.6

[0207] The skewness is then calculated with equation 3.4

[0208] This may be done for each breath and the mean and standard deviation of the breaths within one 30 second epoch are calculated. The skewness is calculated for the abdomen, thorax and RIP volume traces. The RIPSum may be used to obtain locations of each breath.

[0209] The ratio of the maximum flow in inhalation and exhalation may be found by first subtracting the mean from the flow signal and then dividing the maximum of the signal with the absolute of the minimum of the signal. The mean of this ratio may be calculated over 30 second epochs. This ratio is both calculated for the abdomen flow and the thorax flow signals.

[0210] The time constant of inhalation and exhalation may also be used as features for the classifier. The time constant T is defined as the time it takes the signal to reach half its maximum value. This is done by first subtracting the minimum value from the whole signal so that the minimum value of the signal is at zero. Half the max value is then subtracted so that the half-way point is at 0 and max(f) = -min(f). Taking the absolute value of the signal then results in a V-shaped signal and the halfway point is then found by finding the lowest point of the signal. The formula is as follows: 3.7

[0211] The time constant may then be calculated for inhalation and exhalation of each breath and averaged over the epoch. This is calculated on each volume signal and their corresponding flow signal. In total this results in 12 features, but of course more or less features may be used.

[0212] Breath length features may also be included, which may be calculated for all volume signals and their corresponding flow signals. First, the peak of the breath is found as the maximum value of the breath. The start of the breath is then found as the minimum value on the left side of the breath and the end as the minimum value on the right side. The inhale, exhale and total length of each breath is then calculated. The breaths are fetched with the breath-by-breath analysis on the RIPSum signal. This results in total of 18 features, but of course more or less features may be used.

[0213] Section 3.3 Pre-Processing According to Some Embodiments

[0214] The CSV files with the features for each recording may be loaded up in Python. Before any training or classification is started, some pre-processing may be required or preferable. The pre-processing may involve normalizing the features for each recording, to make the features independent of the subject in question. For example, if there is a subject Awith heart rate of 80±5 bpm and subject B with heart rate 100±10, they cannot be compared directly. To make them comparable a z-norm may be used which may be defined as

[0215] Where x is a feature vector, is the mean of the feature vector, and a is the standard deviation of the vector. By using the z-norm, each feature takes the value of 0±l and they are therefore independent of subjects and are comparable between sleep stages.

[0216] The pre-processing may also involve converting the labels from strings ('sleep-wake', 'sleep-rem', 'sleep-nl', sleep-n2', 'sleep-n3') to numbers (0, 1, 2, 2, 2). The five given sleep stages may thus be mapped to three stages: 0 - wake, 1 - REM, 2 - NREM. The labels may then be one-hot-encoded as required by the neural network architecture. To explain further, if an epoch originally has the label 'sleep-n2', it will first be assigned the number 2, and then after one-hot encoding, the label is represented as [0, 0, 1],

[0217] Section 3.4 An Example Classifier According to Some Embodiments

[0218] The use of neural networks was considered for the classification task, as neural networks are well suited to learn from large and complex datasets. The use of gated recurrent units (GRU) was considered as gating mechanism to make the classification more time and structure dependent. GRU is a special type of recurrent layer that takes a sequence of data as an input instead of a single instance. GRU provides the network to see the ability to capture the time variance of the data, that is it can see more than just the exact moment it is trying to classify. The structure of a GRU unit according to some embodiments described herein can be seen in FIG. 9.

[0219] According to one embodiment, the implementation and training of the neural network was performed in Python, using the Keras machine learning library, with TensorFlow backend. TensorBoard was used to visualize and follow the progress of the training in realtime. The training of the classifier, however, is not limited just to that language or library, and rather they are mentioned as examples of ways to train the classifier in accordance with some embodiments described herein.

[0220] Section 3.4.1 An Example Architecture of A Classifier According to Some Embodiments

[0221] After experimenting with different neural network architectures and tuning hyperparameters, a robust classifier embodiment was converged on. In this embodiment, the final classifier is a neural network, having three dense layers (each with 70 nodes), followed by a recurrent layer with 50 GRU blocks. The output layer of the network has of 3 nodes,representing for each timestep the class probabilities that the given 30 sec. input window belongs to the sleep stages wake, REM and NREM, respectively. A diagram of an example network can be seen in FIG. 10 where n is the number of features fed to the network.

[0222] While a particular number of layers, nodes, and blocks is discussed in relation to this embodiment, the present disclosure is not limited to any such particular number. The specific numbers associated with this embodiment merely represent one embodiment of the classifier converged to after rigorous experimentation by the inventors.

[0223] In some embodiments, the classifier may be simplified to a single neural network, with both dense layers and a recurrent layer, whereas the previous classifier was composed of two separate neural networks (a dense one and a recurrent one). Further, early stopping may be introduced to minimize training time and to help reduce overfitting. Learning rate was also changed from being static to dynamic, so it is reduced on plateau. Other hyper-parameters were also changed, such as the dropout rate and the timesteps for the recurrent network. The new model was easier to tune and gave a higher cross-validated Fl -score.

[0224] Some variations of the structure of the original classifier embodiment may include:1. Skipping the dense pretrained model, keeping the same structure for the RNN model;2. Use bidirectional LSTM model, instead of a GRU model;3. Change patience in “Reduce learning rate on plateau”, tried values between 2-10;4. Tried timesteps= 10, future=5;5. Cascaded binary classifier, where first classify sleep-wake, then classify sleep into nrem / rem. a. Tried two versions of rem-nrem classification, first using weights=0, performed badly b. Second training only on rem-nrem, performed better than the first version;6. Ensembling models trained with different seeds and different features;7. tanh activation instead of relu in the dense net, for a balanced input to the RNN;8. Try leaky-relu activation instead of relu, in the dense net.

[0225] As used herein, RNN is Recurrent Neural Network a type of an artificial neural network which learns patterns which occur over time. An example of where RNNs are used is in language processing where the order and context of letters or words is of importance.

[0226] LSTM is Long-Short Term Memory a type of an artificial neural network which learns patterns which occur over time. The LSTM is a different type of an artificial neural network than RNN which both are designed to learn temporal patterns.

[0227] GRU is Gated Recurrent Unit, a building block of RNN artificial neural networks.

[0228] Secondly, some variations of the structure of the current classifier described in chapter 5.1 may include: .1. The dense layer preceding GRU has 50 nodes instead of 70;2. The GRU layer with 70 nodes instead of 50;3. Using dropout values from 0.20-0.50 (dropout of 0.22 performed best).

[0229] As shown by the embodiments described herein, there may be many alternative neural network structures that would yield a comparative or similar result. There may even be neural network structures, such as Convolutional Neural Networks (CNN), which as noted above can be preferable as such networks can use the raw recorded signals without having to have the features extracted or predetermined as done according to some embodiments described herein.

[0230] The number of layers, number of units, the connection between layers, the types of layers (RNN, LSTM, Dense, CNN, etc), activation functions, and other parameters can all be changed without reducing the performance of the model. Therefore, this disclosure should be not limited to a particular number of layers, number of units, the connection between layers, the types of layers (RNN, LSTM, Dense, CNN, etc.), activation functions, or other parameters that can be changed without reducing the performance of the model.

[0231] Although the subject matter of this disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the described features or acts described above, or the order of the acts described above. Rather, the described features and acts are disclosed as example forms of implementing the claims.

[0232] Section 4 Additional Validation Study of An Example Embodiment of an Al Model of this Disclosure for Predefined Patient Groups

[0233] Diagnostics for sleep -disordered breathing (SDB) typically involve labor-intensive, in-laboratory Polysomnography (PSG), accompanied by manual scoring from a sleep technologist. The inventors performed a retrospective study which validated the performance of one embodiment of the Nox BodySleep2.0 (herein simply “BodySleep”), which in this case included a specialized CNN-based Al analysis, in conjunction with Home Sleep Apnea Tests (HSAT) for accurate Apnea-Hypopnea index (AHI) classification, across diverse subgroups.

[0234] Sleep Data from various sleep centers were used, with a total of N = 2477 sleep studies used in the analysis. The subgroups considered for this study were demographics, comorbidities, and medication types. The disclosed “BodySleep” embodiment was comparedto manual scoring using percentage agreement, predictive values, cohen’s kappa, and 95% confidence intervals derived from bootstrapping.

[0235] The analysis included in the embodiment exhibited strong agreement with manual scoring of AHI classification across most subgroups. For AHI thresholds of 5, 15, and 30, the overall percentage agreement (OP A) was observed to be 95%, 92%, and 95% respectively. Predictive values were also strong, with a positive predictive value (PPV) of 97%, 96%, and 94% for the same AHI thresholds. Cohen’s Kappa values ranged from 0.84 to 0.87, indicating substantial agreement, and Fl scores were consistently high, ranging from 0.89 to 0.96.

[0236] Embodiments of “Body Sleep” disclosed herein (also referred to as the “Nox BodySleep2.0”) thus may show to be a viable tool for accurate AHI severity classification in HSAT studies, making it a potential cost-saving and accessible alternative to manual PSG scoring. While this embodiment performed consistently well across most subgroups, certain subgroups with limited data may require further investigation.

[0237] Section 4.1 Introduction Material for Additional Validation Study

[0238] Approximately one-third of a person’s life is spent sleeping, with the average adult requiring 7-9 hours of sleep each night for optimal health and well-being. However, fast-paced society and lifestyle choices can often interfere, resulting in a large portion of adults sleeping fewer hours than recommended. Sleep can be divided into three stages: wakefulness, rapid eye movement sleep (REM), and non-rapid eye movement sleep (NREM). which is subdivided into three stages of N1-N3. During NREM sleep, the brain activity slows down, and physical renewal occurs. During REM sleep, brain activity increases, but the muscles are mostly paralyzed. In healthy adults, these sleep stages appear in a predictable cycle pattern throughout the night. This roughly 90-120 minute cycle can be influenced and disrupted by various factors, that decrease the quality of sleep. Sleep quality is influenced by a range of factors including diet, age, physical activity, medication, genetic factors, environmental factors, sleep duration, and sleep disorders.

[0239] Sleep disordered breathing

[0240] Sleep-disordered breathing (SDB) refers to a group of sleep disorders characterized by respiratory events that can occur during sleep. Those disorders include, but are not limited to, obstructive sleep apnea (OSA) and central sleep apnea (CSA).

[0241] OSA is a common disorder of repeated upper airway collapse during sleep. A complete or partial collapse results in respiratory events of apnea or hypopnea, respectively. An apnea is defined as a 90% reduction in airflow for 10 seconds or more. Hypopnea is defined as >30%reduction in airflow for 10 seconds or more, accompanied by either a >3% oxygen desaturation or an arousal event. The severity of OSA is determined based on the apnea-hypopnea index (AHI), representing the average number of apneas and hypopnea events per hour of sleep. The severity is determined by the American Academy of Sleep Medicine (AASM) where a score of fewer than 5 apneas per hour is considered a normal score, between 5 and < 15 apneas per hour indicates mild OSA, 15 to < 30 apneas per hour indicates moderate OSA, and >30 apneas per hour indicates severe OSA.

[0242] The global prevalence of OSA is estimated to be almost one billion people worldwide. Obesity, male sex, and increased age are the main risk factors of OSA. Common symptoms of OSA include loud snoring, sleep fragmentation, and excessive daytime sleepiness. Patients with OSA are often unaware of their loud snoring and breathing cessations. This lack of symptom awareness, coupled with a lack of education relating to the disorder and healthcare systems mainly focusing on acute illnesses, causes OSA to be severely underdiagnosed and undertreated.

[0243] Sleep studies

[0244] The most comprehensive sleep study is an in-laboratory polysomnography (PSG), also known as a type 1 sleep study, considered the gold standard for assessing sleep and OSA. This study necessitates an overnight visit to a sleep laboratory, where multiple physiological variables are recorded. By accurately determining the sleep stages and respiratory events, these signals allow for precise AHI scoring. Home sleep apnea tests (HSAT) encompass type 2-4 sleep studies allowing the study to be performed at home. A type 2 study uses a portable PSG device, which is typically set up by a sleep technologist in a laboratory, at the patient’ s home, or in some cases by the patients themselves using detailed guidelines. Self-applied somnography (SAS) and an enriched HSAT test (HSAT+) are notable types of type 2 studies, with SAS utilizing frontal electroencephalogram (EEG) and electrooculography (EOG) signals, and HSAT+ using a reduced EEG, allowing for precise hypopnea scoring. Type 3 and 4 sleep studies include fewer channels. Type 3, also called a polygraph, consists of the same signals as a PSG study, excluding the EEG, EOG, electrocardiogram (ECG), leg electromyography (EMG), and chin EMG. Type 4 sleep studies narrow it further to only one to three channels. However, only one type of type 4 study has been accepted by the AASM as a definitive diagnostic tool. Table 2-1 provides an in-depth comparison of these sleep studies.Table 2-1: Comparison of measurements for different types of sleep studiesMeasurements Type 1 Type 2 Type 3 Type 4At home X X XIn a laboratory XSleep technologist XElectro-encephalogram (EEG) X X / Electro-ocoulogram (EOG) X X / Electro-cardiogram (ECG) X / / Chin Electro-myography (EMG) X / / Leg Electro-myography (EMG) X X / Respiratory flow X X / / Nasal vs mouth breathing X XRespiratory movements (RIP belts) X X XOxygen saturation X X X XHeart rate X X X XBody position X X X / Video XAudio X / / / Generally included: X. Can be included: / . EEG: Electro-encephalogram; EOG: Electrooculography; ECG: Electro-cardiogram; EMG: Electro-myography; RIP: Respiratory inductance plethysmography.

[0245] Using HSAT is a relatively new method of measuring SDB and can be more convenient for patients. It is less expensive than an in-laboratory PSG and allows the patient to sleep in a familiar home setting as opposed to a sleep laboratory. However, limitations of type 3-4 sleep studies include a tendency to underestimate OSA severity, primarily because it calculates the AHI based on total recording time rather than total sleep time. Additionally, the absence of EEG signals in HSAT also impacts their ability to identify arousal, resulting in a potential underestimation of hypopneas. With the integration of machine learning (ML) algorithms or analysis such as embodiments of BodySleep2.0 disclosed herein, the data from HSAT can be used to score sleep stages and detect arousals, bypassing the need for an EEG. Many patients that could be accurately assessed by an HSAT study, provided it has a mechanism to score sleep stages and detect arousals, are sent for an in-laboratory PSG. Individuals with an AHI < 5 from an HSAT study may be invited for an in-lab PSG toconfirm the absence of SDB. A positive SDB diagnosis, specifically OSA, is met if either AHI or Respiratory Disturbance Index (RD I) is > 15, or AHI or RDI > 5 along with a documented comorbid condition, such as excessive daytime sleepiness. The PSGis unquestionably a vital tool for patients with complicated comorbidities, to make a precise clinical diagnosis. Using new diagnostic techniques could, however, result in better use of the sleep laboratory’s current capacities for patients who need those resources. Smart diagnostic devices with built-in automatic data processing algorithms or analysis make it possible to detect SDB more precisely at home without using time-, personnel-, and cost-consuming PSG tests. The gap between the high prevalence of SDB and the limited diagnostic capabilities could be filled by improving the diagnostic accuracy of HSAT by using more sophisticated diagnostic methods than PSG.

[0246] Deep learning with sleep studies

[0247] Embodiments described herein may utilize different classifiers and feature determination methods that have been trained on datasets with thousands of participants. During testing, these embodiments have achieved sleep staging accuracy similar to interrater reliability of manual scoring. Sleep staging is a time-consuming process that may require manual inspection by a sleep technician, in batches of 30-second epochs, of EEG, ECG, and EMG. The manually scored sleep staging is evaluated with inter-rater reliability as quantified by kappa ( / c) that reflects epoch-by-epoch agreement above chance. Utilizing PSG data, annotated by sleep technicians, may offer an extensive repository of labeled data that proves valuable for training embodiments that include deep learning algorithms to evaluate sleep disorders.

[0248] Using embodiments that include Al to determine sleep stages and score respiratory and movement events according to some embodiments described herein may reduce the time sleep technologists must spend on PSG scoring, allowing them to devote more time to patient needs. This could potentially lead to savings in both cost and time for patients and clinicians, as well as a reduction of tedious waiting for in-lab PSG.

[0249] Section 4.2 Embodiments termed “Bodvsleep2.0”

[0250] Some embodiments of the methods, systems, and devices disclosed herein, referred to as Nox BodySleep 2.0 (Nox Medical, Iceland), may include an Al model such as a deep learning algorithm, which may be based on a convolutional neural network developed by the inventors at Nox Medical, and may classify 30-second epochs of a type 3 sleep study into the states of REM, NREM, and wake. The analysis was designed to predict changes in autonomic functions correlating with the different sleep stages and arousals. Example embodiments may extract and / or receive data from actigraphy and / or respiratory inductance plethysmography (RIP)belts. Example embodiments may use these signals to differentiate between REM, NREM, and wake, detect arousals, and detect respiratory events and motor activity during sleep that are caused by increased sympathetic activity.

[0251] These signals can offer insight into arousal events, which can be used in the identification of hypopneas. Furthermore, these alternative signals can be more easily gathered in anHSAT study, which may reduce the reliance on manual scoring and decreasing stress on sleep centers. The use of CNNs paired with RIP and actigraphy signals for the automatic scoring of arousal events and detection of hypopneas as described herein may be beneficial due to the CNN’s proficiency in feature extraction. However, the effectiveness of this approach may be compromised due to individual variability, particularly demographics, the presence of a comorbid condition, or medication usage.

[0252] Section 4.3 Factors That May Affect the Effectiveness of Some Embodiments of the Present Disclosure

[0253] Demographics

[0254] Demographics provide insights into population characteristics, enabling researchers to analyze trends and patterns to better understand the healthcare needs of a specific population. By collecting information about sex, age, and body mass index (BMI), it is possible to gain a better understanding of the potential limitations of algorithms that are being applied in healthcare settings. Studies have shown that OSA is more prevalent in males compared to females. Epidemiological studies of OSA excluded females until the early nineties. The prevalence of OSA symptoms seems to differ between males and females. Males generally have a higher snoring index compared to females, who less frequently report snoring. Females instead report symptoms like headaches, fatigue, depression, sleep disturbances, and anxiety, these symptoms are often misdiagnosed as insomnia or depression. The prevalence of OSA among females appears to be somewhat connected to different developmental stages such as puberty, pregnancy, and the postmenopausal state. A study by Koo et al. has focused on female sex hormones, to explain the differences in the prevalence of OSA between the sexes.

[0255] In addition to sex, the age of individuals is also known to have an effect on OSA. The importance of early diagnosis, treatment of OSA, and patient management is becoming more apparent. It is especially important for older individuals because they have a poorer perception of their symptoms. Individuals with OSA have exhibited more impairment in physical and cognitive functions compared to individuals without OSA.

[0256] Another factor that can affect the prevalence of OSA is physiological properties like weight. Overweight and obesity are significant public health concerns worldwide and the bodymass index (BMI) is widely used to measure it. Individuals with obesity are also more likely to have OSA, compared to individuals with lower BMI. Fat distribution in females tends to be more peripheral compared to males and settles around hips, buttocks, and thighs. Excess fat in males tends to accumulate more centrally on the abdomen and neck. The difference in fat distribution between sexes may be a factor in the variation in OSA prevalence, as more adipose tissue settling centrally and around the airway is related to an increased risk of OSA.

[0257] Due to the potential differences in symptoms experienced by individuals based on factors such as gender, age, and physiological characteristics, it is crucial to ensure that healthcare solutions are equally effective for all. Therefore, it is essential to validate any new healthcare solution across diverse groups and subgroups to determine areas for improvement or assess its adequacy.

[0258] Comorbidities

[0259] The relationship between OSA and various comorbidities is complex, with conditions potentially influencing each other with a bidirectional relationship, increasing both the risk of onset and exacerbation of existing symptoms.

[0260] The severity of various comorbid conditions has been found to increase with OSA severity, and studies have reported OSA as an independent risk factor for metabolic, cardiovascular, renal, and mental health disorders, among many others. The interrelation of OSA and its comorbidities is further highlighted by treatment for OSA such as positive airway pressure (PAP) being successful in protecting against the worsening of prognosis, and reducing symptoms of many comorbid disorders. Type 2 diabetes and OSA share risk factors of obesity and aging, and symptoms such as decreased sleep quality Type 2 diabetes may influence respiration and sleep patterns through autonomic dysfunction in upper airway stability. Autonomic neuropathy, which is common in diabetes, may also affect breathing, in addition to other autonomic body functions.

[0261] Asthma is an inflammatory condition of the airways that leads to episodes of wheezing, breathlessness, chest tightness, and coughing. These symptoms are worse at night and in the early mornings, with asthma patients often waking up due to these symptoms, leading to frequent sleep fragmentation. Nocturnal asthma may affect respiration and movement signals, due to shortness of breath, variable expiratory airflow limitation, and nasal congestion from chronic rhinosinusitis, a common comorbidity with asthma.

