Inter-beat interval sequence of heart for supporting detection of obstructed sleep apnea

Abstract

There is provided a method for an apparatus for supporting detection of obstructed sleep apnea (OSA), comprising: obtaining, by the apparatus, an inter-beat interval (IBI) sequence of the heart of the subject; performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject; obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject; determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined based on the one or more first scaling exponent alphas and one or more second scaling exponent alphas, and / or one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale; providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.

Description

[0001] Inter-beat Interval sequence of heart for supporting detection of obstructed sleep apnea

[0002] Technical field

[0003] Various example embodiments relate to an inter-beat interval sequence of heart and more particularly using the inter-beat interval sequence of a heart for supporting detection of obstructed sleep apnea (OSA).

[0004] Background

[0005] Obstructive sleep apnea (OSA) is a common and serious sleep disorder that affects hundreds of millions of people worldwide. OSA is primarily diagnosed using polysomnography (PSG), which monitors multiple physiological signals - brain waves, heart rate, respiratory effort, airflow, and oxygen saturation - overnight in a clinical setting. While highly accurate, PSG is costly and inconvenient, requiring patients to spend the night in a specialized facility. It is therefore unsuitable for continuous monitoring. For at-home diagnosis, there are portable sleep monitors that use simpler metrics like blood oxygen level, SpO2, and respiratory rate to detect apneas. Relying on the SpO2 may not accurately reflect the seventy of OSA, especially in borderline cases. While portable devices offer more convenience and scalability, they generally provide less precise and comprehensive data compared to PSG, particularly for milder cases or differentiating between OSA subtypes.

[0006] Apple Watch (https: / / www.apple.com / health / pdf / sleep-apnea / Sleep_Apnea_Notifications_on_Apple_Watch_September_2024.pdf) includes a feature designed to help identify signs of sleep apnea. It uses the accelerometer to monitor small wrist movements during sleep that are associated with interruptions in normal respiratory patterns. These disruptions are tracked through a new Apple Watch metric called Breathing Disturbances.

[0007] Penzel T, Kantelhardt JW, Grote L, PeterJH, Bunde A. Comparison of detrended fluctuation analysis and spectral analysis for heart rate variability in sleep and sleep apnea. IEEE Trans Biomed Eng. 20030ct;50(10):1143-51. doi: 10.1109 / TBME.2003.817636. PMID: 14560767. DOI: 10.1109 / TBME.2003.817636 discloses employing conventional DFA (detrended fluctuation analysis) that yields at most two discrete scaling exponents: Oi calculated over short scales (here 10-40 beats) and a2calculated over longer scales (here 70-300 beats). There is no discussion of scaledependent detrended fluctuation analysis (sDFA) for accurate and reliable obstructed sleep apnea detection.

[0008] US 2019209020 A1 describes conventional DFA, but only in the form of a single scaling exponent per epoch or a few discrete G[n] values. It does not disclose or suggest a scale-dependent DFA producing a(s) as a continuous function of scale. Multiscale Entropy (MSE) is conceptually and mathematically distinct from scale-dependent DFA: MSE is based on coarse-graining and sample entropy across scale factors to assess signal complexity, whereas scale-dependent DFA quantifies fluctuation-scaling behavior continuously as a function of scale. These two analyses measure entirely different properties of the signal and are not interchangeable.

[0009]

[0010] The problem mentioned above is alleviated by providing a method and technical equipment, where the method is implemented. Various aspects comprise a method, an apparatus, and a computer program product comprising a computer program stored therein, which are characterized by what is stated in the independent claims. Various example embodiments are disclosed in the dependent claims.

[0011] In a first aspect, the invention provides a method for an apparatus for supporting detection of obstructed sleep apnea (OSA), comprising:

[0012] - obtaining, by the apparatus from a transmitting device over a data transfer connection or from a memory, an inter-beat interval (IBI) sequence of the heart of the subject;

[0013] - performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject;

[0014] - obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject;- determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined

[0015] - between the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or

[0016] - between one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale;

[0017] - providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.