[0262] Seasonal allergies may affect respiration through nasal congestion and obstruction, as well as inflammation of the upper airway. Negative pressure in the pharynx from allergic rhinitis may increase nasal resistance, predisposing the upper airway to collapse. Additionally,nasal congestion associated with allergic rhinitis could cause sleep fragmentation, due to increased negative intrathoracic pressure swings interfering with respiration patterns.

[0263] Heart failure (HF) has been identified as a risk factor for the development of central sleep apnea (CSA). In patients with HF, Cheyne-Stokes respiration is the most common form of CSA, characterized by periodic cycles of crescendo-decrescendo breathing that result in apnea or hypopnea episodes. Hyperventilation, circulatory delay, and cerebrovascular reactivity have been found to occur during sleep in patients with HF, leading to respiratory instability. This change in respiratory patterns has been suggested to be due to increased respiratory control response to changes in partial pressure of carbon dioxide (PaCCh). Further complexities to sleep disturbances may arise from comorbid conditions that may subtly influence sleep. For instance, cardiovascular conditions such as atrial fibrillation, heart disease, and hypertension have a high comorbidity rate with SDB. While their influence on respiration or movement during sleep may not be explicit, these conditions are associated with heart rate variability and blood pressure fluctuations that could indirectly affect sleep quality and patterns. Since these conditions may alter sleep dynamics such as respiration or sleep patterns, it may be important that the usage of embodiments disclosed herein that may include Al algorithms for sleep scoring is not only accurate for the broader public but also reliable for those with a comorbid condition.

[0264] Medications

[0265] Various medications drugs can have profound effects on sleep and its architecture. Beta-blockers are a large group of drugs commonly used to treat hypertension, coronary artery disease, and heart failure. Their effect on the body includes lowering heart rate, blood pressure, and cardiac output. Non-selective beta-blockers also tend to cause contraction of smooth muscles which can lead to bronchoconstriction, a tightening of the airways, in predisposed individuals. This could lead to increased respiratory effort. The effects of betablockers on sleep do seem to vary depending on studies and their specific properties.

[0266] Antidepressants are another group of drugs that significantly impact sleep by altering physiological patterns of sleep stages, particularly in REM sleep. These include selective serotonin reuptake inhibitors (SSRIs), norepinephrine-dopamine reuptake inhibitors (NDRIs), serotonin antagonist and reuptake inhibitors (SARIs), and serotonin-norepinephrine reuptake inhibitors (SNRIs). Antidepressants can alter sleep quality through various mechanisms, including the activation of serotonergic 5-HT2 receptors and changes in noradrenergic and dopaminergic neurotransmission.

[0267] Benzodiazepines (BDZ) are also thought to affect sleep architecture. A very recent systematic review of the literature on BDZ and its effects on sleep reported an increase in time spent in NREM stage 2, a decrease in NREM stage 3 and 4, and also a decrease in REM sleep time in individuals who use BDZ. These changes could potentially lead to concentration difficulties, memory impairment, and weight gain. Studies have also shown, via questionnaire, that withdrawal from BDZ use can improve sleep disturbances and daytime sleepiness over time. Furthermore, BDZ are also thought to affect the arousal threshold. In a study on chronic pain patients using opioids, BDZ seemed to slightly depress respiration but also increased the respiratory arousal threshold resulting in a reduced sleep apnea risk and severity with these patients.

[0268] Amphetamine (AMP), atomoxetine (ATX), and methylphenidate (MPH) are stimulant drugs. They are all sympathomimetic drugs that increase noradrenergic and dopaminergic transmission, which impacts blood pressure and heart rate.

[0269] Opioids are known to promote respiratory instability. Opioid-induced CSA is today the second most common type of CSA and occurs in up to 24% of opioid users. Research has indicated that severe SDB, specifically CSA, is common in individuals undergoing long-term opioid therapy. These individuals have a higher frequency in central apneas and a lower arousal index than those, not under opioid therapy. The association between opioid use and OSA is somewhat unclear but a recent randomized controlled trial from 2020 reported that morphine altered respiratory control but not other OSA phenotypes such as airway collapsibility, pharyngeal muscle responsiveness, and arousal threshold.

[0270] Considering that medications can influence respiratory effort, sleep pattern, sleep onset, and total sleep time, it is important to recognize that medications can impact the results of a sleep study. Therefore it is important to ensure, if algorithms are used for AHI scoring, that they give reliable results, not just for the general population but also for individuals using different types of medications.

[0271] Section 4.4 A Description of the Study

[0272] Aim and obi ective

[0273] The aim of the study was to validate the performance of the one embodiment described herein (referred to BodySleep2.0 or simply as “BodySleep”), for AHI and AHI categories to manually scored PSGs and enriched home sleep apnea tests (HSATs+) on different subgroups. The subgroups include age, sex, BMI, and different comorbidities and medications. The objective of these investigations is to determine if the embodiment performs well compared to the reference method and if its performance is different in sub-groups thatcould require further investigations, and data collection, or be considered as a contraindication.

[0274] Data Collection

[0275] The data collected included manually scored PSG (Nox Al, Nox Medical, Iceland) and HSAT+ (Nox T3, Nox Medical, Iceland) sleep studies along with the individuals’ additional information, for example, gender, age, medications, and comorbidities. The studies were conducted in Georgia, USA, at the Hospitals e Clinicas CUF (Lisbon, Portugal). The necessary local permissions to collect, store, process, and use the data for the purposes of clinical validation were acquired by Nox Medical or their research collaborators.

[0276] Study Population

[0277] The initial datasets included 4,583 sleep studies: 2,994 PSG and 1,589 HSATs+. After removing duplicates, the datasets were reduced to 2,968 and 1,330 recordings, respectively. Some general exclusion criteria were applied. All daytime recordings were excluded, that is recordings that started before 6:00 pm or after 6:00 am, recordings with shorter than 4 hours of recorded sleep, recordings of individuals under 18 years old, and recordings that contained no manually scored respiratory or arousal events. Individuals were categorized by age, gender, BMI, comorbidities, and medications that could have affected their sleep or respiratory system. All subgroups were looked at individually and recordings with missing values for the subgroups being analyzed were excluded. The flowchart 1100 of FIG. 11 depicts the various exclusion criteria and the final dataset values, following the general exclusion. FIG. 11 shows the general exclusion process for all groups: demographics, comorbidities, and medication, wherein PSG is a Polysomnography; HSAT is a Home Sleep Apnea Test; and AHI is a Apnea-hypopnea Index. At 1101, the PSG data set branch began with N = 2968 recordings. At 1110, 363 recordings were excluded due to being less than 4 hours in bed. At 1120, 30 records were excluded for missing scoring. At 1130, 452 recordings were excluded for being under age 18. At 1140, PSG branch remained with 2121 recordings with a mean AHI of 18.9 ± 20.6. The HSAT branch began with 1330 recordings at 1105. At 1115, 658 recordings were excluded for being in bed less than 4 hours. At 1125, 316 recordings were excluded for missing a score. The HSAT branch remained at 1135 with 356 recordings with a mean AHI of 25.9 ± 23.5.

[0278] The validation based on demographics was split into three main categories: sex, age, and BMI, which were additionally divided into subgroups. When the categories were analyzed additional recordings had to be excluded in the merged dataset. There were six recordings that had missing sex, nine had missing BMI, and 145 had missing age after the general exclusion criteria had been applied. The recordings that were left to be validated for the sex, BMI, andage category were N = 2471, N = 2458, and N = 2332 respectively. The average AHI after the additional exclusion was 19.9 ± 21.1, 20.0 ± 21.2, and 20.0 ± 21.2 respectively for the categories.

[0279] For the validation of the comorbidity group, additional N = 1490 recordings were excluded after the general exclusion criteria had been applied. A total of N = 973 recordings were left to be validated. The average AHI was 15.2 ± 22.3. The individuals that remained reported 14 different comorbidities which were self-reported through a questionnaire. The comorbidities subgroups and the number of individuals in each group can be seen in Table 2- 10.

[0280] For the validation of the medication group, additional N = 2081 individuals were excluded after the general exclusion criteria had been applied. A total of N = 396 recordings were left to be validated. The average AHI was 18.5 ± 21.0. The individuals that remained, reported the use of nine different medications through a self-reported questionnaire, five being anti-depressants. The medication subgroups and the number of individuals in each group can be seen in Table 2-13.

[0281] Section 4.5 Additional Validation Study Design and Analysis Plan

[0282] This was a retrospective data analysis study. The data included manually scored PSGs (Nox Al, Nox Medical, Iceland) and HSATs+ (Nox T3, Nox Medical, Iceland) sleep studies accompanied by the individuals’ demographic data and additional information on their comorbidities and medications. An enriched home sleep apnea test (HSAT ) is a type of home sleep study with additional EEG consisting of one frontal electrode and one ocular electrode, where arousals are scored for more accurate hypopnea scoring. The reference AHI represents the AHI from manually scored PSGs and HSATs+. The test AHI was obtained by removing signals from the PSG and HSAT± studies and only leaving RIP signals and actigraphy which were then scored by the BodySleep analysis, as disclosed herein. By reducing the PSG and removing signals like EEG, EOG, and ECG, the study resembles an HSAT. This process can be considered further in FIG. 12, which shows a visual representation 1200 of how test and reference AHI were obtained. 1210 shows the dataset with all recordings PSG / HSAT±. At 1215, EEG, EOG, and EMG data are removed for the test branch. At 1225 the dataset of the HSAT branch is reduced (i.e., “Reduced PSG”). At 1235 an embodiment of the disclosed method was performed, termed “BodySleep2.0 Analysis”, following the methods and using the system described herein. At 1245 an automatic respiratory analysis was performed. And at 1255, Test AHI was produced. The reference, regular PSG / HSAT± branch begins at1220. The recordings of the full PSG / HSAT+ dataset are manually scored at 1230, at 1240 an automatic respiratory analysis is performed. And at 1250 the reference AHI is produced.

[0283] Section 4.6 Statistical Analysis of Additional Validation Study

[0284] Exploratory parameters

[0285] The exploratory parameters were chosen to represent the level of agreement and the diagnostic performance between the manual scoring and the automatic scoring from BodySleep2.0, as disclosed herein.• Positive percentage agreement (PPA), where individuals in the group are identified correctly as having AHI > 5.• Negative percentage agreement (NPA), where individuals in the groups are identified correctly as having AHI < 5.• Overall percentage agreement (OP A), where individuals in each group are correctly identified as having either AHI > 5 or AHI < 5.• Positive Predictive Value (PPV), evaluates the proportion of positive AHI > 5 test results that truly are positive based on OSA prevalence in the general population.• Negative Predictive Value (NPV), evaluates the proportion of negative AHI < 5 test results that truly are negative based on OSA prevalence in the general population.

[0286] Bootstrapping was used to build a sampling distribution to calculate the 95% confidence intervals for different subgroups. Sampling was done on the sleep study level. Additionally, Bland-Altman plots and Cohen's Kappa were used to assess the level of agreement or reliability between the reference method and an embodiment disclosed herein, BodySleep2.0, and the Fl score was used to evaluate the accuracy and reliability of the classification models’ performance.

[0287] Technology

[0288] This study utilized Python 3.11 as the main programming language, along with libraries such as Pandas 2.0.3 for data manipulation, Matplotlib 3.7.2 for data visualization, Numpy 1.25.2 for data manipulation, and Skleam 1.3.0 for constructing confusion matrices. Git was employed for version control.

[0289] Results: Overall Performance on The Study Cohort

[0290] The study included a total of 4298 sleep studies, and after removing duplicates and applying the exclusion criteria for having slept under 4 hours, missing AHI scoring, or beingunder 18, 2477 were considered eligible for analysis. Among the 2477 eligible participants, there were 1371 men, 1095 women, and 11 unknown, with an average age of 50 ± 17 years. AHI mean score was 20 ± 21 and a median score of 13. Table 2-2 displays descriptive statistics for all the eligible individuals after applying the above-mentioned exclusion criteria. Table 2-2: Descriptive Statistics of Individuals Health MetricsMetric Min Max Mean ± Std Median Interquartile rangeAge [years] 18 99 50 ± 17 51 26Weight [kg] 22 250 93 ±27 89 32Height[cm] 121 206 172 ± 10 172 15BMI [kg / 2]0 4 84 3 1 ± 9 30 10AHI [ / h] 0 143 20 ± 21 13 22Total Sleep Time [min] 241 627 349 ± 57 347 67ODI3 [ / h] 0 149 17 ± 19 10 18BMI: Body Mass Index; AHI: Apnea-Hypopnea index; 0DI3: 3% Oxygen desaturation index.

[0291] Agreement

[0292] Table 2-3 shows the agreement statistics (PPA NPA and OP A) and the 95% confidence intervals (CI) from bootstrapping for PSG and HSAT+ studies at different AHI thresholds. The bounds of the Cis for PPA, NPA, and OPA were very high for all thresholds. As the AHI thresholds increased to 15 and 30, there was a decrease in bounds for PPA accompanied by an increase for NPA.Table 2-3: Agreement on AHI severity classification for AHI >5, AHI > 15 and AHI >30PPA [%] NPA [%] OPA [%]AHI >5 96 [95" 97] 91 [89, 94] 95 [94' 96]AHI > 15 87 [85, 89] 97 [96, 98] 92 [91, 93]AHI >30 85 [82, 88] 99 [98, 99] 95 [95, 96]PPV: Positive predictive value; NPV: Negative predictive value; AHI: Apnea-HypopneaIndex; CI: Confidence interval.

[0293] Predictive Value

[0294] Table 2-4 displays the initial PPV and NPV values along with their corresponding 95% confidence intervals obtained through bootstrapping. The confidence intervals for both statisticshave very high limits for all thresholds. As the AHI thresholds increased, there was a slight decrease in limits for PPV accompanied by an increase for NPV.Table 2-4: Predictive value on AHI severity classification for AHI > 5, AHI > 15 and AHI > 30PPV [%] NPV [%]AHI >5 97 [97, 98] 87 [84, 89]AHI > 15 96 [95, 97] 89 [88, 91]AHI >30 94 [92, 96] 96 [95, 97]PPV: Positive predictive value; NPV: Negative predictive value; AHI: Apnea-Hypopnea Index; CI: Confidence interval.

[0295] To visualize the agreement between the reference method and the one obtained by the embodiment a Bland- Altman plot was created. The Bland- Altman analysis showed a mean difference of 1.0. The limits of agreement (equal to ± 2 standard deviations) were -7.8 and 9.9 AHI. Most data points were centered around where the difference (y- axis) is zero. There was no clear systematic bias where the differences were mainly above or below zero. FIG. 13 shows a Bland Altman plot for the whole cohort.

[0296] Table 2-5 summarizes Cohens 's Kappa values and Fl scores that were obtained for different AHI severity. Cohen’s kappa increased as the AHI increased and ranged from 0.84 to 0.87. The opposite happened to the Fl, the score decreased with a higher AHI. It went from 0.96 to 0.89 as the AHI severity decreased.Table 2-5: Comparison of Cohen’s Kappa and Fl Score for different AHI severity

[0297] Confusion Matrices

[0298] Table 2 - 6, show the confusion matrices for AHI thresholds of greater than 5, 15, and 30. They show the true positive (TP), false positive (FP), true negative (TN), and false negative (FN) classifications of different AHI thresholds when the reference AHI scores and the test AHI scores were compared.Table 2-6: Confusion Matrices for AHI > 5, AHI > 15, and AHI > 30

[0299] Demographics

[0300] The following table shows the number of individuals in different subgroups for sex, age, and BMI.Table 2-7: Number of the individuals in different subgroups, mean valuesGender Size [N] Age [years] Height [cm] Weight [kg]BMI[kg / m2]Female 1062 47.9 165.6 83.4 30.8Male 1264 52.0 181.1 101.6 31.7BMI Size [n] Age [years] Height [cm] Weight [kg]BMI[kg / m2]Normal 504 41.8 178.1 64.0 21.8Overweight 682 53.1 172.9 82.2 27.4Obese 1140 51.4 172.8 112.7 37.7Age Groups Size [N] Age [years] Height [cm] Weight [kg]BMI[kg / m2]18-25 261 20.8 170.2 76.4 26.426-35 267 30.2 171.9 96.7 32.636-45 404 40.3 174.0 97.1 32.346-55 513 50.5 176.9 100.1 33.156-65 430 59.5 174.5 95.3 31.7>65 451 71.9 173.7 88.0 29.7BMI: Body Mass Index

[0301] Bland-Altman

[0302] From the Bland Altman plots shown in FIGS. 14, 15, and 16, it can be seen the majority of data points were centered around the zero difference line for all groups and their associated subgroups. Observations outside the limits of the agreement could be potential outliers. The distribution of the differences between the two methods was similar for all subgroups. There was no clear consistent bias where the differences were predominantly above or below zero. The smallest detectable change for all subgroups was similar.

[0303] FIGS. 14A and 14B show Bland Altman plots of the reference and test AHI for a) males (FIG. 14 A), and b) females (FIG. 14B).

[0304] FIGS. 15A-15F show Bland Altman plot of the reference and test AHI for all the different age groups: a) 18-25 years (FIG. 15 A), b) 26-35 years (FIG. 15B), c) 36-45 years (FIG. 15C), d) 46-55 years (FIG. 15D), e) 56-65 years (FIG. 15E), and f) 65+ years (FIG. 15F).

[0305] FIGS. 16A-16C show Bland Altman plot of the reference and test AHI for the different BMI groups: a) Normal (BMI < 25) (FIG. 16 A), b) Overweight (25 < BMI < 30) (FIG. 16B), and c) Obese (BMI > 30) (FIG. 16C).

[0306] Agreement

[0307] In this section are the agreement values for the different groups: Sex, age, and BMI. Table 2-8 shows the values of the agreement statistics (PPA, NPA, and OP A) for all subgroups along with their respective 95% CI from bootstrapping.Table 2-8: Agreement on AHI severity classification for AHI >5 for males and females in the PSG and HSAT+ datasetSex PPA [%] NPA [%] OPA [%]Male 97.2 [96.2, 98.2] 92.8 [89.8, 95.5] 96.2 [95.2, 97.2]Female 93.5 [91.8, 95.2] 89.8 [86.2, 93.1] 92.5 [90.9, 94.1]Age groups PPA [%] NPA [%] OPA [%]18-25 92.7 [88.8, 96.2] 90.1 [82.6, 96.6] 92.0 [88.5, 95.3]26-35 92.9 [89.2, 96.3] 82.5 [71.9, 92.0] 90.7 [87.2, 94.1]36-45 92.7 [89.6, 95.5] 88.9 [81.6, 95.0] 91.9 [89.1, 94.4]46-55 96.7 [94.8, 98.3] 93.5 [88.7, 97.5] 95.9 [94.2, 97.5]56-65 98.2 [96.6, 99.4] 97.1 [93.6, 100.0] 97.9 [96.4, 99.1]>65 98.2 [96.6, 99.4] 98.2 [95.3, 100.0] 98.2 [96.9, 99.3]BMI severity group PPA [%] NPA [%] OPA [%]BMI < 25 92.3 [89.6, 94.8] 84.8 [78.8, 90.5] 90.4 [87.7, 92.8]25 <BMI < 30 95.1 [93.3, 96.8] 86.8 [81.5, 92.3] 93.3 [91.4, 95.2]30 <BMI 97.5 [96.4, 98.4] 97.0 [94.9, 98.7] 97.4 [96.3, 98.2]BMI: Body mass index; PPA: Positive percentage agreement; NPA: Negative percentage agreement; OPA: Overall percentage agreement.

[0308] Confidence intervals had high upper and lower bounds for all statistics in all groups and their subgroups. Males had smaller ranges and slightly higher upper and lower bounds on all confidence intervals than females. For all statistics, the upper and lower bounds of the confidence intervals appeared to increase with older age. With rising BMI, the bounds of the confidence intervals for all statistics increased.

[0309] Predictive Value

[0310] The predictive values were calculated for each sub-group: Sex, Age, and BMI. Table 2- 9 shows the values of the predictive value statistics (PPV and NPV) for all subgroups along with their respective 95% confidence intervals from bootstrapping.Table 2-9: Predictive values for each sex group for AHI >5 in the PSG and the HSAT+ datasetsSex PPV [%] NPV [%]Male 97.9 [96.9, 98.7] 90.7 [87.3, 93.6]Female 96.4 [95.1, 97.6] 82.5 [78.1, 86.6]Age group PPV [%] NPV [%]18-25 96.2 [93.0, 98.8] 82.1 [73.0, 90.3]26-35 95.1 [92.1, 98.0] 75.8 [64.6, 86.2]36-45 96.7 [94.4, 98.5] 77.7 [69.2, 85.4]46-55 97.9 [96.4, 99.2] 89.8 [84.6, 94.7]56-65 99.1 [97.9, 100.0] 94.4 [89.5, 98.2]>65 99.4 [98.4, 100.0] 94.9 [90.4, 98.3]BMI severity group PPV [%] NPV [%]BMI < 25 94.7 [92.4, 96.7] 79.1 [72.6, 85.4]25 <BMI < 30 96.4 [94.8, 97.9] 82.5 [76.3, 88.1]30 <BMI 99.0 [98.3, 99.6] 92.6 [89.5, 95.3] BMI: Body mass index; PPV: Positive predictive value; NPV: Negative predictive value.

[0311] Confidence intervals had high upper and lower bounds for both statistics (PPV and NPA) in all subgroups. The bounds of the confidence intervals for NPV were slightly lower than for PPV for all subgroups. The confidence intervals have lower limitations for NPV when comparing males to females in terms of sex. With regard to age, the predictive value seemed to increase with older age. With regard to BMI, the predictive value appeared to rise with higher BMI.

[0312] Comorbidities

[0313] Table 2-10 depicts descriptive statistics for different comorbidities. Comorbidities groups with fewer than 10 individuals were not analyzed due to a lack of data. Additionally, the individuals with a BMI > 30 were considered obese.Table 2-10: Means of comorbidity subgroups bgroup Size [N] Age [years] Height [cm] Weight [kg] BMI [kg / m^]ADHD 22 32.8 174.6 94.1 30.2Anxiety 10 60.3 172.1 95.0 32.3Asthma 46 41.1 170.8 97.4 33.4Atrial fibrillation 59 64.0 172.6 90.3 30.2Diabetes 59 46.6 171.9 107.7 36.3Heart disease 46 64.0 174.6 101.8 33.2Heart failure 13 62.3 173.9 112.9 37.1Hypertension 217 56.4 174.3 108.6 35.7Low testosterone 44 50.3 188.8 103.7 32.4Obesity 1213 51.4 173.0 112.5 37.6Gastrointestinal reflux 255 53.5 171.6 93.8 31.7Seasonal allergies 58 30.3 177.3 116.5 37.1Seizures 19 40.2 171.3 86.6 29.2ADHD: Attention deficit hyperactivity disorder; BMI: Body mass index.

[0314] Bland-Altman

[0315] The Bland- Altman plot in FIGS. 17A and 17B show that the majority of data points were centered around the zero difference line for both groups with comorbidity and the group without a known comorbidity. The mean difference for both groups was similar and the same applies to the standard deviation. Data points outside the limits of the agreement could be potential outliers. The distribution of the differences between the two methods was similarfor all subgroups. There was no clear consistent bias where the differences were predominantly above or below zero. FIGS. 17A and 17B show a Bland- Altman plot showing agreement for individuals with some comorbidity (FIG. 17A) and individuals without known comorbidities (FIG. 17B).

[0316] Agreement

[0317] Table 2-11 shows the PPA, NPA, and OPA for each comorbidity as well as the 95% CI from bootstrapping. The limits of the Cis for PPA were overall high. For heart failure, the lower bound of the CI was the lowest, or 66.7%, and for the low testosterone group, or 84.0%. Other comorbidity groups had a lower bound around 90.0% that ranged in many cases to 100.0% . Regarding the NPA, the lower bounds of the Cis were lowest for heart failure, seasonal allergies, ADHD, and anxiety. The OPA was high for all the groups and the lower bound of the CI was over 85%, except for anxiety and heart failure. The upper bounds of the Cis were high in all cases.Table 2-11 : Agreement on AHI severity classification for AHI > 5 for different comorbiditiesComorbidities PPA [%] NPA [%] OPA [%]ADHD 100.0 [100.0, 100.0] 100.0 [0.0, 100.0] 100.0 [100.0, 100.0]Anxiety 100.0 [100.0, 100.0] 75.0 [0.0, 100.0] 90.0 [66.7, 100.0]Asthma 100.0 [100.0, 100.0] 100.0 [100.0, 100.0] 100.0 [100.0, 100.0]Atrial fibrillation 96.4 [90.9, 100.0] 100.0 [100.0, 100.0] 96.6 [91.4, 100.0]Diabetes 96.0 [89.7, 100.0] 100.0 [100.0, 100.0] 96.6 [91.3, 100.0]Heart disease 97.1 [90.6, 100.0] 83.3 [57.1, 100.0] 93.5 [85.6, 100.0]Heart failure 90.0 [66.7, 100.0] 66.7 [0.0, 100.0] 84.6 [62.5, 100.0]Hypertension 98.2 [95.9, 100.0] 92.0 [83.9, 98.3] 96.8 [94.3, 99.0]Low testosterone 93.8 [84.0, 100.0] 100.0 [100.0, 100.0] 95.5 [88.5, 100.0]Obesity 97.5 [96.4, 98.4] 96.6 [94.4, 98.6] 97.3 [96.3, 98.1]Gastrointestinal Reflux 94.7 [91.3, 97.8] 93.9 [87.4, 100.0] 94.5 [91.6, 97.1]Seasonal Allergies 98.1 [93.7, 100.0] 25.0 [0.0, 100.0] 93.1 [86.2, 98.5]Seizures 100.0 [100.0, 100.0] 100.0 [100.0, 100.0] 100.0 [100.0, 100.0]AHI: Apnea-Hypopnea index; ADHD: Attention deficit hyperactivity disorder; PPA: Positive percentage agreement; NPA: Negative percentage agreement; OPA: Overall percentage agreement

[0318] Predictive Value

[0319] Table 2-12 shows the PPV and NPV for each comorbidity and their 95% CI from bootstrapping. Anxiety had the lowest PPV value of 85.7% with a 95% CI of [50-100]% and a NPV of 100.0% with a 95% CI of [0.0-100.0]%. This could be explained by the lack of individuals with anxiety. The highest PPV was 100.0% with a 95% CI of [100-100] % for ADHD, asthma, atrial fibrillation, diabetes, low testosterone, and seizures. These high values could also be explained by the lack of individuals with AHI < 5 and the comorbidities mentioned above. As for the other reported comorbidities, the limits of the confidence intervals for PPV and NPV were high for all comorbidities except for Heart failure with an NPV of 66.7% with a CI of [0-100]%. This could also be explained by the lack of individuals with Heart failure.Table 2-12: Predictive value - Positive Predictive Value (PPV) and Negative Predictive Value (NPV)Medication PPV [%] NPV [%]ADHD 100.0 [100.0, 100.0] 100.0 [0.0, 100.0]Anxiety 85.7 [50.0, 100.0] 100.0 [0.0, 100.0]Asthma 100.0 [100.0, 100.0] 100.0 [100.0, 100.0]Atrial fibrillation 100.0 [100.0, 100.0] 66.7 [25.0, 100.0]Diabetes 100.0 [100.0, 100.0] 81.8 [55.6, 100.0]Heart disease 94.3 [85.3, 100.0] 90.9 [71.4, 100.0]Heart failure 90.0 [66.7, 100.0] 66.7 [0.0, 100.0]Hypertension 97.6 [95.0, 99.5] 93.9 [86.4, 100.0]Low testosterone 100.0 [100.0, 100.0] 85.7 [66.7, 100.0]Obesity 98.9 [98.1, 99.6] 92.6 [89.3, 95.3]Gastrointestinal Reflux 97.8 [95.4, 100.0] 86.1 [77.3, 93.5]Seasonal Allergies 94.6 [88.1, 100.0] 50.0 [0.0, 100.0]Seizures 100.0 [100.0, 100.0] 100.0 [100.0, 100.0]ADHD: Attention deficit hyperactivity disorder; PPV: Positive predictive value; NPV: Negative predictive value.

[0320] Medications

[0321] The characteristics of each subgroup can be seen in Tables 2-13, 2-21, and 2-22. Only one individual reported the use of NaSSA. That subgroup was not evaluated further due to its small size. FIG. 19 is provided to show a flowchart used for defining the medication study population.Table 2-13: Characteristics of the individuals in different subgroups, mean valuesSubgroup Size [N] Age [years] Height [cm] Weight [kg]BMI[kg / m2]BDZ 34 58.2 172.8 97.1 32.3Beta-blockers 46 63.5 174.6 101.8 33.3NDRI 63 45.2 176.1 95.2 31.9Opioids 18 59.6 183.8 85.0 28.1SARI 62 46.9 173.2 94.3 31.5SNRI 32 63.7 167.6 85.9 30.1SSRI 115 38.1 170.3 92.6 31.7Stimulants 34 35.4 170.8 83.4 28.8BDZ: Benzodiazepine; NDRI: Norepinephrine-dopamine reuptake inhibitor; SARI: Serotonin antagonist and reuptake inhibitor; SNRI: Serotonin and norepinephrine reuptake inhibitor; SSRI: Selective serotonin reuptake inhibitors BMI: Body mass index.

[0322] Bland-Altman

[0323] To visualize the difference in agreement between the BodySleep analysis method as disclosed herein and the reference method, two Bland-Altman plots were made, one for individuals taking any medication and another one for individuals who did not. The plots, which can be seen in FIGS. 18A and 18B, which show that most of the observations were inside the limit of the agreement, with fewer observations outside the agreement for medication takers. FIGS. 18A and 18B show a Bland- Altman plot showing agreement for individuals taking medication (FIG. 18A) and individuals not taking medication (FIG. 18B).

[0324] Agreement

[0325] Table 2-14 shows the PPA, NPA, and OPA for each subgroup with 95% confidence interval from bootstrapping. The results show that BodySleep2.0 disclosed herein had a high agreement with the reference scoring from the data. The OPA calculated for the different subgroups is high for all medications. Overall agreement has an upper bound over 90% with the standard error of < 6 and a lower bound of over 80% for all medications. Additionally, participants taking medication had a substantial agreement between the two scoring methods with a strong Cohen’s kappa of 0.86 and an Fl score of .96Table 2-14: Agreement on AHI severity classification for AHI >5 for different medicationsMedication PPA [%] NPA [%] OPA [%]BDZ 95.7 [85.7, 100.0] 100.0 [100.0, 100.0] 97.1 [90.3, 100.0]Beta-blockers 100.0 [100.0, 100.0] 71.4 [33.3, 100.0] 95.7 [88.6, 100.0]NDRI 95.6 [88.9, 100.0] 100.0 [100.0, 100.0] 96.8 [91.8, 100.0]Opioids 93.3 [76.9, 100.0] 100.0 [0.0, 100.0] 94.4 [81.2, 100.0]SARI 97.4 [91.8, 100.0] 91.3 [78.3, 100.0] 95.2 [89.5, 100.0]SNRI 96.0 [87.5, 100.0] 85.7 [50.0, 100.0] 93.8[84.3, 100.0]SSRI 94.3 [88.9, 98.8] 88.9 [75.3, 100.0] 93.0 [88.0, 97.3]Stimulants 85.0 [68.2, 100.0] 100.0 [100.0, 100.0] 91.2 [80.2, 100.0]BDZ: Benzodiazepine; NDRI: Norepinephrine-dopamine reuptake inhibitor; SARI: Serotonin antagonist and reuptake inhibitor; SNRI: Serotonin and norepinephrine reuptake inhibitor; SSRI: Selective serotonin reuptake inhibitors; PPA: Positive percentage agreement; NPA: Negative percentage agreement; OPA: Overall percentage agreement.

[0326] Predictive Value

[0327] Table 2-15 shows the PPV and NPV values along with their respective 95% CI for each subgroup as well as the original value of each statistic before bootstrapping. The confidence intervals for PPV had high bounds for all subgroups.

[0328] All subgroups of medications, except SARIs and beta-blockers, had lower bounds for NPV compared to PPV.Table 2-15: Predictive value - Positive Predictive Value (PPV) and Negative PredictiveValue (NPV)Medication PPV [%] NPV [%]BDZ 100.0 [100.0, 100.0] 91.7 [71.4, 100.0]Beta-blockers 95.1 [87.5, 100.0] 100.0 [100.0, 100.0]NDRI 100.0 [100.0, 100.0] 90.0 [75.0, 100.0]Opioids 100.0 [100.0, 100.0] 75.0 [0.0, 100.0]SARI 95.0 [87.5, 100.0] 95.5 [85.7, 100.0]SNRI 96.0 [87.3, 100.0] 85.7 [50.0, 100.0]SSRI 96.5 [92.4, 100.0] 82.8 [67.9, 96.0]Stimulants 100.0 [100.0, 100.0] 82.4 [61.5, 100.0]BDZ: Benzodiazepine; NDRI: Norepinephrine-dopamine reuptake inhibitor; SARI: Serotonin antagonist and reuptake inhibitor; SNRI: Serotonin and norepinephrine reuptake inhibitor; SSRI: Selective serotonin reuptake inhibitors; PPV: Positive predictive value; NPV: Negative predictive value. Table 2-16: Embodiment Performance with patients taking medication Condition Cohen’s Kappa Fl ScoreA£ZZ > 15 86.4 91.8AHI > 30 88.2 90.6Table 2-17: Embodiment Performance for non-medicated patientsCondition Cohen’s Kappa Fl ScoreAHI > 5 810 96AAHI > 15 83.8 91.0AHI > 30 85.7 88.7

[0329] Lastly, relating to comorbidities and medications, Tables 2-18, 2-19, 2-20, and 2-21 are provided to show characteristics of the individuals in different subgroups and mean values relating to the data of the sleep studies as used herein.Table 2-18: Characteristics of the individuals in different subgroups, mean values Subgroup AHI [ / h] Arousals [ / h] Respiratory events [ / h] TST [min]ADHD 21.3 7.5 13.9 355.2Anxiety 18.9 4.0 14.8 443.4Asthma 16.3 4.7 11.6 352.8Atrial fib 28.3 11.2 17.0 368.4Diabetes 25.9 6.1 19.8 334.7Heart disease 23.7 8.4 15.3 332.2Heart failure 17.8 7.0 10.8 333.6Hypertension 24.4 8.5 15.9 338.4Low testosterone 22.3 8.6 13.8 342.1Obesity 23.2 7.7 15.6 342.8Reflux 17.6 4.2 13.5 337.8Seasonal 31.2 10.6 20.6 371.7Seizures 17.0 6.0 10.9 351.9Table 2-19: Characteristics of the individuals in different subgroups, mean valuesSubgroup Min AHI Max AHI Mean AHI Median AHI STD AHIADHD 0.0 115.6 21.3 10.7 26.8Anxiety 1.8 46.9 18.9 12.8 17.7Asthma 0.0 79.4 16.3 12.6 15.6Atrial fib 0.0 109.8 28.3 25.3 22.4Diabetes 0.0 108.2 25.9 15.7 26.1Heart disease 0.0 84.7 23.7 18.0 23.9Heart failure 0.0 62.6 17.8 10.0 19.4Hypertension 0.0 144.0 24.4 16.6 26.3Low testosterone 0.0 119.1 22.3 15.8 25.7Obesity 0.0 144.0 23.2 15.7 24.7Reflux 0.0 121.2 17.6 11.2 19.6Seasonal 0.0 117.7 31.2 20.7 29.4Seizures 0.0 85.4 17.0 9.3 21.8Table 2-20: Characteristics of the individuals in different subgroups, mean valuesSubgroup AHI [ / h] Arousals [ / h] Respiratory events [ / h] TST [min]BDZ 16.2 4.6 11.6 338.3Beta-blockers 24.5 6.4 18.1 338.3NDRI 19.4 3.3 16.2 341.2Opioids 20.8 2.8 18.0 344.3SARI 14.7 3.7 11.0 330.0SNRI 23.1 7.5 15.6 351.6SSRI 17.0 4.3 12.7 350.0Stimulants 11.3 3.7 7.7 364.0Table 2-21: Characteristics of the individuals in different subgroups, mean valuesSubgroup Min AHI Max AHI Mean AHI Median AHI STD AHIBDZ 0.0 104.1 16.2 8.5 21.7Beta-blockers 0.0 108.2 24.5 16.0 25.5NDRI 0.0 114.2 19.4 13.2 21.3Opioids 0.0 86.9 20.8 16.3 21.4SARI 0.0 79.7 14.7 9.2 17.9SNRI 0.0 125.4 23.1 12.8 28.9SSRI 0.0 91.2 17.0 9.8 19.5Stimulants 0.0 108.2 11.3 5.6 19.4

[0330] Confusions Matrices: To aid in the understanding of the data set considered herein, the following confusions matrices are provided.Table 2-22: Confusions Matrix for malesTable 2-23: Confusions Matrix for femalesTable 2-24: Confusion Matrix for BMI severity: Normal (25 < BMI)Table 2-25: Confusion Matrix for BMI severity: Overweight (25 < BMI < 30)Table 2-26: Confusion Matrix for BMI severity: Overweight Obese (30 < BMI)Table 2-27: Confusion Matrix for the age group: 18-25Table 2-28: Confusion Matrix the age group 26-35Table 2-29: Confusion Matrix for age groups: 36-45Table 2-30: Confusion Matrix the age group 46-55Table 2-31 : Confusion Matrix the age group 56-65Table 2-32: Confusion Matrix the age group > 65Table 2-33: Confusion Matrices for all comorbidities (a-m)(a) Confusion Matrix ADHD (b) Confusion Matrix anxiety(d) Confusion Matrix for atrial(c) Confusion Matrix for asthma fibrillation(e) Confusion Matrix for(f) Confusion Matrix for heart diabetes disease(g) Confusion Matrix for heart(h) Confusion Matrix for failure hypertension(i) Confusion Matrix for lowtestosterone (j) Confusion Matrix for obesity(k) Confusion Matrix for reflux(1) Confusion Matrix for seasonal(m) Confusion Matrix forseizuresTable 2-34: Confusion Matrix for BDZTable 2-35: Confusion Matrix for Beta-blockersTable 2-36: Confusion Matrix forNDRITable 2-37: Confusion Matrix for OpioidsTable 2-38: Confusion Matrix for SARITable 2-39: Confusion Matrix for SNRITable 2-40: Confusion Matrix for SSRITable 2-41 : Confusion Matrix for Stimulants

[0331] Section 4.7 Discussion of Additional Validation Study

[0332] This study aimed to validate the methods disclosed herein, for example, in a preferred embodiment of the “Nox BodySleep2.0” in classifying sleep stages and detecting arousalsacross the diverse subgroups of demographics, comorbid conditions, and medication types. This retrospective analysis compared AHI values, of PSG and HSAT+ studies, obtained from the automatic respiratory analysis using the embodiment’s scoring, to AHI values obtained from the same respiratory analysis using manual scoring. The results indicate that the embodiment is a good tool compared to the reference method.

[0333] Section 4.7.1 Overview of the Complete Dataset

[0334] When comparing the test AHI and the reference AHI, the AHI value obtained using the embodiment of Nox BodySleep2.0 demonstrated very good overall agreement, when AHI >5, across the whole dataset. The agreement values remained high even with rising AHI values.

[0335] In the context of predictive value analysis, the embodiment demonstrated a good performance. The PPV being high overall indicates the embodiment is good compared to the reference method with regards to accurate sleep stage and arousal estimation for sleep studies with AHI >5. The NPV being high means the embodiment is good at estimating sleep stages and arousals for sleep recordings when AHI < 5. A greater threshold for AHI showed higher values of NPV indicating a slightly better performance of the BodySleep2.0 evaluating AHI under the new threshold.

[0336] The Bland Altman plot for the entire dataset, showing data points mostly being concentrated around the zero difference line, with no obvious bias, means there is a good level of agreement between the two methods. Similar conclusions can be made by the high Cohen’s Kappa coefficient and high Fl score.

[0337] Demographics

[0338] The Bland Altman plots for all subgroups showed similar results as the plot for the whole dataset, indicating a good level of agreement between the embodiment of Nox BodySleep2.0 and the reference method for all subgroups.

[0339] The confidence intervals for the agreement statistics showed that the embodiment of Nox BodySleep2.0, in general, performs well compared to the reference method for all subgroups. The greater upper and lower bounds and smaller ranges observed in males may suggest that the embodiment performs slightly better for males compared to females. The increase of confidence interval bounds, for PPA, NPA, and OP A, with older age could mean that the embodiment of Nox BodySleep2.0 performs better on recordings from individuals as they get older. In the same way, increasing the limits of all confidence intervals with a higher BMI could imply the embodiment of Nox BodySleep2.0 performing slightly better with a higher BMI.

[0340] The predictive value statistics showed a similar trend. The confidence intervals had high bounds for both statistics, indicating that the Nox BodySleep2.0 is both good at estimating individuals with AHI > 5 and AHI < 5 for all subgroups. The lower confidence interval bounds for NPV could be explained by fewer individuals with AHI < 5 in the dataset for all subgroups.

[0341] Comorbidities

[0342] When looking at individuals with comorbidities, the CI limits were relatively high for all statistics except for the NPV for individuals with gastroesophageal reflux. Among the gastroesophageal reflux patients, the automated analysis tends to slightly underestimate AHI levels in individuals with a threshold of AHI > 5. It is important to highlight that existing literature suggests that Gastroesophageal Reflux could potentially introduce effects that may affect measurements. Breathing patterns in individuals with gastroesophageal reflux can be distinctive and unique, which may not be accurately captured by the embodiment, likely due to insufficient training data on individuals with this condition. Consequently, less common and unique behaviors may not be adequately incorporated or considered. The few individuals in the dataset with AHI < 5 and certain comorbidities may help explain some of the confidence intervals for PPA and PPV being [100, 100] and NPA and NPV being [0, 100] or [100, 100] in tables 2-12 and 14.