[0018] In a second aspect, the invention provides an apparatus comprising means for carrying out the method.

[0019] In a third aspect, the invention provides a computer program comprising computer program code configured to, when executed on at least one processor, cause an apparatus to perform the method.

[0020] The features recited in the dependent claims and the embodiments in the description are mutually freely combinable unless otherwise explicitly stated. The exemplary embodiments presented in this text and their advantages relate by applicable parts to all aspects of the invention, even though this is not always separately mentioned.

[0021] An advantage of the present invention is that detection of OSA is facilitated by using simple instrumentation and utilizing a simple heart rate measurement. The use of advanced and expensive technology may be avoided by using the present invention. The present invention provides a novel method for processing heart rate data in the form of inter-beat interval (IBI) sequences. The IBI sequence data may be processed in a precise and comprehensive manner to provide a preliminary clinical assessment or a prediagnosis without the use of complex and expensive hospital-grade technology.

[0022] The present invention provides a way to assess the clinical condition of a subject with the use of a simple instrument utilizing the method provided herein.

[0023]

[0024] of the Drawings

[0025] In the following, various example embodiments will be described in more detail with reference to the appended drawings, in which

[0026] Fig. 1 shows, by way of example, an electrocardiogram (ECG) signal for forming interbeat interval ( I B I) sequence of a heart;

[0027] Fig. 2 shows, by way of example, a block diagram of an apparatus for estimating condition of subject;

[0028] Fig. 3 illustrates, by way of example, a method for determining a likelihood for OSA; Fig. 4 illustrates results of scale-dependent detrended fluctuation analysis for detecting OSA;

[0029] Fig. 5 illustrates, by way of example, a method for determining reliability of sDFA analysis of IBI for supporting detection of obstructed sleep apnea; and

[0030] Fig. 6 illustrates, by way of example, a method for interaction with user for supporting detection of obstructed sleep apnea.

[0031]

[0032] Embodiments

[0033] The following embodiments are exemplary. Although the specification may refer to “an”, “one”, or “some” embodiment(s) in several locations, this does not necessarily mean that each such reference is to the same embodiment(s), or that the feature only applies to a single embodiment. Single features of different embodiments may also be combined to provide other embodiments.

[0034] Use of ordinal terms such as “first,” “second,” “third,” etc., in the claims and description to modify a described feature does not by itself connote any priority, precedence, or order of one described feature over another or the temporal order in which acts of a method are performed, but are used merely as labels to distinguish one described feature having a certain name from another described feature having a same name (but for use of the ordinal term) to distinguish the described feature.As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements. There is provided method for an apparatus for supporting detection of obstructed sleep apnea (OSA). The method provides deriving information from the autonomic nervous system of the subject with the help of scale-dependent detrended fluctuation analysis for supporting detection of OSA. The method comprises obtaining, by the apparatus, an inter-beat interval (IBI) sequence of the heart of the subject, performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject, obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject, determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined based on

[0035] - the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or

[0036] - one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale;

[0037] said method further comprising providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.

[0038] The method is based on sDFA. The disclosed sDFA processing improves physiological signal analysis in monitoring environments that rely on physiological signal processing by providing a scale-resolved exponent profile a(s) and deviation features across scales, thereby reducing sensitivity to preselected scale ranges used in conventional DFA. As a difference to the conventional DFA, in sDFA the scaling exponent, denoted by alpha (a), is defined as a continuous function of the scale, a(s), rather than as one or two isolated values. The scaling exponent alpha characterizes a power-law scaling of a detrended fluctuation function as a continuous function of scale. By defining the scaling exponent alpha as a continuous function of scale, the method captures scale-specific variations in detrended fluctuation behaviour that are averaged out in conventional DFA,enabling robust detection of physiologically relevant changes in heart-rate dynamics and improving robustness of the likelihood for OSA derived from the IBI sequence. The detrended fluctuation function is determined by calculating, for each scale, a mean square measure of deviations of an integrated inter-beat interval time series from a local trend within windows of that scale. As shown in the Fig. 4, a(s) provides a full scaledependent profile that reveals variations and diagnostic features which are entirely invisible to conventional DFA. This continuous, scale-resolved characterization provides for accurate and reliable obstructed sleep apnea detection.

[0039] The method provides a non-invasive apparatus and method for assisting detection of OSA using advanced heart rate variability (HRV) analysis derived from signals measured from the heart, such as an electrocardiogram (ECG) or photoplethysmogram (PPG) data, whereby detection of OSA may be supported based on simple instrumentation and utilizing a simple heart rate measurement. Examples of the simple instrumentation comprise monitoring devices capable of measuring electrical activity of the heart, devices capable of measuring activity of the heart based on photoplethysmography and devices capable of measuring activity of the heart based on electrocardiography. The monitoring devices may be wearable heart rate sensors, smart rings, sport watches, ECG monitoring devices, PPG monitoring devices, smart mattresses or other devices capable of measuring electrical activity of the heart. Result of the measurement of the electrical activity of the heart may be a signal for indicating an IBI sequence of the heart. Examples of the signal comprise an ECG signal, PPG signal and a beat rate signal. The beat rate signal may be a sample sequence comprising instantaneous values of heart rate, or beat rate, of the heart.

[0040] The apparatus is configured to, and the method causes the apparatus to, process an inter-beat interval (IBI) sequence and to provide output information indicating a deviation and / or a likelihood value as a screening or risk indicator for obstructive sleep apnea. The provided information does not constitute a clinical diagnosis and is not intended to replace polysomnography or a physician assessment. Instead, the provided information supports detection in the sense of prompting further confirmatory testing when the likelihood value or deviation exceeds a threshold.In the following, the deviation determined based on the scaling exponent alphas and the likelihood for OSA are related in that the likelihood for OSA may be derived from the deviation, wherein the likelihood for OSA is a screening indicator and not a clinical diagnosis.

[0041] It should be noted that in the following the likelihood for OSA and the deviation determined based on the scaling exponent alphas, or their derivatives, is used interchangeably.

[0042] In accordance with at least some embodiments, a scale-dependent detrended fluctuation analysis (sDFA) is applied to the obtained IBI sequence. The scaledependent detrended fluctuation analysis provides analyzing HRV patterns of the IBI sequence and detecting HRV patterns that are indicative of OSA. In this way HRV patterns caused by characteristic fluctuations in autonomic nervous system regulation that are disrupted during apneic events may be detected for determining a likelihood of OSA. The sDFA is described in M. Molkkari and E. Rasanen, Robust Estimation of the Scaling Exponent in Detrended Fluctuation Analysis of Beat Rate Variability, Computing in Cardiology 45 (2018); DOI: 10.22489 / CinC.2018.219. In conventional DFA scaling exponent (alpha, a) quantifies how the root-mean-square fluctuations of a detrended signal grow as a function of the observation scale, characterizing the signal’s correlation structure. Scaling exponent value ‘0.5’ may regarded to indicate uncorrelated noise, scaling exponent value greater than ‘0.5’ may be regraded to indicate long-range correlations and scaling exponent value less than ‘0.5’ may be regraded to indicate anticorrelated fluctuations. The conventional DFA yields either a single a for the entire signal or at most two scaling exponents: Oi for small scales (typically 4-16 intervals) and a2for larger scales (typically 16-64 intervals). In contrast, the sDFA yields a scaledependent exponent that defines the exponent, a, as an explicit function of scale, thus a(s), providing a continuous profile rather than one or two discrete values.