[0343] Medication

[0344] The high bounds on all confidence intervals for all performance metrics on all subgroups imply that the performance of the embodiment of BodySleep2.0 on individuals taking medications was similar across all subgroups. The overall agreement suggests that the embodiment is not likely interrupted by people taking the medications described in this study. Some of the Cis for PPA and PPV being [100, 100] and NPA and NPV [0, 100] or [100, 100] in Tables 2-12 and 2-14 may be explained by the lack of sleep studies in the dataset that involve individuals taking medication and the small number of them with AHI < 5.

[0345] Section 4.7.2 Long-Term Implications and Practical Applications According to Some Embodiments

[0346] The use of CNN algorithms, like in some embodiments of the Nox BodySleep2.0 in conjunction with the HSAT studies to estimate sleep stages and score respiratory and arousal events may reduce the amount of time sleep technologists must spend on PSG scoring, allowing them to devote more time to patient needs. It could also enable experts in sleep medicine to effectively compile enormous amounts of data from various sources, including HAST studies, and could potentially lead to substantial savings in both cost and time forpatients and clinicians. It may also serve to solve the problem of the tedious waiting for in-lab PSG.

[0347] Section 4.8 Conclusion of Additional Validation Study

[0348] This study’s methodology is one of its key strengths. By extracting specific parameters from the PSG and HSAT + data for comparison, the potential variance from differing sleep nights or double setups was eliminated. This method also allowed for comparing the embodiment’s performance against the gold standard PSG manual scoring, further increasing this study’s generalizability.

[0349] In conclusion, the embodiment of BodySleep as disclosed herein (i.e., this embodiment of the Nox BodySleep2.0) demonstrated a consistently high level of agreement in accurate AHI classification for those with AHI > 5 across all subgroups. While minor variations were observed in some demographic and comorbidity subgroups, these were minimal. The BodySleep method as disclosed herein, in the embodiment referred to as the Nox BodySleep2.0, can be used with confidence to more accurately estimate AHI severity in HSAT studies.

[0350] Section 5 Comparison Data of Embodiments of BodySleep to other Sleep Studies

[0351] Returning to the figures, FIGS. 21 A and 21C show the systematic underestimation of Home Apnea Sleep Testing (HSAT) Respiratory Event Index (REI) using current HSAT methods compared to Polysomnography (PSG) Apnea Hypopnea Index (AHI), and FIGS.2 IB and 2 ID show the significant improvement to accuracy of the Home Apnea Sleep Testing (HSAT) Respiratory Event Index (REI) using an embodiment of the non-brain, BodySleep analysis method as described herein.

[0352] In the results shown in FIGS. 21 A and 21C, in comparing AHI with REI which are generally highly correlated, AHI is calculated as the count of (Apnea; Hypopnea with Desat; Hypopnea with Arousal ) / Total Sleep Time, and REI is calculated as the count of (Apnea; Hypopnea with Desat) / Recording Time. It is noted that hypopneas are only counted once, even if they fulfill both the Desat and Arousal criteria. Total Sleep Time is typically measured with EEG, which is missing in the regular HSAT study. Therefore the accepted standard is to use Recording Time as the maximum approximation, which systematically drives down the REI compared with AHI.

[0353] As arousals are in the standard determined from EEG in PSG. But an EEG signal is missing in the HSAT and therefore arousals and arousal-associated events, such as arousal- associated hypopneas, so this also drives the REI systematically down compared with AHI, resulting in a significant underestimation the HSAT REI. The overall result is that HSAT REIis by definition >= AHI and this means that if the HSAT-REI-number is above the AHI- clinical thresholds for sleep apnea, the diagnosis is "conclusive" as PSG would only drive it higher.

[0354] In the same way, if it is lower, the HSAT should be considered "inconclusive" as the AHI could have been above the threshold. This means that for some patients, (especially women and kids) all the apneas / hypopneas may not meet the criteria captured by the HSAT, but all would be arousal based. This would make the HSAT deliver a REI of 0 but AHI of 50 as an example. So the correlation is 100% for Apneas and Hypopneas with Desat as they were determined in the same way on the same signals, but 0 on the arousal based.

[0355] Relating to the AHI thresholds of 5 and 15, these are the standard AHI clinical thresholds used for diagnosing sleep apnea. <5=Normal, 5-15 = Mild, 15-30 = Moderate and 30+ = Severe. These thresholds in most clinics determine the therapy, people with chronic conditions and "mild" or above, in many programs get CPAP treatment, while others require Moderate or above to get CPAP. For those that are Mild, without chronic conditions, they receive alternative treatments from CPAP, often in the form of oral appliances.Accordingly, it is important to classify the patients correctly into those categories.

[0356] In the data shown in FIG. 21 A and 21C, a type 3 HSAT study was performed. The circled data point in FIG. 21 A illustrates a patient with REX).8 on type 3 HSAT but a AHI=22.7 on a PSG.

[0357] The data shown in FIGS. 2 IB and 2 ID show the HSAT performed according to one disclosed method wherein arousals and arousal-associated event are determined based on body signals (in this case RIP signals from 2 RIP belts, in a study of 643 sleep studies and 2,407 sleep studies, respectively.

[0358] In FIG. 21B, the patient level agreement for AHI > 5 are shown in Table 3-1 below. Table 3-1

[0359] And for the results shown in FIG. 2 IB, the patient level agreement for AHI > 15 are shown in Table 3-2 below.

[0360] FIGS. 21C and 21D show a similar validation of 2,407 studies, when using HSAT (with no EEG signal) and without an arousal detection as described herein, 1,937 (81%) subjects get the correct outcome, comparing the measured HSAT REI with the actual PSG AHI. However, when using the body-sleep based RIP signals and the methods described herein to determine arousals and arousal-associated events, 2,211 (92%) subjects get the correct outcome and the sleep studies and REI of 274 individuals (11%) are properly and correctly assessed.

[0361] In FIG. 21D, the patient level agreement for AHI > 5 are shown in Table 3-3 below. Table 3-3

[0362] In FIG. 21D, the patient level agreement for AHI > 15 are shown in Table 3-4 below.Table 3-4

[0363] As used in Tables 3-1 to 3-4, "No Arousals" simply means that these are the standardHSAT results without a determination of body-signal or body -based arousal or arousal- associated events, or in other words that is not counting the arousal based hypopneas. The Afib is a shortcut for Afibrillation that is a common cardiac condition. So the Afib datasetconsists of patients undergoing a sleep study that have additionally this Afib-condition (Irregular heartbeat). This shows a significant advantage of the body-signal (and particularly RIP belt) based method described herein, as compared to the pulse-oximeter measurements (or more accurately photoplethysmography, PPG). Comparing a "respiratory based sleep studies" as described herein and "PPG based sleep studies”, a significant difference is that PPG based sleep studies struggle with accuracy if the patients have cardiac conditions, such as Afib, but the Respiratory Based accuracy is not affected like can be seen from the tables above.

[0364] So to have a realistic comparison for the performance of the RIP based signals to determine arousals and arousal-associated events, the PSG were auto-scored, with an Al model including all the PSG-EEG, EMG and ECG signals as well as the HSAT signals. So in Tables 3-1 to 3-4, are shown 1. Standard auto scored HSAT, 2. Standard auto stored PSG (with Al model reading the EEG channels) and 3. HSAT including RIP -based determination of arousals and arousal-associated events as described herein. All compared favorably with the "golden standard" of the manually scored PSG study.

[0365] Section 5.1 Unexpected Results According to Some Embodiments

[0366] This was unexpected and surprising, when the results are considered, as it demonstrates that the information that matters for AHI scoring are all found in the HSAT signals, including the RIP belt signals, and the EEG does not add anything of importance to the accuracy.

[0367] Embodiments described herein may be based on the standard HSAT signals but may provide AHI closely matching what would be expected from PSG. Embodiments may achieve this by, in addition to performing standard REI calculation, correctly detecting the normally missing arousal based hypopneas and determining accurate Total Sleep Time.

[0368] The accuracy of some embodiments described herein may thus be insignificantly affected by cardiac conditions, such as Afib and therefore may be a big-improvement when compared with cardiac / pulse based products (such as PAT) suffering from big contradictions for all types of cardiac conditions.

[0369] Section 6 Methods for Providing a Sleep Study According to Some Embodiments

[0370] According to an example as shown in FIG. 22, embodiments of the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) may provide a method 2200 of obtaining results from a home sleep study (HSS) that are significantly improved to level of accuracy similar to a PSG study. In step 2210, a request is received for a home sleep study (HSS). Such a request may be received over the Internet orthrough a network. At step 2220, delivery of a HSS sensor is arranged. At step 2225, the HSS sensor is delivered to the subject. This may be through a common carrier or delivery, often to the home of the subject. At step 2230, the HSS sensor is applied to the subject. In a preferred example, the HSS sensor may include a RIP belt sensor system including one or more, preferably two, RIP belts, including a thoracis RIP belt and an abdomen RIP belt, as shown, for example, in one of FIGS. 7A-7C. During one or more nights, HSS data is obtained by the HSS sensor. This data may be stored by the HHS sensor, or may be transmitted to a central server or computing device through a Bluetooth transmission, LAN, or cellular network, or the Internet. Or, the HHS sensor or a data storage device can be mailed, shipped, or delivered by carrier to a remote location housing the central server or computer device. Using the bodysignal based system and methods described herein, a BodySleep embodiment may be implemented including determining an arousal of the subject using the data from one or more body signals. A result may be provided based on the RIP data including the determined arousals. And certain diagnosis can be made, a sleep therapy can be prescribed or implemented, a therapy can be modified based on the BodySleep analysis results. The method of 2200 provides for a high-quality HSS with results very comparable to a PSG without requiring clinical involvement in delivery or operation of the HSS. The HSS can be performed entirely by the subject and the HSS data can be uploaded to the Cloud or Internet, and can be analyzed and the results can be provided to the subject, for example, in a web accessible platform. And based on the results, a therapy can be recommended, begun, prescribed, or modified to improve the sleep of the subject.

[0371] Further elements may also be included in the method 2200 shown in FIG. 22 or a similar method. The device shipped or delivered to the subject may include a recorder with one or more or preferably two RIP belts. The device delivered may also or alternatively include an accelerometer, or could be two devices, one on each RIP belt and a separate acceleration meter OR only two belts. The RIP belts may be reusable for multiple nights. The device may come with a Mobile Application or other "Receiving Unit", that has a wireless connection to the Device (Devices) for receiving the recorded RIP signals and acceleration signals (if included) in real time OR delayed during the night OR upload after the night. The Mobile Application may establish a link to the Cloud or over the Internet, for uploading the recorded data OR the Mobile Application run the BodySleep analysis on the data OR the "Receiving Unit" may upload or perform the BodySleep analysis. Based on the recorded data, a set of sleep parameters are derived, such as sleep profile, arousals, sleep disordered breathing parameters, arousal index, and / or sleep stability measures. The device may bewireless and rechargeable by the patient. The device may be activated when the RIP belts are snapped around the patient and deactivated after removal from the patient. The HSS data from the recording may be presented to a person operating in patient care management and / or to the patient himself. The data from the recording may be used to determine if a sleep therapy is effective, needs adjustment and guide how to adjust the therapy. The results from the processing may be presented to a healthcare professional for diagnosis of a sleep disorder, confirmation of health sleep or monitoring of treatment performance.

[0372] Further to the concepts, embodiments, systems, and validations of those concepts, embodiments, and systems, the following provides further, significant real-life applications and / or uses of the method and systems described therein.

[0373] Section 7 Additional or Alternative Embodiments of Methods, Systems, and / or Devices

[0374] Section 7.1 A New Type of Processing Signals from HSAT Devices According to Some Embodiments

[0375] As described above, the RIP signals and optionally an acceleration signal may be received and analysis according to the embodiments of BodySleep described herein. An arousal and sleep profile can be provided as additional parameters for scoring a HSAT recording. An accurate measure of standard Sleep Disordered Breathing condition can be provided that is compared to AASM PSG performance. Alternative parameters can be provided from the HSAT study such as endotypes that would normally require PSG. Results in a conclusive diagnosis of SDB from HSAT that would normally require PSG recording.

[0376] Section 7.2 Quality Assurance of HSAT Using Embodiments of BodySleep Analysis Methods Described Herein

[0377] Instead of relying on using embodiments of the BodySleep analysis methods described herein for diagnoses, embodiments can be used for qualifying HSAT recordings. A normal HSAT diagnosis may be performed, which as was the state of the art before the filing of the present disclosure, hypopneas and / or arousals are missed. The BodySleep analysis automation according to some embodiments may be performed and compared with the HSAT. In case of significant difference the HSAT study may be determined as inconclusive, and the patient may be sent to PSG for a conclusive measurement.

[0378] Section 7.3 A New Type of Processing Signals From PSG According to Some EmbodimentsSome embodiments may be similar to those described above for HSAT analysis, but the results of embodiments of the BodySleep analysis methods may work as surrogate signals forstandard PSG signals, such as if the EEG signals are of bad quality etc. This application may be especially important for Home Sleep PSG testing (Type II or Self-Applied-Somnography) as there may be considerable failure rate for hookup done by the patient that can then be mitigated by using the BodySleep analysis output. In case that measure, such as PSG / SAS does not provide the required EEG and EOG signals, embodiments of the BodySleep can be used instead. In case that there is a great difference between the PSG / SAS and BodySleep results, the study can be deemed inconclusive and may need to be repeated.

[0379] Section 7.4 Managing Treatment of Sleep Disorders According to Some Embodiments

[0380] Introduction: Sleep Apnea

[0381] Sleep care management is a significant and growing field. Compliance to therapy, especially Continuous Positive Airway Pressure (CPAP), is very low in an unmanaged model, as it takes training and adaptation to get the therapy right and the patient comfortable. Unmanaged therapy has demonstrated over 50% non-compliance in the first year in multiple studies over the years. A managed therapy has however been demonstrated by the Applicant and the inventors to over 90% adherence, which may be thanks to continuous monitoring on performance over radio modules in the CPAP's and high-quality service by care managers. Similar to having a personal trainer for exercise, the care-managers may use a preemptive approach to spot patients struggling and adjust their therapy to be effective again. This model, however, may only support CPAP units with a radio module, but alternative therapies such as oral appliances therapy (OAT), may not support this option. Therefore, OAT is rarely used in value-based programs, as they are hard to monitor. Using a simple Respiratory Inductance Plethysmography (RIP) belt sensor device according to some embodiments described herein, a patient can measure one or more nights once or more often during the year, which may be sufficient to both help the patient to adjust to alternative therapies like OAT and regularly check the patient’s compliance. Other alternative therapies include hypoglossal nerve stimulation by an implantable device, pharmacological treatments, surgeries, positional treatment, lifestyle interventions, or any other treatments.

[0382] With this issue of OAT and other alternative therapies being a fact, more and more solutions are surfacing indicated with the potential of being used for this purpose. Commercial products, such as Apple watches or Oura ring have the potential to provide this type of information if they were somehow calibrated to an accurate reference as is described in Applicant’s earlier application directed to calibrating SSS with an HASS in Applicant’s earlier patent application US Application No. 17 / 351,933, filed at the USPTO on June 18,2021, entitled “PERSONALIZED SLEEP CLASSIFYING METHODS AND SYSTEMS”, which is herein incorporated by reference. Some advantages of embodiments described herein, for example, of using the methods and systems described herein, and particularly embodiments of the Nox BodySleep2.0 analyzed data from a simple sensor device with 2 RIP belts (preferable single patient use) may include providing a high accuracy sleep study information from a simple and low-cost screener that could secondly be used in combination with a wearable, to calibrate it (for example, according to US Application No. 17 / 351,933).

[0383] The methods and systems described herein may also support the monitoring of CPAP use and is then agnostic or unconcerned to the CPAP device, brand, model, and method of application. In cases where a patient suffers mask leakage or is given a nasal mask, yet breathes with the mouth open, the RIP belts may still accurately measure the breathing whereas the CPAP device may not.

[0384] Sleep care management using CPAP devices is based on data measured by the CPAP and delivered over radio modules to the cloud. The CPAP is, however, only in an indirect connection to the patient, the CPAP only "sees" the patient through the air-tube between the CPAP and the patient, based on the air-pressure and air-flow signals. Even if this gives the PAP device significant information on how well the patient is breathing, it cannot provide much information regarding how well the patient sleeps. This is especially difficult, as a patient on an inefficient treatment might not have direct apneas, but is half-cured, meaning that he might be struggling and having arousals. According to some embodiments, a sensor device as described herein that implements (e.g., one embodiment of the Nox BodySleep2.0 sensor) in association with the CPAP data may be used to calibrate a simplified sleep study. A recording of a few nights using a sensor device as described herein (e.g., an embodiment of a Nox BodySleep2.0 sensor) during CPAP treatment, provide both the information how well the patient slept during those nights on treatment and also information how to interpret the data from the CPAP up to the point of the embodiment of a BodySleep2.0 sensor recording and from that time one. This could improve the reliability of the data that the care managers have to work with and provide valuable and early warning if the patient's performance starts to degrade, that would eventually lead to the patient stopping using the therapy.

[0385] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) can be a fundamental building block in an inexpensive sensor device (such as a 2-belt RIP sensor device) that can be used by patients to monitor the performance of the treatment they receive for their sleep disorders. The device can be shippedto the patient at some point in time and the patient can use the device with their treatment in their own home. The value of the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) may bring to the 2-belt sensor is that it may allow the 2 belt sensor to detect sleep stages and arousals in the patient along with changes in breathing, such as apneas and hypopneas. Arousal scoring is particularly important since it allows the detection of hypopneas without requiring a measurement of drops in blood oxygen saturation (SpO2). The measurement of the SpO2 signal is traditionally measured by a pulse oximeter, which is a relatively expensive device, adds complexity to the sleep study, is prone to failure, and decreases comfort.

[0386] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) in conjunction with the RIP belt sensor (e.g. a 2-belt RIP system) may provide an inexpensive, scalable, comfortable, and accurate method to measure sleep, arousals, and sleep apnea in patients.

[0387] Accordingly, one method may include the following: At least a 2 RIP belt sensor (which may preferably be a single patient use), is sent to a customer on request. The patient downloads an app in his mobile phone that is paired with the sensor for wireless communications (such as BLE). The patient sleeps with the sensor that streams the recorded data either directly or buffered to the mobile device, where it is received and buffered before being streamed to the cloud for storage. The received data is processed by BodySleep2.0, and the analysis output may be provided to an adequate person responsible for monitoring the patient sleep performance or treatment compliance.

[0388] According to some embodiments, the method may include adjusting the therapy based on the received data. This may beneficially improve the compliance of the patient to the treatment - as the therapy is adjusted, the patient may be more likely to be compliant as the patient observes the effectiveness of the treatment increasing with the adjustments.

[0389] According to another method, the following same or similar method as above is followed except the device is a recorder (for example, such as a Nox T3s recorder), that stores the data, the data is then uploaded during or after the study to the cloud OR the data on the device is downloaded upon its physical return to the clinic / operation where BodySleep2.0 is used for analyzing like in Method 1. The patient does not need to download an app.

[0390] According to some embodiments, a sleep care management method is provided wherein one or more RIP belts, preferably two RIP belts and preferably single patient use belts, are provide to a customer on request. An app is provided to the patient to download. The patient downloads an app in his mobile phone that is paired with the sensor for wirelesscommunications (such as BLE). The patient sleeps with the sensor that streams the recorded data either directly or buffered to the mobile device, where it is received and buffered before being streamed to the cloud for storage. The received data is processed by the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) and the analysis output provided to an adequate person responsible for monitoring the patient sleep performance or treatment compliance.

[0391] A second method is provided similar to the above sleep care management method above, except the device is a recorder (like the Nox T3s), that stores the data, the data is then during or after the study uploaded to the cloud OR the data on the device is downloaded on its physical return to the clinic / operation where BodySleep analysis method or system is used for analyzing like in the above method.

[0392] Section 7.5 Calibrating a Simple Sleep Study Device According to Some Embodiments Described Herein

[0393] According to a calibrating method: A patient uses a consumer grade or a simple medical device to monitor his treatment effectiveness. A RIP belt sensor (preferably a 2-belt sensor and for single patient use), is sent to a customer on request. The patient downloads an app in his mobile phone that is paired with the sensor for wireless communications (such as BLE). The patient sleeps with the sensor that streams the recorded data either directly or buffered to the mobile device, where it is received and buffered before being streamed to the cloud for storage. The received data is processed by a BodySleep processor, for example, the Nox BodySleep2.0, and the analysis output is used to calibrate the consumer grade or simple medical device as described in US Application No. 17 / 351,933.

[0394] According to another method, the following same or similar method as above is followed except the device is a recorder (like T3s), that stores the data, the data is then uploaded during or after the study to the cloud OR the data on the device is downloaded upon its physical return to the clinic / operation where BodySleep2.0 is used for analyzing like in Method 1. The patient does not need to download an app.

[0395] Section 7.6 Augmenting CPAP Data for Improved Therapy Management According to Some Embodiments

[0396] According to another example of a method, the following is performed. First, a BodySleep method may be performed using a BodySleep sensor, such as a Nox BodySleep2.0 Sensor, which may record a patient using CPAP, preferable over multiple nights. A BodySleep analysis may be performed, for example, according to an embodiment of a BodySleep2.0 sleep analysis validated as described herein. A comparison between thereceived data from the CPAP and the measured data from BodySleep2.0 may be used to augment the accuracy of the CPAP data as described in WN Ref. No US Application No. 17 / 351,933. A post-data analysis may be performed on stored CPAP data to determine how the patient has been trending. The calibrated CPAP data model may be used in the future to keep trending the patient with high accuracy and to identify when he is at risk of quitting therapy.

[0397] Section 7.7 Using One or More RIP Belts (For Example, Two RIP Belts) to Diagnose Sleep Apnea According to Some Embodiments

[0398] As described herein, sleep apnea is a disease where a patient periodically stops breathing (apnea) or has severely reduced airflow which terminates in a drop in the blood oxygen saturation or an arousal (hypopnea). Apneas and hypopneas occur during sleep. Sleep apnea is commonly diagnosed by measuring breathing and blood oxygen saturation. In some cases electroencephalography (EEG), electrooculography (EOG), and electromyography (EMG) are also used. The reduction in airflow is typically measured by a nasal cannula, the desaturation is measured by an oximeter, the arousals are detected in the EEG signals, and various sleep stages are detected using the EEG, EOG, and EMG signals.

[0399] According to the American Academy of Sleep Medicine (AASM) hypopneas and apneas are defined as certain reduction in breathing followed by a drop in blood oxygen saturation or an arousal. Even though a drop in blood oxygen saturation is often used to score hypopneas, it has been shown that most respiratory events terminate in arousals.

[0400] By measuring the respiratory movements of the thorax and abdomen using RIP belts and employing a BodySleep method as described herein, it may be possible to detect apneas and hypopneas from the flow signal derived from the RIP signals, a majority of the apneas and hypopneas result in an arousal which can be detected by a BodySleep method as described herein, and the sleep stages may also be detected by the BodySleep methods as described herein.

[0401] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 device) may provide a foundation that can be used to design and build a new and novel device to diagnose sleep apnea and monitor sleep apnea treatment. Examples of the device may be a small electronic device using two RIP belts, one placed around the thorax to measure thoracic breathing motions, and another one placed around the abdomen to measure abdomen breathing movements. The device may be easy to use by the patient, can be easily shipped in the mail, may be inexpensive so it is not costly ifdevices get lost or delayed, the devices can be disposable, the devices can live with the patient, and the devices can be used once or multiple times by the patient.

[0402] A method may be provided based on the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 device) for diagnosing sleep apnea. The method may include sending at least a RIP sensor, for example a 2-belt RIP sensor, (which may also be single patient use belts) to a customer on request. The patient may download an app in his mobile phone that is paired with the sensor for wireless communications (such as BLE). The patient may sleep with the sensor that streams the recorded data either directly or buffered to the mobile device, where it may be received and buffered before being streamed to the cloud for storage. The received data may be processed by a system configured to perform an embodiment of the BodySleep analysis described herein (for example, the Nox BodySleep2.0), and the analysis output may be provided to an adequate person responsible for providing the patient with the correct diagnosis of sleep apnea.

[0403] A second method may also be provided, which may be similar to the method above, except the device may be a recorder (like a Nox T3 device), that stores the data, the data may then be uploaded during or after the study to the cloud or the data on the device is downloaded upon its physical return to the clinic / operation where BodySleep2.0 is used for analyzing like in the method above. The patient does not need to download an app.

[0404] Another method may be provided. The method may include receiving at a neural network body signal data. The body signal data may include RIP data. The neural network may be specially configured to determine sleep stages and / or arousals and may be trained on specialized body signal data such as PSG data and / or other sleep study and / or RIP signal data. The method may include determining, using the neural network, one or more sleep stages and / or arousals using the body signal data. The method may include outputting a result that indicates any sleep stages and / or arousals based on the body signal data.

[0405] Accordingly, some methods and embodiments described herein may include using a specially trained Al model such as a neural network to transform body signal data into a list of sleep stages and / or arousals which may lead to an actionable determination and / or diagnosis. The list may be output by the Al model, for example as a CSV list. Some embodiments may beneficially provide a cheaper and more comfortable alternative to an inlab PSG in such a way, and this may improve the results of the sleep study may be improved, as the quality of the recorded sleep may be increased.

[0406] In some embodiments, the method may include administering an appropriate treatment for the diagnosed sleep apnea, for example a CPAP treatment, a pharmacologic treatment, or other treatments described herein. In some embodiments, the method may include adjusting a current treatment based on the diagnosis. For example, a dosage amount may be increased and / or decreased, or a different level of CPAP treatment may be prescribed.

[0407] Section 7.8 Diagnosis of Sleep Disorders Other than Sleep Apnea According to Some Embodiments

[0408] Section 7.8.1 Periodic Limb Movements of Sleep (PLMS)

[0409] Patients suffering from PLMS may have characteristic periodic movements or twitches of muscles in the legs or arms. PLMS is typically diagnosed by a polysomnography (PSG) sleep study where electroencephalography (EEG) and electromyography (EMG) are recorded. The EMG signals are recorded on the limbs to detect characteristic increases in muscle tone associated with the muscle twitching. The EEG signals are recorded to detect arousals associated with muscle twitching. The PLMS events have characteristic periodicity that are reflected in the EMG and arousal events. Furthermore, the arousals associated with the PLMS events are not associated with other causes of arousals that may be periodic such as breathing cessation during sleep (i.e. apneas and hypopneas).

[0410] With PLMS being one of the three most common sleep disorders, it is important to have a scalable method for measuring it and monitoring treatment of PLMS for titration of the medicine used. Conventionally PLMS is measured in PSG using EMG electrodes on the right and left leg and when the muscle is active, it shows up in the EMG. In PLMS (Periodic Limb Movement during Sleep) the muscular activity is periodic and must fulfill a certain criterion to be distinguishable from movements caused by arousals from sleep apnea. Typically, the period of PLMS is 20-30 seconds but can be longer, and that overlaps with the frequency of severe OSA. PLMS does not always cause cortex arousal as defined in the sleep scoring manual, but if it doesn't affect the sleep pattern it is not a problem. While the interscorer reliability of EEG manually scored arousals is low (60%) the auto scored BodySleep2.0 arousals may be both sensitive and specific to real events taking place in the body. And if only PLMS activities that cause arousals matter, the PLMS can be confirmed by some embodiments described herein.

[0411] With the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) arousal events may be reliably marked that are not associated with OSA and can therefore include this important disorder to the mix where embodiments of a BodySleep analysis (for example, Nox BodySleep2.0) may be beneficial.

[0412] In an example device that contains at least one and preferably at least two RIP belts where an analysis such as an embodiment of the Nox BodySleep2.0 is used to determine periods of wake, REM sleep, and non-REM sleep, and detect arousal events it may be possible to detect arousals during different stages of sleep. Furthermore, the two RIP belts can be used to detect apneas and hypopneas since the RIP belts measure the breathing movements of a patient. The breathing movements can be used to construct a signal that is proportional to flow during breathing. The RIP flow signal can be used to detect apneas and hypopneas. Combining the sleep, arousal, and respiratory analysis applied to the RIP signals it may be possible to identify arousals that are not associated with respiratory events, occur during sleep, and are periodic. These arousals can be determined to be associated with PLMS and may be the foundation of using the RIP belts and embodiments of the BodySleep analysis method to diagnose PLMS, instead of requiring a full PSG sleep study.

[0413] The sensitivity of the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) may be preferably trained to match the PSG scoring of arousals as well as possible. For PLMS analysis embodiments of the arousal model may be used and then the periodicity may be used to determine if the events detected originated from PLMS or something else. The detection of arousal and arousal-associated events can be used to capture switching between autonomic and somatic respiratory control without requiring a capturing of the respiratory recovery breath response in case of sleep apnea. Thus by only capturing lower recovery breaths with higher sensitivity where the reality is that this is of a different physiological origin. Embodiments of the model may be used for PLMS analysis as embodiments of the arousal model may not only capture the recovery-breath characteristics associated with sleep apneas but as well the change of respiratory control between the autonomic and somatic systems when the patient is aroused. With the arousals detected, then the periodicity may be used to determine if the events detected originated from PLMS or something else.

[0414] Using the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system), a method may be provided for diagnosing PLMS. At least a 2 RIP belt sensor (preferably single patient use), is sent to a customer on request. The patient downloads an app in his mobile phone that is paired with the sensor for wireless communications (such as BLE). The patient sleeps with the sensor that streams the recorded data either directly or buffered to the mobile device, where it is received and buffered before being streamed to the cloud for storage. The received data is processed the systems, sensors, and / or methods described herein (e.g., as implemented in embodiments of aNox BodySleep2.0 system). Arousals and respiratory events are detected. Arousals associated with apneas or hypopneas are excluded and the periodicity of the remaining arousals is analyzed. It is determined if a series of arousals are periodic, repeating within a regular period (allowing certain variance) as is used for scoring PLMS EEG signals in PSG. A PLMS period is marked over the time where PLMS is repeating and mark the periodic arousal events within that period as LM. The analysis output is provided to an adequate person responsible for providing the patient with the correct diagnosis of PLMS. The indexes are reported as they were scored from PSG.

[0415] As is shown in FIGS. 23A and 23B, the inventors of the present application have found a correlation between arousals or arousal-associated events and PLMS when the arousals or arousal-associated events are found to have a periodicity. Using a classifier according to some embodiments described herein to perform a classification or a machine learning algorithm, PLMS has surprisingly been able to be identified based on a determined periodicity of a plurality of the arousals or arousal-associated events using embodiments described herein. The period of the PLMS may range from 5 seconds to 90 seconds, but the actual periodicity is determined or identified using a classifier to perform a classification or a machine learning algorithm. Further examples and embodiments of the method, system, and devices to identify PLMS in the subject of the sleep study are enumerated in Group 2 of the enumerated embodiments provided below.

[0416] As shown in FIG. 23 A, there may be an event associated with PLMS. The event may be a movement of a right leg and / or of a left leg. The event may occur periodically, and the movement may coincide with one or more other events. FIG. 23 A shows four total left leg events and two total right leg events. FIG. 23 A also shows the periodic nature of the events based on the consistent spacing between the events.

[0417] FIG. 23 A also shows that these events may be detectable using the RIP signals gathered from the Thorax and / or the Abdomen of the patient that is experiencing PLMS. As shown by the rectangles that highlight each event, there is a slight change in the shape of the pulse that may coincide with the occurrence of an event. The inventors of the present disclosure have identified that this change in shape may be detectable and may provide a consistent way to diagnose PLMS by detecting PLMS events.

[0418] A second PLMS diagnosing method is also provided, which is similar to the abovedescribed method except the device is a recorder (like a Nox T3s), that stores the data. The data is then uploaded during or after the study to the cloud or the data on the device is downloaded upon its physical return to the clinic / operation where the systems, sensors, andmethods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) are used for analyzing like in the above method. The patient does not need to download an app.

[0419] A third PLMS method is provided, similar to the first PLMS method above, except arousals and sleep stages are determined using EEG / EOG / chin EMG as per a standard PSG sleep recording. The arousals and sleep stages are used as described in the first PLMS method above when they were derived using the analysis provided by the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system).

[0420] Another method may be provided. The method may include receiving at a neural network body signal data. The body signal data may include RIP data. The neural network may be specially configured to determine sleep stages and / or arousals and / or PLMS events and may be trained on specialized body signal data such as PSG data and / or other sleep study and / or RIP signal data. The method may include determining, using the neural network, one or more sleep stages and / or arousals and / or PLMS events using the body signal data. The method may include outputting a result that indicates any sleep stages and / or arousals and / or PLMS events based on the body signal data. Accordingly, some methods described herein may include using a specially trained Al model such as a neural network to transform body signal data into a list of sleep stages and / or arousals and / or PLMS events which may lead to an actionable determination and / or diagnosis. The list may be output by the Al model, for example as a CSV list.

[0421] Some embodiments may thus beneficially provide a cheaper and more comfortable alternative to an in-lab PSG, and this may improve the results of the sleep study may be improved, as the quality of the recorded sleep may be increased.

[0422] In some embodiments, the method may include administering an appropriate treatment for the diagnosed PLMS, a pharmacologic treatment or other treatments described herein. In some embodiments, the method may include adjusting a current treatment based on the diagnosis. For example, a dosage amount may be increased and / or decreased.

[0423] Section 7.8.2 Diagnosis of Narcolepsy According to Some Embodiments

[0424] Patients suffering from Narcolepsy are known to have cataplexy, where they lose muscle tone in the body. They are also known to transition from wake to rapid-eye movement (REM) sleep, which is a characteristic of the disease. REM sleep is characterized with the paralysis of the skeletal muscles, including but not limited to the intercostal muscles of the thorax.

[0425] Narcolepsy is commonly diagnosed in several ways. One method of diagnosing Narcolepsy is to use a special sleep study protocol called Multiple Sleep Latency Test (MSLT) or a Maintenance of Wakefulness Test (MWT). Both the MSLT and MWT sleep tests require a patient to spend a night at a hospital where an in-lab polysomnography (PSG) sleep study is performed on them. The following day the patient continues to wear the PSG sleep recording device and follows a strict protocol while being monitored by a sleep technician or a nurse. These sleep studies are uncomfortable for the patient and require extensive hospital resources.

[0426] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) may include a sleep stage and arousal detection Al analysis which uses the breathing movements of the thorax and abdomen to estimate Wake, REM, and Non-REM sleep periods. During REM sleep and during cataplexy the skeletal muscles are paralyzed while the diaphragm is active. This may have a significant impact on how the breathing movements of the thorax and abdomen look like. By carefully measuring the thorax and abdomen breathing movements using the highly sensitive respiratory inductance plethysmography (RIP) sensors it may be possible to distinguish periods of thorax paralysis using embodiments described herein..

[0427] FIG. 20 shows an example of how the thoracic RIP signal changes in a period of REM sleep interrupted by an awakening and a period of non-REM sleep. At the top of the figure the colored markers indicate 30 second periods that have been scored as a certain sleep stage by a trained sleep technician using electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals. The scoring of sleep stages by a sleep technician using the EEGZEOG / EMG signals is the state-of-the-art approach to score sleep. These sleep stages are presented as a reference to highlight how the abdomen and thorax RIP signals behave during REM, Wake, and Non-REM. FIG. 20 shows that the amplitude of the thoracic RIP signal is lower during the REM periods than during the Wake and non-REM periods. Furthermore, the amplitude of the thoracic signal is variable. This is indicative of intercostal muscle paralysis.

[0428] In addition to the ability to discriminate between periods where the skeletal muscles are paralyzed a combination of sleep staging using the EEGZEOG / EMG and the analysis of the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) may be useful to detect periods of REM sleep or periods where there are discrepancies between the state-of-the-art EEGZEOG / EMG sleep staging and the sleep staging of the BodySleep analysis. It is known that narcolepsy is characterized by sleepperiods where sleep technicians struggle to identify the sleep stages from the EEG / EOG / EMG signals and the patient may describe periods of where they are aware but still cannot move or control their thoughts.

[0429] A method of diagnosing Narcolepsy is provided, which may include using the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) to detect the transitions from wake to REM which could be used to provide input in the diagnosis of Narcolepsy. The BodySleep analysis can be used to detect cataplexy or loss of muscle tone in the body. The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system), in conjunction with an analysis of the EEG / EOG / EMG signals, can be used to provide input in the diagnosis of Narcolepsy.

[0430] According to some embodiments, the method may include receiving, at a neural network (for example a BodySleep2.0 neural network as discussed herein), body signal data. In some embodiments, the body signal data may be RIP data gathered from one or more RIP belts. The method may include using the neural network to determine transitions from wake to REM. The method may include using the neural network to determine cataplexy or loss of muscle tone in the body. The neural network may be trained on sleep data such as body signal data during sleep as well as PSG data to determine both the transitions as well as cataplexy or loss of muscle tone in the body. The method may include, based on the determination(s) of the neural network, outputting a determination of whether the received body signal data indicates narcolepsy. Accordingly, some methods described herein may include using a specially trained Al model such as a neural network to transform body signal data into a list of sleep stages and / or arousals which may lead to an actionable determination and / or diagnosis. The list may be output by the Al model, for example as a CSV list.

[0431] Some embodiments may beneficially provide a cheaper and more comfortable alternative to an in-lab PSG, and this may improve the results of the sleep study may be improved, as the quality of the recorded sleep may be increased.

[0432] In some embodiments, the method further includes administering an appropriate treatment based on the determination of narcolepsy. The treatment may be pharmaceutical such as a stimulant (e.g., modafinil, armodafmil, methylphenidate, amphetamines), an antidepressant (e.g., venlafaxine, fluoxetine, clomipramine), and / or other pharmaceutical treatments or the treatment may be behavioral such as establishing healthy sleep habits.

[0433] Section 7.8.3 Dementia Detection According to Some Embodiments

[0434] Dementia is an umbrella term used for general decline in cognitive abilities that impacts a person’s ability to perform everyday activities. Dementia includes causes such as Alzheimer’s disease, Lewy Body Dementia, Parkinson’s Disease, and other causes. Dementia has been shown to correlate with sleep disorders and sleep disorders may even accelerate the onset of Dementia. Specific sleep disorders are known to have predictive power when detecting or diagnosing certain types of dementia.

[0435] REM sleep behavior disorder (RBD) is a core feature in the diagnosis of Lewy Body Dementia. RBD is characterized by the patient losing muscle paralysis (atonia) during REM sleep. RBD may appear years or decades before other symptoms of Lewy Body Dementia. A sleep recording device consisting of one or more RIP belts, preferably at least two RIP belts, using the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) may be used to diagnose RBD. Embodiments of the BodySleep methods described can distinguish between wake and sleep and can distinguish between REM and non-REM sleep. Furthermore, when the RIP belts are placed on the patient’s thorax and abdomen it may be possible to detect periods when the skeletal muscles are paralyzed during REM sleep by monitoring how the thoracic breathing movements are affected. However the abdomen breathing movements are driven by the diaphragm that is not affected by the skeletal muscle paralysis during REM sleep. In Parkinson’s Disease a Meta-analyses revealed significant reductions in total sleep time, sleep efficiency, N2 percentage, slow wave sleep, rapid eye movement sleep (REM) percentage, and increases in wake time after sleep onset, N1 percentage, REM latency, apnea hypopnea index, and periodic limb movement index in PD patients compared with controls.

[0436] A method of detecting dementia is provided. Using a device having one or more RIP belts, preferably two RIP belts and the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system), RBD may be detected by identifying periods of REM sleep where the patient does not have atonia.

[0437] Using a device having one or more RIP belts, preferably at least two RIP belts, and embodiments of the BodySleep analysis method described herein, PLMS may be detected using the methods described in at least Section 7.8.1..

[0438] According to another method, using a device having one or more RIP belts, preferably at least two RIP belts and a BodySleep analysis method as described herein, any of the parameters mentioned in the Meta analysis including total sleep time, sleep efficiency, REM sleep percentage, increase in wake after sleep onset, REM latency, apnea hypopnea index, and PLMS may be identified.

[0439] Section 7.9 Advancing Sleep Diagnostics According to Some Embodiments

[0440] Introduction: HSAT augmentation

[0441] A system, sensor, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) may be a massive improvement for HSAT studies as it may allow the correct detection of all the AHI events, hypopneas that do not end in desaturations but only arousals, and may provide a classification of sleep stages into WAKE / NREM / REM. . With the information already in place from HSAT with embodiments of a BodySleep analysis method as described herein, it doesn't take much to augment the information to complete the PSG picture. The inventors have demonstrated from our SelfAppliedSomnography (SAS) recordings for Als (PSG) that the frontal EEG signals (recorded on the forehead) do contain everything that is needed to derive a PSG equivalent sleep staging accuracy. It is therefore possible to record one or two EEG signals using a HSAT device, such as a Nox T3s device, in addition to the regular HSAT signals (the T3s already has those two channels and when this is done, sometimes referred to as HSAT+) and score the NREM periods into Nl, N2 and N3 based on the EEGs.

[0442] According to some embodiments, combining processing on the EEG with the results from embodiments of BodySleep2.0, may provide accurate timing of the NREM periods and all the arousals, which may enable acquisition of the most accurate classification of sleep during NREM and may improve the accuracy of the overall sleep staging and arousals.

[0443] A method is provided for augmenting HSAT with the systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system). According to a first method, a recording device, such as a Nox T3s device is used to record a HSAT study with one or two additional frontal-EEG channels and one or more RIP belts, preferably at least 2 RIP belts. A BodySleep system, sensors, or method as described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 system) is used to derive all the parameters that can be derived from the BodySleep signals, including but not limited to those discussed herein (see, for example, Section 6). In some embodiments, an auto scoring is run on the EEG signals, which may determine sleep stages and arousals. The results may be combined from both in a relative manner for highest accuracy PSG like outcomes, including PLMS from above, sleep staging, sleep time, and combined / optimal arousals.

[0444] Section 7.10 Body Position and Activity Using RIP Signals According to Some Embodiments

[0445] Most sleep studies contain activity and body position sensors to report along with the recorded sleep data. This is normally done using acceleration sensors that are now relativelylow cost and easy to implement in any product. The body position may be used to classify the apnea event based on body position, as if the apneas are for example only occurring when the patient is in supine position but not on the right or left sides, alternative treatment like oral appliance or even "tennis balls on the back" can be sufficient to avoid the apnea. For a disposable product, the acceleration sensors may however be both relatively expensive with the total cost of the device and may consume power that enlarges the battery needed for the same recording time. It would therefore be beneficial if the sensor could be removed but the position and activity information could be derived in a different way.

[0446] The RIP belts according to embodiments described herein may be a movement sensor that may be affected by any body motion that affects the form of the abdomen or the thorax. Additionally, the alignment of the organs may change with the different body positions, and this may affect the movements of the thorax towards the abdomen. Upright position may mean that the abdomen pressure is taken off the diaphragm and therefore the thorax compartment, and this may show up in the RIP signals. Supine position may mean that the rib-cage is free from the arms to move up and down, while left and right positions are hindered by the pressure on the side, especially if an arm is pressing the side. Prone position may include pressure on both compartments.

[0447] Below, in Table 4-1, the validation and performance of a system and method as described above are provided wherein a 2-belt RIP system was used to determine the body position of the subject, comparing the predicted label of the body position to the true label of the body position, with an accuracy of 0.82 for the non-supine body position, 0.98 for the upright body position, and 0.82 for the supine body position. Thus, showing that the body position of the subject can be accurately or acceptably accurately determined based only on the signals of 2 RIP belts, thus simplifying the devices required and improving the accuracy of the HSAT sleep study.Table 4-1

[0448] A method of determining a body position and activity is provided using RIP signals. According to a first method, so, it is clear that the information of the body position are in the RIP signals and extracting them with an Al model trained towards a standard body position signals recorded in all sleep devices can be done. Activity is the same, any body movement that is large enough to move the abdomen or thorax, shows up as irregularity in the belts and can be marked with an Al model trained on the activity data from a sleep study.

[0449] According to some embodiments, a method may include training an Al model on RIP signal data and / or PSG data in order to identify irregularities with the data resulting from a body position or a change in body position. A method may also include receiving RIP signal data from one or more RIP belts and determining whether there were any irregularities. Based on the determination, a body position may be identified using a specially trained Al model for this purpose.

[0450] Section 7.11 Augmenting HSAT studies to Contain Full PSG Information According to Some Embodiments

[0451] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0) may provide a massive improvement for HSAT studies as they may allow the correct detection of all the AHI events and may provide a classification of sleep stages into WAKE / NREM / REM. With the information already in place from HSAT with embodiments of BS2, it doesn't take much to augment the information to complete the PSG picture. The inventors have demonstrated from their SelfAppliedSomnography recordings for Als (PSG) that the frontal EEG signals (recorded on the forehead) do contain everything that is needed to derive a PSG equivalent sleep staging accuracy. It may therefore be possible to record one or two EEG signals using the a recording device, such as a Nox T3s HSAT device, in addition to the regular HSAT signals and score the NREM periods into Nl, N2 and N3 based on the EEGs.

[0452] A method is provided for augmenting a HSAT study. The method includes recording with a recording device, such as a Nox T3s, a HSAT study with one or two additional frontal -EEG channels. A BodySleep analysis method or system, as described herein, is used to derive all the parameters that can be derived from the BS signals. An auto scoring is run on the EEG signals, determining sleep stages and arousals. The results are combined from both in a relative manner for highest accuracy PSG like outcomes, including PLMS from method #1 above, sleep staging, sleep time, and combined / optimal arousals.

[0453] According to some embodiments, combining processing on the EEG with the results from embodiments of BodySleep2, may provide accurate timing of the NREM periods and all the arousals, which may enable acquisition of the most accurate classification of sleep during NREM and may improve the accuracy of the overall sleep staging and arousals, is something new.

[0454] Section 7.12 Using Embodiments Described Herein (e.g., As Implemented in Embodiments of a Nox BodySleepl.O) for Augmenting CPAP Data for Improved Therapy Management

[0455] As described above, sleep care management using CPAP devices is based on data measured by the CPAP and delivered over radio modules to the cloud. The CPAP is however only in an indirect connection to the patient, "sees" the patient through the air-tube between the CPAP and the patient, based on the air-pressure and air-flow signals. Even if this gives the PAP device significant information on how well the patient is breathing, it does not have much to work with regarding how well he sleeps. This is especially difficult, as a patient on an inefficient treatment might not have direct apneas, but is half-cured, meaning that he might be struggling and having arousals. According to some embodiments, embodiments of a BodySleep2 Sensor in association with the CPAP data may be used to calibrate a simplified sleep study. A few night BodySleep sensor or system, as described herein, recording during CPAP treatment, may provide the information how well the patient slept during those nights on treatment and the information how to interpret the data from the CPAP up to the point of the BodySleep sensor recording and from that time on. This could improve the reliability of the data that the care managers have to work with and provide valuable and early warning if the patient's performance starts to degrade, which may eventually lead to the patient stopping using the therapy.

[0456] According to some embodiments, a method is provided wherein a BodySleep sensor may perform a recording on a patient using CPAP, preferably over multiple nights, and a BodySleep analysis method according to some embodiments described herein may be performed. The method may include comparing the received data from the CPAP and the measured data from BodySleep analysis method to augment the accuracy of the CPAP data.Post-data analysis may be performed on stored CPAP data to determine how the patient has been trending. The calibrated CPAP data model may be used in the future to keep trending the patient with high accuracy and to identify when and / or if he is at risk of quitting therapy.

[0457] Section 7.13 Using Embodiments Described Herein (e.g., As Implemented in Embodiments of a Nox BodvSleepl.O) for Determining a Likelihood of Success of a Considered Sleep Disorder Treatment or Projecting a Likelihood of Success of Sleep Disorder Treatment

[0458] Numerous types of treatments may be prescribed for a subject suffering from a sleep disorder, such as sleep apnea. These treatments may include, but are not limited to, a pharmacological treatment used to treat sleep apnea, an oral appliance used to treat sleep apnea, an implantable device used to treat sleep apnea, a hypoglossal nerve stimulation (HGNS), a Positive Airway Pressure (PAP) based treatment used to treat sleep apnea, a lifestyle intervention used to treat sleep apnea, a pharmacological treatment of Periodic Limb Movements of Sleep (PLMS), cognitive behavioral therapy for insomnia (CBTi). A pharmacological treatment may include a treatment with Glucagon-like Peptide 1 Receptor Agonists (GLP-1 agonists, Ozempic (semaglutide) or Rybelsus, or another an antidiabetic medication, a pharmacological treatment used to reduce weight of the subject), or simply a change in regimen, such as a diet, restricted caloric intake, reduced stress, increased exercise, primarily to reduce weight.

[0459] However, based on the physiological or anatomical basis for the sleep disorder breathing, treatments may have varying levels of success for different patients. As described in Applicant’s US Application 18 / 058,498, filed at the USPTO on November 23, 2022, entitled “Methods and Systems of Calibrating Respiratory Measurements to Determine Flow, Ventilation and / or Endotypes”, which is herein incorporated by reference in its entirety, an endotype is a subtype of a condition, which is defined by a distinct functional or pathobiological mechanism. This is distinct from a phenotype, which is any observable characteristic or trait of a disease, such as development, biochemical or physiological properties without any implication of a mechanism. It is envisaged that patients with a specific endotype present themselves within phenotypic clusters of diseases.

[0460] OSA endotyping may be a method for identifying the pathophysiological traits that contribute to OSA. For example, these traits may include upper airway collapsibility, upper airway muscle compensation, arousal threshold and loop gain. Understanding the pathogenesis of OSA for individual patients can be used for targeted treatment. Endotyping may be an integral part of precision OSA diagnosis and treatment.

[0461] OSA endotypes may be derived from patients’ breathing patterns, which may be captured with flow sensors. The main variable of interest may be the amount of ventilation during each minute of sleep (minute ventilation), which may be the basis for endotype determination. Calculating endotypes may be validated in laboratory settings using the gold standard pneumotach with a sealed oronasal mask. When used with an oronasal mask, the pneumotach measures unbiased flow and circumvents possible confounding effects of oral ventilation. The methods described herein may take the additional step to scaling the pneumotach method to RIP results, which may be available in Polysomnographic (PSG) sleep studies such that endotyping can be applied to standard PSG recordings.

[0462] As described in Applicants US Application 18 / 058,498, endotyping of a subject’s sleep disorder may be performed using RIP signals obtained from RIP belts. A flow may preferably also be considered to perform an endotyping of the subject’s sleep disorder. Further, sleep stages may be considered for endotyping a subject’s sleep disorder, as described in Applicant’s US Application No. 17 / 026,844, filed on September 21, 2020, which is also herein incorporated by reference in its entirely. Lastly, the methods described herein for determining arousal and arousal-associated events using Nox’s Body Sleep 2.0 may also be used in endotyping a subject’s sleep disorder, and based on this endotype, it may be determined whether a considered sleep disorder treatment will likely be effective or not.

[0463] Section 7.14 Obesity and Sleep Disorders

[0464] As discussed above, it may be determined whether a considered sleep disorder treatment will likely be effective or not using embodiments of the present disclosure. For example, regarding a pharmacological treatment using a weight-reducing medication, such as Ozempic, the inventors of the present application have found that while Ozempic may be helpful to help a subject reduce weight, such a treatment is not necessarily always effective in mitigating a sleep disorder.

[0465] Gap in Weight Management Care: The Critical Role of Sleep Care Management for GLP-1 Users

[0466] The inventors of the present application have found that there is an important connection between obesity and obstructive sleep apnea (OSA). Obesity is a condition that predisposes to a number of chronic medical conditions,! including OSA. Weight loss results in variable improvement in OSA severity, with rare cases of full remission.

[0467] GLP-1 agonists have demonstrated effectiveness in achieving meaningful weight loss, which in turn improves OSA. While this is certainly of value, one cannot equate significant improvement with curative results.

[0468] Before starting a GLP-1 agonist, it is crucial to screen patients for OSA, especially since those with obesity are at a higher risk of having OSA.3 Relying on weight loss alone to cure OSA has not been supported by conclusive evidence in the literature, and untreated OSA can lead to costly chronic medical conditions. Proper diagnosis, treatment, and ongoing management of OSA are essential to avoid the increased total healthcare costs and utilization linked with untreated OSA.

[0469] Obesity and OSA Connection

[0470] Obesity is associated with serious chronic medical conditions, including obstructive sleep apnea (OSA). In obese individuals, it has been shown that the prevalence of OSA can jump from 25 to 45%.4 GLP-1 agonists have shown efficacy in facilitating significant weight loss, consequently reducing OSA symptoms. However, while noteworthy, such improvements rarely equate to a cure. Partially treated OSA leaves patients with ongoing symptoms and at a higher risk of developing chronic medical conditions, leading to higher total healthcare costs.

[0471] The Effects of Weight Loss on OSA

[0472] Studies have demonstrated that weight loss results in variable improvement in OSA. Weight loss by either medical or surgical techniques resolves OSA in only a minority of patients. A systematic review and meta-analysis to assess the effects of surgical weight loss on the AHI identified 12 studies representing 342 patients. While bariatric surgery was found to significantly reduce OSA severity, the mean AHI after surgical weight loss was consistent with moderately severe OSA. It was concluded that patients undergoing bariatric surgery should not expect resolution of OSA (using the AASM 1 A hypopnea definition) after surgical weight loss and will likely need continued treatment to minimize its complications.

[0473] It is important to note that studies reporting the most favorable OSA outcomes with weight loss used a method that underestimates the AHI (AASM IB hypopnea definition was utilized rather than the recommended 1 A definition) and is consequently prone to overestimating improvement. Unless the 1 A hypopnea definition is used, the percentage of missed hypopneas increases as OSA severity decreases, exaggerating the degree of improvement. This is because the IB definition requires a greater drop in oxygen saturation and does not include events resulting in sleep fragmentation alone.

[0474] Weight Loss, the Illusion of OSA Resolution, and Consequences

[0475] Since OSA develops gradually over time, patients typically have no recollection of their prior status for comparison, and any improvement can be perceived as sufficient resolution. As a result, the patient’s perception is unreliable, and objective sleep testing maybe necessary using methods that comprehensively determine AHI , even if the patient is satisfied with their status after weight loss.

[0476] The assumption that OSA has resolved when it has only improved can give a false sense of security, while the remaining OSA may leave the patient with lingering impairment and at ongoing risk for associated chronic medical conditions.

[0477] Beyond Obesity: Anatomy Predisposing to OSA

[0478] There is a public misperception that OSA is entirely secondary to obesity and that weight loss resolves the problem. Weight gain and obesity (particularly central adiposity) may be important factors that predispose to OSA and can increase pharyngeal collapsibility through mechanical effects on pharyngeal soft tissues and lung volume as well as through central nervous system-acting signaling proteins (adipokines) that may affect airway neuromuscular control.

[0479] However, there may be underlying craniofacial anatomic features that determine vulnerability to OSA independent of weight, which may have to be taken into account. Mandibular, nasal, and oropharyngeal characteristics can predispose normal-weight individuals to OSA and compound the effects of weight gain.

[0480] Irreversible Neuromuscular Changes Resulting from OSA

[0481] Even for patients for whom weight gain may have been the sole predisposing factor for OSA, achieving ideal body weight after weight loss may not ensure resolution of OSA due to irreversible changes in the nerves and muscles of the oropharynx, which can remain prone to collapse during sleep. These changes may at least in part be caused by the vibration trauma from snoring.

[0482] Potential Benefits of GLP-1 Agonists for Treatment of OSA

[0483] With the emergence of weight loss benefits of GLP-1 agonist medications for the treatment of type 2 diabetes mellitus, the potential benefits of these medications for the treatment of obstructive sleep apnea (OSA) have been raised. The beneficial effects of GLP-1 agonist medications on OSA are attributed to the mechanism of weight reduction. A direct therapeutic effect on OSA has not been identified. Not yet peer-reviewed or published results of a recent study have shown that overweight or obese patients with moderate to severe OSA (AHI>15) taking the GLP-1 agonist Zepbound (tirzepatide) had an average of 20% weight loss and associated mean AHI reduction of 55%. Full details are not yet available for review, including the details of testing and calculation of AHI, as well as the actual starting and ending AHI values. The study was sponsored by the medication manufacturer, Eli Lilly.

[0484] Notably, patients with this level of weight loss are more likely to be in the higher BMI range and may not have achieved ideal body weight. In those cases, remaining OSA can be attributed to not only the remaining excess weight but also other factors not related to weight, as explained previously. Weight distribution may also be taken into account, and can determine the degree to which weight loss will affect the AHI.

[0485] The Advantages of Combined therapy

[0486] GLP-1 agonists hold promise as a supplement to CPAP for obese patients with OSA, who will benefit from combining both modalities or as an alternative to CPAP for patients unable to use CPAP or other OSA treatments. The advantages and mechanisms of combined therapy are summarized below.

[0487] Typically, more severe OSA requires higher CPAP settings, which can complicate treatment due to patient discomfort caused by the higher pressures, including an increased tendency for CPAP mask air leaks (which compromise treatment and disturb sleep) and air swallowing (which can cause gastrointestinal discomfort). Patient discomfort with high CPAP settings can decrease acceptance and long-term compliance. As mentioned, even though weight reduction by itself rarely resolves OSA, it usually decreases OSA severity and associated pressure requirements to effectively treat OSA, simplifying treatment and reducing patient discomfort. With this in mind, GLP-1 agonists can be considered an effective supplementary treatment for patients using CPAP, making it more comfortable for ongoing use.

[0488] Conclusion of Sleep Care Management for GLP-1 Users

[0489] Obesity is a condition that predisposes to a number of chronic medical conditions, including OSA. Weight loss results in variable improvement in OSA severity, with rare cases of full remission. GLP-1 agonists have demonstrated effectiveness in achieving meaningful weight loss, which can, in turn, reduce OSA severity but this is rarely curative due to other factors contributing to OSA. Untreated OSA puts a patient at a risk for associated chronic medical conditions, which if left untreated lead to higher healthcare costs.

[0490] The improvement in OSA resulting from weight loss secondary to GLP-1 agonist use can be expected to depend not only on the magnitude of weight loss, but also on other possible factors that contribute to OSA, including anatomic predisposition, age, and irreversible neuromuscular changes occurring as a result of OSA.

[0491] While CPAP remains the gold-standard therapy for OSA, the weight loss benefits of GLP-1 agonists raise the consideration of their potential use as adjunctive treatment for obese patients with OSA who are using CPAP and having problems with high-pressurerequirements and difficulty losing weight, or as an alternative treatment option for patients who are unable to use CPAP.

[0492] Patients seeking GLP-1 agonists present an opportunity to identify at-risk individuals without a prior diagnosis of OSA. It is recommended that a patient who is being referred for GLP-1 agonist therapy be screened for OSA since obesity increases a patient’s risk of having OSA. The inventors of the present disclosure have found that management of the full spectrum of sleep care from evaluation through treatment adoption and long-term adherence to therapy provides better results and treatment. The inventors’ comprehensive care framework and proven outcomes allow us to strategically implement optimal OSA management which can reduce total healthcare costs and utilization.

[0493] Accordingly, as described herein and further outlined in the enumerated embodiments of Group 6 provided below, it is noted GLP1 agonists when used as a weight reduction method will impact the physiological causes of sleep apnea. Using GLP1 agonists will likely reduce the severity of sleep apnea but may not eliminate it entirely. Therefore, the inventors of the present disclosure have found that it is likely that patients may benefit from a new treatment modality than they use when starting GLP1 agonist treatment. GLP1 agonists may become a treatment for sleep apnea. The inventors of the present disclosure have developed systems, methods, and devices for endotyping of sleep apnea as a method of determining the physiological causes of sleep apnea. Using sleep recordings it is possible to quantify certain parameters that indicate if the sleep apnea is primarily caused by the collapsibility of the upper airway (collapsibility), lack of muscle compensation (compensation), people waking up too easily when ventilation is disturbed (arousal threshold), or if the respiratory control is too sensitive to disturbances in ventilation (loop gain).

[0494] PSG sleep recordings are the standard method of doing a sleep recording to determine the severity and endotypes of sleep apnea. As described herein, it is possible to get an accurate measurement of the endotypes using an HSAT sleep study and even by only using two RIP belts.

[0495] The inventors of the present disclosure have found that it will likely become important for insurance companies and payors of medical treatment to be able to identify which patients are likely to benefit from GLP1 agonist treatment of their sleep apnea and who are less likely to benefit. The inventors of the present disclosure have also found that it will be highly valuable to be able to make the prediction based on a sleep recording done at scale in the patients homes using HSAT or two RIP belts.

[0496] The inventors of the present disclosure have therefore developed methods, systems, and devices for determining the physiological causes of sleep apnea using PSG, HSAT, or one or more, for example two, RIP belts according to some embodiments described herein. These methods, systems, and devices can be used to determine the likelihood of a patient benefiting from treatment with a specific treatment modality, such as GLP1 agonists, whereas each treatment modality may target only one or some of the physiological causes of sleep apnea.

[0497] Introduction

[0498] The inventors of the present disclosure have developed the methods, systems, and devices described herein and technology to measure physiological signals during sleep to diagnose sleep and sleep disorders. The methods and technology may include polysomnography (PSG) and polygraph (PG), home sleep apnea testing (HSAT), or home sleep testing (HST) recorders, sensors, and accessories. The methods and technology may further include software to configure the recorders, view sleep recordings, and manually score and interpret the sleep recordings. The software may also include automatic analyses of the physiological signals from the sleep recordings which are used to automatically score the sleep recordings, and also extract information from the recorded signals that may otherwise be unobtainable. Furthermore, the inventors of the present disclosure have developed methods, systems, and devices to determine the endotypes of sleep apnea which can be used to determine the physiological cause of sleep apnea in patients and may be used to guide treatment selection when personalizing sleep apnea treatment.

[0499] By incorporating the information derived from a sleep recording with other patient information such as medical records, medical history, life style, interventions, and other data it may be possible to build a more complete picture of the patient to prescribe the correct treatment at the point of diagnosis and make predictions on how the need for treatment dose or treatment modality may evolve over a period of time.

[0500] Currently the first line of treatment for sleep apnea is Positive Airway Pressure (PAP). The most common forms of PAP therapy are Continuous Positive Airway Pressure (CPAP), Bilevel Positive Airway Pressure (BiPAP), Automatic Titrating Positive Airway Pressure (APAP or AutoP AP), as well as Adaptive Servo-Ventilation (ASV). Other treatments to sleep apnea have emerged and are becoming more prominent. These treatments include medical devices such as oral appliance therapies (OAT) and hypoglossal nerve stimulation (HGNS). The alternative treatments also include lifestyle changes such as weight loss, limiting alcohol and caffeine intake or maintaining healthy sleeping habits, and positional therapy.Pharmacological interventions are also on the horizon with pharma companies developing drugs or drug combinations to address sleep apnea specifically or with sleep apnea treatment as an unintended effect of using certain medications. Further, myofunctional therapy and surgeries are used to treat sleep apnea.

[0501] Currently, the use of Glucagon-like Peptide 1 Receptor Agonists (GLP-1 agonists) to reduce body weight is on the rise. The evidence regarding their effectiveness to lower the severity of sleep apnea is building, but the reduction of body mass is known to reduce the severity of sleep apnea as measured by the Apnea-Hypopnea Index (AHI). Other pharmacological treatments on the horizon are the combination of aroxybutynin and atomoxetine by Apnimed, acetazolamide by Prof Jan Hedner at Goteborg University, tirzepatide by Eli Lilly, and more.

[0502] Other factors, beyond weight control and sleep habits, may influence the severity of sleep apnea in patients and may change over time. These factors include, but are not limited to, age, menopausal status of women, use of drugs or medications, and progression of comorbid disease.

[0503] Embodiments described herein may determine the optimal treatment of sleep apnea for a patient and how the optimal treatment may change in the future depending on interventions or other actions taken by the patient.

[0504] Section 7.15 The Future of Pharmacologic Therapies in Sleep Apnea

[0505] Introduction

[0506] The inventors of the present disclosure have found that sleep medicine is on the cusp of transformation. A new class of pharmacologic therapies may soon revolutionize obstructive sleep apnea (OSA) treatment by targeting the physiological roots of the disorder - modulating traits like arousal threshold, airway muscle tone, and ventilatory control stability. These therapies may offer a path to less invasive, better-tolerated, and more accessible options for millions of OSA patients.

[0507] However, the promise of these therapies also exposes a critical diagnostic gap in the field. Unlike continuous positive airway pressure (CPAP), which is prescribed broadly, pharmacologic treatments are endotype-specific, which means that they work only for patients whose OSA is driven by particular physiological traits.

[0508] A successful treatment may thus hinge on identifying appropriate candidates and monitoring therapy response over time. Without diagnostic systems capable of accurately characterizing endotypes, clinicians risk misapplying therapies, patients may experiencesuboptimal outcomes, and the healthcare system may struggle to support precision medicine at scale.

[0509] Given the increasing availability of pharmacologic treatments, the inventors have discovered that the need for precision is urgent. New drugs may be endotype-specific by design. Prescribing them without knowledge and / or understanding of a patient’s underlying physiology risks ineffective treatment, adverse events, wasted healthcare resources, and erosion of clinician and patient confidence in these therapies. Conversely, an excessive focus on drug treatments could discourage patients with OSA endotypes effectively managed by positive airway pressure (PAP) therapy from starting, adhering to, and persisting with PAP - exacerbating an already existing barrier to care.

[0510] The inventors have found that the path forward may require a fundamental shift in diagnostic strategy: from event-counting metrics like the Apnea-Hypopnea Index (AHI) and oximetry-based proxy signals like PPG and PAT to physiology -based diagnostics that are capable of measuring the underlying mechanisms of breathing and identifying the endotypes as predictors of therapeutic response.

[0511] Embodiments of the systems, methods, and devices described herein that may be rooted in Respiratory Inductance Plethysmography (RIP) may be uniquely capable of fulfilling this role. For example, the inventors’ Nox Flow and BodySleep technologies - based on calibrated RIP technology as discussed herein - may provide real-time, quantitative, and clinically relevant insights into this new era of pharmacologic treatment for OSA, aiding physicians to diagnose patients with confidence, select the right therapy, and monitor its effectiveness over time.

[0512] These benefits are not limited just to pharmacologic treatments, but instead represent the ability of embodiments described herein such as BodySleep to provide cost-effective, real time analysis of the efficacy of a given treatment plan.

[0513] Without such a level of precision, the field may risk a future where the wrong patients receive these potent therapies, leading to avoidable side effects, failed interventions, and further widening the existing gaps in care. Moving forward, precision diagnostics may not be optional and instead may be the foundation on which the success of pharmacologic OSA therapy will stand or fall.

[0514] Pharmacologic Therapies for OSA

[0515] For decades, PAP therapy has been the cornerstone of OSA treatment. While effective, PAP’s limitations are well -documented: discomfort, mask intolerance, and low long-term adherence rates, leading to high rates of treatment discontinuation. Many patients,unable or unwilling to tolerate PAP, remain untreated, exposing them to the health risks of unmanaged OSA, including cardiovascular disease, metabolic dysfunction, and cognitive decline.

[0516] In response to these challenges, pharmaceutical companies have recognized the unmet need for alternative therapies. A new wave of pharmacologic treatments is emerging, designed to target the underlying physiological drivers of OSA - offering the potential for less invasive, more tolerable, and accessible options for millions of patients. These therapies aim to modulate specific traits, such as:

[0517] Arousal Threshold: Sedative agents may help patients stay asleep during minor respiratory disturbance by raising the threshold at which arousals occur, provided this can be accomplished without increasing airway restriction or event duration.

[0518] Upper airway Muscle Tone: Agents like norepinephrine reuptake inhibitors increase pharyngeal muscle tone, reducing airway collapsibility.

[0519] Loop Gain: Medications that stabilize ventilatory control can help patients with unstable breathing patterns by reducing over-sensitivity to CO2.

[0520] These pharmacologic approaches may mark a paradigm shift - moving away from a one-size-fits-all model toward targeted, mechanism-specific therapy.

[0521] However, they are not universal solutions. Each drug is designed for a specific SOA endotype, and without the ability to identify these endotypes accurately, clinicians risk misapplication, suboptimal outcomes, and eroded trust in these therapies. Patients may also have features of more than one endotype, raising the consideration of targeted combination therapy.

[0522] Moreover, pharmacologic therapies introduce new demands on clinical workflows. Unlike PAP, these medications may require dose adjustments to ensure effectiveness and safety. This shift underscores the urgent need for physiology -based diagnostics that can match the right therapy to the right patient - and support ongoing care in the long term.

[0523] How Pharmacologic Therapies for OSA Work

[0524] As an illustrative example, Apnimed’s “AD 109” may exemplify the new wave of pharmacologic therapies designed to treat OSA by directly targeting the physiological traits - or endotypes - that underly the disorder. Unlike CPAP, which applies continuous positive pressure to splint the airway open, AD 109 works by modulating the patient’s own physiology during sleep. It combines two active components:

[0525] Atomoxetine: a norepinephrine reuptake inhibitor that increases sympathetic tone and enhances upper airway muscle activation, directly addressing the endotype of poor upper airway muscle compensation.

[0526] Aroxybutynin: a novel antimuscarinic that acts on key neurological pathways involved in OSA by stimulating upper airway dilator muscles to prevent obstruction and maintain airway patency during sleep.

[0527] This dual-action mechanism helps stabilize the airway physiologically to reduce OSA severity.

[0528] However, its success may depend entirely on matching the therapy to the right patient. A patient whose OSA is primarily driven by high loop gain (i.e., unstable ventilatory control) is unlikely to benefit from AD 109 and may experience side effects such as excessive sedation. Conversely, a patient who would respond well to PAP may be diverted away from an effective and proven solution if endotyping is not performed.

[0529] AD 109 is not an isolated example. The pharmacologic pipeline for OSA is expanding, with therapies in development targeting a range of physiological traits, including loop gain modulation, chemoreflex sensitivity, and airway structural properties.

[0530] As these treatments become available, clinicians may face a new set of challenges: determining which therapy is appropriate for each patient, how to titrate dosages, how to monitor efficacy, and how to manage side effects.

[0531] The Power of Endotypes: a Framework for Precision

[0532] Endotypes are the physiological traits that define how OSA manifests in each individual. They are the root causes behind the patterns of respiratory events seen during sleep - and understanding them may be essential for effective, personalized care. The four most clinically validated endotypes are:

[0533] Upper Airway Collapsibility: The ease with which the airway structurally collapses during sleep. Patients with high collapsibility often benefit form therapies that mechanically splint the airway, such as CPAP or oral appliances. A related endotype is the location of the collapse.

[0534] Upper Airway Muscle Compensation: The ability of airway muscles to respond to obstruction. Poor compensators may benefit from therapies like atomoxetine, which enhance neuromuscular tone.

[0535] Arousal Threshold: The sensitivity of a patient’s cortical arousal response to respiratory stimuli. A low threshold leads to frequent awakenings from minor disruptions, while a high threshold allows tolerance of more significant events without arousal.

[0536] Loop Gain: The stability of the ventilatory control system. High loop gain indicates an overly sensitive system that tends to overcorrect in response to CO2 changes, leading to cyclical breathing instability. These patients maty benefit from therapies like acetazolamide or oxygen therapy.

[0537] Endotyping is not theoretical - it is a clinically actionable framework that allows physicians to match the right therapy to the right patient. Research suggests that a substantial proportion of OSA patients do not have primarily anatomic causes of obstruction; instead, they present with combinations of high loop gain, low arousal threshold, or poor compensation. Without identifying all of these factors, clinicians are left to make decisions on incomplete data.

[0538] Accordingly, endotypes may be key to unlocking the full potential of pharmacologic therapy. Precision medicine for OSA may only be possible when diagnostics can measure what matters: the physiology of each patient’s condition.

[0539] The Inadequacy of Proxy -Based Diagnostics

[0540] Many commercially available diagnostic systems attempt to infer respiratory patterns using proxy signals such as peripheral arterial tonometry (PAT), photoplethysmography (PPG), mandibular movement sensors, or sound. While these technologies may offer some utility in screening for sleep-disordered breathing, they may be fundamentally inadequate for endotype-based precision diagnostics.

[0541] Proxy signals are indirect markers of respiratory physiology. They rely on downstream effects of respiratory events, such as changes in vascular tone, heart rate variability, or movement, rather than directly measuring the mechanics of breathing. As a result, they may suffer from critical limitations such as:

[0542] Diagnostic Ambiguity: Proxy signals may be influenced by factors unrelated to respiration, including medications, autonomic dysfunction, cardiovascular comorbidities, skin pigmentation, and external artifacts. They can neither isolate nor quantify the specific mechanisms driving OSA.

[0543] Inability to Detect Endotypes: Proxies may be entirely incapable of distinguishing between patients with high loop gain, low arousal threshold, or upper airway collapse. They may provide no insight into ventilatory control stability, airway muscle responsiveness, or the physiological response to therapy.

[0544] Diagnostic Blind Spots: Proxy systems may be less effective in patients with hypopnea-dominant OSA, subtle flow limitation, or fragmented sleep patterns without significant desaturation. These cases are often misclassified or entirely missed.

[0545] Incompatibility with pharmacologic Monitoring: Because proxy signals may not reflect actual ventilatory patterns, they cannot reliably measure the physiologic changes by pharmacologic treatments, such has improved muscle tone or altered arousal dynamics.

[0546] The consequences of relying on proxies may be diagnostic uncertainty, misdiagnosis, misaligned therapy, and the perpetuation of care gaps. In the context of pharmacologic OSA treatment, where understanding the specific pathophysiology is essential, proxies may simply be unable to provide the resolution or reliability clinicians need to make informed, confident decisions.

[0547] In contrast, direct, physiologic measurement - such as calibrated RIP as described herein - may support the precise matching of therapies to patients, enabling the promise of precision medicine in sleep apnea care.

[0548] The Diagnostic Solution: Nox Flow and Calibrated RIP

[0549] An embodiment of the present disclosure, termed “Nox Flow”, may be built on calibrated RIP, and may be a diagnostic platform that delivers quantitative and physiologybased measures of the actual mechanics of breathing, including physiologic insight into OSA endotypes.

[0550] Unlike proxies, which may attempt to infer breathing patterns from secondary signals, Nox Flow may captures the actual respiratory volume and flow shape. Key capabilities of Nox Flow may include:

[0551] Quantitative respiratory flow measurement: Capturing precise, calibrated signals of airflow and effort.

[0552] Detection of flow limitation and inspiratory effort: Differentiating obstructive from central events and identifying collapse dynamics.

[0553] Measurement of ventilatory instability and loop gain: Providing insights aiding targeted therapy selection for unstable control phenotypes.

[0554] Direct arousal detection from ventilatory response: Providing objective markers for therapies that modulate arousal threshold, even without having to record EEG.

[0555] Sleep stage classification via respiratory signatures: Enabling assessment of sleep architecture and REM-dependent phenomena, even without EEG.

[0556] By combining high-fidelity hardware, advanced signal processing, and Al-powered analytics as described herein, Nox Flow may aid endotype-driven care at scale, whether in the lab or the home. This may represent a fundamental departure from proxy-based systems, which may be unable to match the accuracy, reliability, or clinical relevance of flow measurement derived from precise respiratory parameters.

[0557] Beyond Diagnosis: Supporting Therapy Titration and Longitudinal care

[0558] Pharmacologic therapy for OSA may not be a static intervention; it may require dynamic management similar to other chronic conditions such as hypertension or diabetes. These therapies may require a closed-loop model of care - from identifying the right candidates to selecting therapy, titrating dose, monitoring outcomes, and adjusting the plan as patient physiology is modified.

[0559] Clinicians may need to manage the entire care continuum by utilizing objective, physiology -based data at each stage of therapy:

[0560] Confirming Endotype Alignment: Before initiating therapy, it should be confirmed that a patient’s physiological profile matches the intended mechanism of action - such as identification of poor muscle compensation for agents that augment upper airway neuromuscular activation.

[0561] Titrating Does with Confidence: Pharmacologic therapies may require careful dose adjustment to balance efficacy with safety. Clinicians should track key physiological markers - like arousal burden, ventilatory control stability, and airway compensation - across multiple nights to guide these changes.

[0562] Monitoring Long-Term Outcomes: Sleep apnea may be a dynamic condition, and patient physiology may evolve over time. Ongoing assessment of therapy impact should be practiced to optimize care, identifying when adjustments are needed, and avoiding unnecessary dose escalation or prolonged exposure to ineffective treatments.

[0563] Detecting Unintended Effects: Some pharmacologic agents may introduce new risks such as excessive sedation, impaired ventilatory responsiveness, or worsening of comorbidities. Clinicians should have the capability to detect these changes early to ensure safe, effective prescribing.

[0564] This level of precision - understanding why events occur, how they respond to interventions, and when therapy must change - may not be achievable with event-counting metrics like AHI or proxy signals such as PPG or PAT. It may require respiratory physiology-based diagnostics that measure the underlying mechanisms of OSA and provide actionable insights into endotypes.

[0565] As pharmacologic therapies for OSA enter the market, the field should move beyond counting events and embrace tools that enable a truly individualized, endotype-driven approach to care, such as embodiments described herein.

[0566] Combination Approaches

[0567] While pharmacologic therapies for OSA may provide a critical advancement in care, these therapies likely have a fundamental limitation: these therapies typically reduce the severity of OSA but may not fully resolve it. By design, pharmacologic agents may target specific physiological traits, such as low arousal threshold or poor airway muscle compensation - but they may not address all contributing factors. This may mean that for many patients, these therapies will only partially improve symptoms rather than fully resolve OSA.

[0568] This fundamental limitation points to the role that combination therapy may have in future OSA care. The agents may improve specific physiological mechanisms, such as stabilizing the airway or reducing arousals, but patients may still require additional therapies - such as PAP therapy at lower pressures or oral appliances - to achieve optimal outcomes.

[0569] Once again, the success of these combination strategies may hinge on precise endotyping. Without a clear understanding of which traits drive an individual patient’s OSA, clinicians risk applying therapies inappropriately - exposing patients to side effects, delaying effective treatment, and undermining confidence in both pharmacologic and traditional therapies. Endotyping may not be an academic exercise; it may be the clinical key to unlocking the full potential of both pharmacologic and combination approaches.

[0570] The future of OSA management may not be about choosing between pharmacologic or mechanical therapies - it may instead be about integrating multiple modalities in a precision-guided, patient-centric model. The agents may be a powerful new tool, but their role may be as part of a comprehensive, combination approach to care.

[0571] Accordingly, the promise of pharmacologic therapies may be real but incomplete. By embracing combination strategies - rooted in robust endotyping - can patients receive optimized, patient-centered care that transforms outcomes in OSA.

[0572] Nox Flow and Calibrated RIP

[0573] Nox Flow may be built on validated RIP technology according to embodiments described herein and may be built to deliver quantitative and physiology -based data on the actual mechanics of breathing. Unlike proxy systems that infer respiratory events from downstream signals, calibrated RIP may capture the actual dynamics of airflow and thoracoabdominal expansion - which may provide a direct window into the physiological traits that drive OSA.

[0574] Some embodiments described herein may be termed “DeepResp™” or “DeepRespHSAr” or simply “DeepResp”, and such embodiments may provide a system at the heart of this system. DeepResp™ may include an advanced Al engine such as theBodySleep2.0 according to some embodiments described herein which may transform complex physiological data into clear, actionable insights.

[0575] Embodiments of DeepResp™ may include applying sophisticated, particularized, and / or specialized algorithms to multi-night recordings, extracting key markers such as flow limitation patterns, ventilatory instability (loop gain), arousal threshold, compensation capacity, and sleep staging. By automating the analysis of RIP signals into endotype profiles, DeepResp™ may aid clinicians to make informed therapy decisions, whether selecting the proper treatment, titrating pharmacologic agents, or monitoring long-term outcomes.

[0576] Together, Nox Flow and DeepResp™ may form an integrated precision diagnostic platform that may deliver:

[0577] True Respiratory Flow and Effort: Direct measurement of airflow dynamics, not estimates

[0578] Endotype Identification: Insight into the underlying physiology, including collapsibility, arousal threshold, loop gain, and compensation.

[0579] Respiratory Arousal Detection: Quantifying arousal burden ,a key driver of sleep fragmentation and associated symptoms, which can persist despite otherwise seemingly effective treatment.

[0580] Sleep Staging Without EEG: REM detection and sleep architecture analysis using thoracoabdominal signals.

[0581] Therapy Guidance: A foundation for aiding selection, titration, and evaluating pharmacologic treatments.

[0582] A high level of precision may be essential for matching therapies to the right patients and ensuring safe, effective, and long-term management of OSA. Nox Flow and DeepResp™ may not just be tools for diagnostics - but as well provide an insight to the parameters that are the foundation of precision medicine in sleep care.

[0583] Conclusion

[0584] Pharmacologic therapies for OSA represent a breakthrough - an opportunity to offer patients alternatives to CPAP that target the root causes of their condition. But this promise may only be fulfilled if these therapies are matched to the right patients, based on a precise understanding of their individual physiology.

[0585] Without diagnostic systems capable of identifying endotypes, the filed may risk a future where pharmacologic treatments are misapplied, where the wrong patients receive the wrong therapies, and where side effects, therapy failures, and wasted resources erode trust in bot the treatments and the filed itself. Worse, patients who would benefit from well-established therapies like CPAP may be sidelined in the rush toward novel drugs, further widening care gaps.

[0586] Nox Flow, which may be built on validated RIP according to embodiments described herein, may be a scalable diagnostic platform that provides insights to the real-time, quantitative, physiology -based data aiding clinicians to guide treatment selection, titrate dosing, and monitor response over time, parameters that are the foundation upon which the safe, effective, and responsively use of pharmacologic therapies will depend.

[0587] Embodiments described herein may provide a multi-purpose accurate, scalable and affordable way for diagnosing and monitoring patients on treatment for multiple nights. A 2xRIP single patient sleep test sensor, powered by DeepRESP™, may provide the ingredients necessary for diagnosis, treatment selection, treatment titration and remote patient monitoring as follow up on treatment.

[0588] The future of sleep medicine may be precision medicine. Nox Flow may not just be a tool for diagnostics - it may provide the insights to the parameters that may be the foundation upon which the safe, effective, and responsible use of pharmacologic therapies will depend. Embodiments described herein may allow the field to integrate physiology-based diagnostics into care pathways, ensuring that patients receive the right treatment, at the right time, for the right reason.

[0589] Section 7.16 Monitoring Treatment Efficacy and Dose Titration According to Some Embodiments

[0590] The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 and / or in a DeepResp™ system) can be a fundamental building block in an inexpensive sensor device (such as a 2-belt RIP sensor device) that can be used by patients to monitor the performance of the treatment they receive for their sleep disorders. The device can be shipped to the patient at some point in time and the patient can use the device with their treatment in their own home. The systems, sensors, and methods described herein (e.g., as implemented in embodiments of a Nox BodySleep2.0 and / or in a DeepResp™ system) may provide a 2 belt sensor to detect sleep stages and arousals in the patient along with changes in breathing, such as apneas and hypopneas. The systems, sensors, and methods described herein also may provide accurate and reliable endotyping of a patient’s sleep.

[0591] Endotyping may provide for the prediction of the efficacy of a pharmacologic treatment. For example, if the endotype indicates that the patient does not have poor muscle compensation, then a treatment including an agent that augments upper airwayneuromuscular activation would likely be ineffective. If the endotype instead indicated that the patient has a low arousal threshold, then a treatment directed towards increasing the person’s arousal threshold would likely be effective.

[0592] In addition to providing for an accurate prediction of the efficacy of a pharmacologic treatment, the systems, sensors, methods, and embodiments of the present disclosure also allow for continual monitoring and adjusting of the treatment which may improve patient safety and economic efficiency.

[0593] For example, patients with PLMS are often treated with pharmacologic treatments. However, these treatments are often based on the initial diagnosis, with no follow up investigations being done as to the efficacy. These follow up investigations may be necessary, as the drug may need to be titrated over time in order to hit the maximum cost / benefit levels. Not performing follow up diagnostics to judge the efficacy of the treatment poses similar risks discussed herein of decreased patient safety, decreased confidence in the treatment, and increased costs to the system.

[0594] As the patient undergoes the treatment, embodiments of the present disclosure may enable a continually updating picture of the sleep health of the patient. The diagnostic information generated by the embodiments can be used to show whether a treatment remains effective or needs to be adjusted. For example, a patient with PLMS may require a higher dosage that previous dosages because the PLMS remains untreated. The only way to know whether this is true may be to conduct the follow up diagnostics, which are enabled by embodiments described herein.

[0595] The inventors of the present disclosure found that the novel pharmacologic treatments that are making their way into the market may need to be titrated over time, starting patients at a low dosage until the point is reached where increasing the dosage would do more harm than good. Using data from embodiments described herein, the dose may be titrated night by night until this optimum dosage is reached. Such diagnostic studies may take place over the course of a single night or many nights.

[0596] As an illustrative example, the new pharmacologic treatments may include drugs that simultaneously affect the patient Compensation and Arousal Threshold, which are two of the endotypes that the DeepResp™ outputs. If the output of the DeepResp™ indicates that the patient has those endotypes, then it may indicate that the drug is a good fit (i.e., the Compensation is a key contributor to the patient’s OSA). From the initial dosage, the patient may continue to be monitored by the system overnight over one or more nights. The dose may then be titrated and the patient may see the Compensation increase while the arousalthreshold does not and the AHI drops. The dose may then be increased until such increases in dosage offer no or a negative effect, such as the Compensation is not increased with higher dose, there is an increase in arousals and sleep disturbance or other negative effects show up.

[0597] The BodySleep2.0 and other embodiments described herein may provide an optimal tool for this type of titration as they may provide the signals required for the DeepResp™ processing of endotypes.

[0598] One advantage of using calibrated RIP as described herein is that doing so may enable the field to pivot from a subjective approach to treatments to an objective approach to treatments. Currently, dosage amounts may be corrected, if ever, based on a patient’s subjective experience after receiving the dose. For example, the patient may report feeling less tired during the day. This has the downside, however, that the patient’s subjective feelings may not reflect whether the patient has actually been cured or if the treatment could be improved based on objective data.

[0599] The systems, sensors, and methods described herein may provide an objective, data driven approach to determining and monitoring treatments of sleep disorders by detecting and analyzing the sleep stages, arousals, and endotypes of the patient. This shift from subjective to objective may also enable more cost-effective treatment protocols to be developed. Instead of relying on subjective patient descriptions, the treatment of the sleep disorder may be personalized to the patient until the objective metrics indicate that the sleep disorder has been treated and / or is being treated optimally and / or successfully.

[0600] The treatment discussed above may be any treatment for any sleep disorder and / or any combination of any treatment for any number of sleep disorders. Treatments for sleep disorders may include pharmacologic treatments (e.g., a drug), CPAP, oral appliances, implants such as hypoglossal nerve stimulation (Inspire, Genio, and the like) and implants such as phrenic nerve stimulation, and / or other implants.

[0601] Treatments may be combined with one another to treat one or more sleep disorders. Sleep disorders may include OSA, PLMS, and Narcolepsy. For example, a treatment may include a pharmacologic treatment that targets a specific endotype and a CPAP treatment that targets the same or another endotype.

[0602] The systems, sensors, and methods described herein may provide the necessary data and analysis to allow for optimization of treatments. For example, the system may gather first RIP data according to one or more methods described herein for a first night. The system may also gather RIP data according to one or more methods described herein for a second night. Based on the arousal events, the endotypes, or any other features derived from the data suchas sleep stages, the systems may determine the effectiveness of the treatment as well as whether the treatment needs to be modified. For example, if, after the first night, the data indicates that the number of arousals did not change or that the endotype is still present, then the treatment may be changed or the system may recommend and / or predict a change to the treatment. The recommendation may then be applied to the treatment. Then, if, after the second night, the data indicates that the treatment’s effectiveness improved or if there was no change, then the system may make a new recommendation and / or prediction accordingly.

[0603] As an illustrative example, a patient may present with OSA. The system may monitor the patient’s sleep over a first night and, based on the data gathered and analysis performed on that data, recommend a treatment that would fit the endotypes of the sleep. The recommended treatment may include any of those treatments discussed herein such as CPAP, an oral appliance, and / or a pharmacologic treatment. The system may also recommend initial settings, such as CPAP pressure and / or dosage amount, that would likely be fitting for the patient’s sleep disorder, in this case OSA. If the patient presents with multiple sleep disorders, for example both OSA and PLMS, then the system may provide a recommendation of treatment for one or any number of the sleep disorders.

[0604] The patient may then begin the treatment. The system may then monitor the patient over a second night and gather and analyze data for the second night according to the methods, sensors, and systems described herein. The system may then be configured to compare the data from the first night with the data from the second night and, if the comparison indicates that a change is necessary, recommend the proper change. For example, if the data from the second night indicates that the number of arousal events decreased slightly, the system may recommend an increase in the dosage and / or pressure of the CPAP.

[0605] This method may be applied over one or any number of nights until changing the treatment no longer provides a positive effect. Additionally, intelligent search methods may be employed to find the optimal treatment. For example, instead of simply incrementing the dosage amount of a pharmacologic treatment, the dosage amount could be stepped up logarithmically or exponentially to reduce the number of steps required to find the optimal treatment.

[0606] The systems, methods, sensors, and embodiments of the present disclosure thus may provide an objective, data driven approach to sleep health and treatment of sleep disorders that improves the patient experience.

[0607] The systems, methods, sensors, and embodiments of the present disclosure may also be combined with the subjective experience of the patient to provide for both subjective andobjective metrics of treatment. For example, embodiments of the present disclosure may include an app on a patient’s phone that is connected to the devices described herein (e.g., a device implementing BodySleep 2.0). The device may include one or more RIP belts and may be configured according to the present disclosure to retrieve RIP data from a patient. The app may be configured to receive this data from the device. The app may also allow a user to input the user’s subjective experiences before, during, and after treatment. The treatment may then be adjusted according to the objective metrics from the sensors as well as the subjective metrics from the patient. In at least such a way, embodiments of the present disclosure may enable a combination of objective and subjective approach to patient care.

[0608] The systems, methods, sensors, and devices according to some embodiments described herein may implement a specially trained Al model, for example embodiments of the BodySleep2.0 which include an Al model described herein to accomplish the above treatment monitoring and efficacy treatment. To this end, the Al model may be trained on RIP data and / or PSG data to determine AHI.

[0609] Section 7.17 Further Embodiments Of Systems, Methods, and Devices

[0610] Section 7.17.1 Prediction / Proposed Outcome Based on Sleep Endotype According to Some Embodiments

[0611] Similar to the above disclosed approach with GLP-1, embodiments of the present disclosure may identify an outcome of a treatment — such as efficacy for OSA or another sleep medicine intervention — based on endotypes derived from RIP signals. For instance, if the embodiments of the methods described herein yield a result of a determination or indication of a particular endotype, that could indicate which drug is likely to be effective. Such treatments may include treatments for OSA as well as other sleep disorders such as PLMS and others described herein.

[0612] Section 7.17.2 Initial Dose Prediction for Single or Multi-Component Drugs According to Some Embodiments

[0613] Systems, methods, and embodiments described herein may enable the prediction of an effective starting dose for a drug or drug combination, as well as any other type of treatment (e.g., CPAP pressures, oral appliance settings, or settings for implants such as hypoglossal nerve stimulation (Inspire, Genio, and the like) and implants such as phrenic nerve stimulation, and other implants). For example, a drug may have one component to enhance Compensation and another to increase arousal threshold. Selecting a good starting dose in this way may make titration more efficient, requiring fewer steps to reach the optimal dose. Suchtreatments include treatments for OSA as well as other sleep disorders such as PLMS and others described herein.

[0614] Section 7.17.3 Use of Multi-Night or Single-Night Sleep Studies for Dose Optimization According to Some Embodiments

[0615] Multi and Single Night studies may be conducted using the methods, systems, and embodiments described herein to measure how a dose of a pharmacologic treatment and / or any other treatment affects endotypes over time. For example, if a patient presents with both low compensation and low arousal threshold, the doses may be adjusted accordingly and track the resulting endotypes night by night to find the optimal dosage that maximizes benefit and minimizes adverse effects.

[0616] The treatment may include an initial dose a drug and / or any other starting condition of any other treatment (e.g., CPAP pressures, oral appliance settings, or settings for implants such as hypoglossal nerve stimulation (Inspire, Genio, and the like) and implants such as phrenic nerve stimulation, and other implants). Such treatments include treatments for OSA as well as other sleep disorders such as PLMS and others described herein.

[0617] Section 7.17.4 Predictive Titration Embodiments to Accelerate Optimization According to Some Embodiments

[0618] By analyzing data across titration nights, embodiments described herein may predict and recommend dose adjustments. This may drastically reduce the time and number of steps needed to reach the optimal dose.

[0619] The treatment may include an initial dose a drug and / or any other starting condition of any other treatment (e.g., CPAP pressures, oral appliance settings, or settings for implants such as hypoglossal nerve stimulation (Inspire, Genio, and the like) and implants such as phrenic nerve stimulation, and other implants). Such treatments may include treatments for OSA as well as other sleep disorders such as PLMS and others described herein.

[0620] As an illustrative example, if the patient has a true optimal dosage of a given pharmacologic treatment, but the initial dose is not equal to that optimal dosage, the dosage amount may be varied over multiple nights until the optimal dosage is found. Embodiments described herein may provide a baseline for quickly and accurately finding the optimal dosage by providing an objective way to classify sleep as discussed herein.

[0621] Embodiments described herein may include a simple increment or decrement of the dosage amount until the optimal amount is found. Additional or alternative embodiments may include a more sophisticated approach such as a logarithmic or exponential increase or decrease to quickly reduce the range of possible dosage and / or settings amounts.

[0622] In some embodiments, a method for titrating a dosage amount may include gathering sleep data, for example obtaining RIP signal data from one or more RIP belts, for one or more nights, preferably at least two or more nights, receiving the data at an Al model such as a neural network, using the Al model to transform the one or more RIP signal data to an output list of sleep stages and / or arousal events and / or PLMS events, comparing the output list over the one or more nights, and, based on a determination that the dosage amount needs to be adjusted, adjusting the dosage amount. The determination that the dosage amount needs to be changed may be performed by the Al model, and the Al model may make an indication of the amount by which the dosage and / or settings need to be changed (e.g., increased or decreased).

[0623] Section 8 Detecting Arousals and Sleep from Respiratory Inductance Plethysmography (RIP) and a Related Study

[0624] Abstract

[0625] Purpose: Accurately identifying sleep states (REM, NREM, and Wake) and brief awakenings (arousals) is essential for diagnosing sleep disorders. Polysomnography (PSG) is the gold standard for such assessments but is costly and requires overnight monitoring in a lab. Home sleep testing (HST) offers a more accessible alternative, relying primarily on breathing measurements but lacks electroencephalography, limiting its ability to evaluate sleep and arousals directly. The inventors of the present disclosure conducted a study which evaluated an embodiment that included a specialized deep learning algorithm according to some embodiments described herein which determines sleep states and arousals from breathing signals.

[0626] Methods: An example of an embodiment described herein was developed to classify sleep states and detect arousals from respiratory inductance plethysmography signals. Sleep states were predicted for 30-second intervals (1 sleep epoch), while arousal probabilities were calculated at 1 -second resolution. Validation was conducted on a clinical dataset of 1,299 adults with suspected sleep disorders. Performance was assessed at the epoch level for sensitivity and specificity, with agreement analyses for arousal index (Ari) and total sleep time (TST).

[0627] Results: The embodiment achieved sensitivity and specificity of 77.9% and 96.2% for Wake, 93.9% and 80.4% for NREM, 80.5% and 98.2% for REM, and 66.1% and 86.7% for arousals. Bland-Altman analysis showed Ari limits of agreement ranging from -32 to 24 events / hour (bias: -4.4) and TST limits from -47 to 64 minutes (bias: 8.0). Intraclass correlation was 0.74 for Ari and 0.91 for TST.

[0628] Conclusion: The embodiment identifies sleep states and arousals from breathing signals with agreement comparable to established variability in manual scoring. These results highlight its potential to advance HST capabilities, enabling more accessible, cost-effective and reliable sleep diagnostics

[0629] Section 8.1 Introduction

[0630] During sleep, the brain transitions between different states: rapid eye movement (REM) sleep, non-REM (NREM) sleep (which encompasses Nl, N2, and N3), and wakefulness. Monitoring these states may be crucial for diagnosing and assessing various sleep disorders which may be characterized by disruption of the usual patterns and duration of NREM and REM sleep, or an unusual number of awakenings or arousals. This is typically done using polysomnography (PSG) equipped with electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), electrocardiography (ECG), respiratory inductance plethysmography (RIP), nasal cannula, and pulse oximetry. However, PSG studies are expensive and often inconvenient for patients, leading to the adoption of home sleep testing (HST) as a more accessible alternative that focuses primarily on breathing and oxygenation signals. While HST may be more affordable and easier to administer it has certain limitations. Notably, it cannot accurately assess sleep states and arousals due to the absence of EEG, EOG, and EMG measurements. These limitations reduce the effectiveness of HST in diagnosing sleep disorders other than sleep apnea. Moreover, it may result in underdiagnosis of sleep apnea in patients with reduced sleep time or those with a high proportion of hypopneas associated with arousals rather than desaturations.

[0631] Sleep states and arousals may be inferred from breathing patterns. For instance, breathing during wakefulness is characterized by volitional overwrite of breathing control, including swallows, sniffs, breath-holds, speech, sighs, coughs, and body movements. In contrast, breathing is remarkably monotonous during NREM sleep, controlled primarily by metabolic demand. During REM sleep, breathing becomes more variable, both in terms of breath amplitude and timing. Additionally, REM sleep is characterized by a significant reduction in skeletal muscle tone, with breathing predominantly driven by the diaphragm. This loss of muscle tone affects the intercostal muscles, whose contraction expands the chest wall, leading to a distinctive breathing pattern during REM where the chest wall caves in during inspiration. These variations in breathing dynamics during sleep reveal a strong coupling between the sleep states and physiological changes that are reflected in the breathing patterns.

[0632] Likewise, arousals may also be detected by analyzing breathing patterns. Arousals may be brief awakenings from sleep, often triggered by stimuli such as loud sounds or breathing obstructions. These arousals may be associated with sympathetic activation within the autonomic nervous system, leading to increases in heart rate and blood pressure. Additionally, ventilation dynamics may be altered following arousal through both chemical and state-related mechanisms. Accompanying arousals may be an increased activation of skeletal muscles, including the engagement of the upper airway dilator muscles. This muscle activation may play a crucial role in resolving upper airway obstructions, particularly in the context of sleep apnea. Arousals have further been shown to cause a transient increase in ventilation, a gasp-like reflex, that is called the ventilatory response to arousal (VRA). This reflex is independent of metabolic demand and occurs even in the absence of upper airway obstruction (e.g., apnea and hypopnea). Research on auditory-induced arousals demonstrated that in addition to an increase in ventilation, the VRA is accompanied by a decrease in inspiratory duration and remains consistent across different sleep states.

[0633] To measure breathing movements of the chest wall and abdomen, both PSG and HST may rely on RIP technology. High-quality RIP belts have been shown to provide a reliable measure of airflow, with strong correlation to nasal cannula readings. The ability of RIP to simultaneously measure the dynamics of chest wall movements and airflow means that it captures all the relevant physiology required to assess sleep states and arousals from breathing.

[0634] In this disclosure, embodiments of a certain artificial intelligence (Al) are described to infer the relationship between sleep and breathing, developing embodiments that may accurately detect sleep states and arousals solely from breathing. This may enable subsequent calculation of total sleep time (TST) as well as arousal index (Ari) — an indicator of sleep fragmentation — from HST, significantly expanding its scope and efficacy. This innovative approach has the potential to transform HST by providing a comprehensive assessment of sleep, while simultaneously paving the way towards more accurate and accessible diagnosis of sleep disorders

[0635] Section 8.2 Materials and Methods

[0636] Certain embodiments described herein, for example embodiments described as “Nox Body Sleep 2.0” (NBS2) may include a specialized Al algorithm designed to determine sleep states and detect arousals using abdominal and thoracic RIP signals. This Al may be trained on RIP signal data and / or PSG sleep study data in order to determine the sleep states and detect arousals using abdominal and thoracic RIP signals. The input signals, for example...

Claims

CLAIMS:

1. A method for identifying Periodic Limb Movement during Sleep (PLMS) in a sleep study of a subject, the method comprising: determining arousal or arousal-associated events in the sleep study of the subject by obtaining data from one or more body signals, the one or more body signals being non-brain signals, and determining arousal or arousal-associated events of the subject using the data from one or more body signals; determining whether the arousal or arousal-associated events are PLMS events based at least in part on a periodicity of a plurality of such arousal or arousal -associated events.

2. The method according to claim 1, wherein the step of determining whether the arousal or arousal-associated events are PLMS events includes identifying one or more respiratory events based on one or more respiratory signals obtained from the subject during the sleep study; determining if the arousal or arousal-associated events are associated with the respiratory event.

3. The method according to claim 1, wherein determining the arousal or arousal-associated event includes using classifier to perform a classification of the of the one or more body signals.

4. The method according to claim 3, wherein the classifier is a neural network, an artificial neural network, a decision tree or trees, forests of decision trees, clustering, a support vector machine, a convolutional neural network (CNN), a machine learning algorithm, and / or a transformer neural network.

5. The method according to claim 1, wherein the one or more body signals include one or more respiratory signals obtained from the subject during the sleep study.

6. The method according to claim 1, wherein the one or more body signals are non-cardiac body signals.

7. The method according to claim 1, where the one or more body signals are not a limb electromyography (EMG) signal.

8. The method according to claim 1, wherein the one or more body signals are indictive of a respiratory activity of the subject.

9. The method according to claim 1, wherein the one or more body signals used in determining the arousal or the arousal-associated event in the sleep study of the subject include the one or more respiratory signals used in identifying the one or more respiratory events.

10. The method according to claim 1, wherein the one or more body signals and the one or more respiratory signals include the same respiratory inductance plethysmography (RIP) signals.

11. The method according to claim 1, wherein the one or more body signals include a thorax effort signal (T), the thorax effort signal (T) being an indicator of a thoracic component of the respiratory effort, and an abdomen effort signal (A), the abdomen effort signal (A) being an indicator of an abdominal component of the respiratory effort.

12. The method according to claim 1, wherein the one or more body signals further includes a signal of an acceleration signal indicating an acceleration of a body part of the subject.

13. The method according to claim 1, further comprising performing a prediction for each of a series of time intervals and aggregating the predictions to score an arousal event or an arousal-associated event .

14. The method according to claim 1, wherein the arousal or arousal-associated event of the subject is determined without an EEG signal.

15. The method according to claim 1, wherein the one or more body signals further comprise an additional body signal that is not a respiratory signal.

16. The method according to claim 1, wherein both the determining of the arousal or arousalevent of the subject and identifying one or more respiratory events are both based only RIP belt signals.

17. A hardware storage device having stored thereon computer executable instructions which, when executed by one or more processors of a computer system, configure the computer system to perform the method according to claim 1.

18. A system for identifying Periodic Limb Movement during Sleep (PLMS) in a sleep study of a subject, the system comprising: a receiver configured to receive one or more body signals, the one or more body signals being non-brain signals; a memory storage having instructions stored thereon; and a processor configured to perform the method according to claim 1.

Images