[0043] IBI sequence is a characteristic of a heart of a subject and comprises sample values that indicate time intervals between successive heart beats of the heart. Accordingly, the IBI sequence is physiological signal data. The IBI sequence may be determined by simple instrumentation and utilizing a simple heart rate measurement. However, it should be noted that, the IBI sequence may be determined also by more sophisticatedinstrumentation such as an ECG device that is capable of measuring an ECG signal from a subject. The successive heart beats, or beats, may be determined based on an RR interval derived from the ECG signal.

[0044] Fig. 1 shows, by way of an example, an ECG signal for forming inter-beat interval (IBI) sequence of a heart. The ECG signal 100 may be measured from a subject and the measured ECG signal may be sampled for forming the IBI sequence. The ECG signal comprises heart beats, / , at RR intervals 101, 102, 104, 106, 108, 110, 112. The RR interval is a beat-to-beat interval which is calculated as the time between successive R-peaks. The RR intervals, therefore, form the IBI sequence. The RR intervals depend on various factors such as age, gender, and / or physiological status of a person. Physiological status here may refer to cardiac health, rest, sleep, exercise, anxiety, etc. Therefore, the IBI sequence can be used for obtaining information for estimating at least one of the following: cardiac health; or exercise load; or drug exposure; or sleep phase; or stress level; or and state of nervous system. The cardiac health may comprise at least one of the following: a healthy heart of the subject; or a cardiac disease of the subject; or a cardiac malfunction of the subject.

[0045] It should be noted that alternatively or additionally the IBI sequence may be formed based on photoplethysmogram (PPG) signal. The PPG signal may be obtained by a PPG monitoring device such as a PPG wrist monitor or other device that use optical sensors to measure blood volume changes in the microvascular bed of tissue. The PPG signal may be formed by a device comprising a light source and a photodetector, whereby the IBI sequence may be determined based on variations in light absorption from measurement data of the photodetector.

[0046] Fig. 2 shows, by way of an example, a block diagram of an apparatus 200 for supporting detection of obstructed sleep apnea (OSA). The apparatus may a server or a computer or a smart phone or an ECG monitoring device or a PPG monitoring device or other device capable of measuring, or obtaining, a signal representing electrical activity of a heart of a subject and determining an IBI sequence from the signal. Examples of ECG monitoring devices comprise a Holter machine or a large-scale ECG monitor. It should be noted that the apparatus may be a body-connected device for example a wearable monitoring device or a smart mattress. Examples of the wearable monitoring devices comprise atleast a wrist worn device such as a sport watch, smart ring, or a wearable heart rate monitor. Examples of the signal comprise at least an ECG signal, a PPG signal and a beat rate signal. The apparatus may receive user input such as commands, parameters etc. via a user interface 202 and / or via a communication interface 208. Examples of the commands comprise at least one of the following: a command to reset an alarm; or a command to determine information indicating a likelihood of OSA; start or stop measurements for determining a likelihood for OSA; or start or stop transfer of IBI sequence from the apparatus to a remote apparatus for determining information indicating a likelihood of OSA by the remote apparatus. The user interface may receive user input e.g. through buttons and / or a touch screen. Alternatively, the user interface may receive user input from the Internet or a personal computer or a smartphone via a communication connection. The communication connection may be e.g. the Internet, a mobile communication network, Wireless Local Area Network (WLAN), Bluetooth®, or other contemporary and future networks. The apparatus may comprise a memory 206 for storing data and computer program code which may be executed by a processor 204 to carry out various embodiments of the method as disclosed herein. A signal analyzer 210 may be configured to implement the elements of the method disclosed herein. The signal analyzer may receive a signal to be processed, e.g. an ECG signal, PPG signal or a beat rate signal, from the memory or from a device, e.g. the heart rate monitoring unit or a wearable monitoring device, capable of measuring a signal representing electrical activity of the heart. The signal analyzer may for example perform one or more functionalities of a method described herein such as one or more of the following: determining sleep offset; determining sleep onset; and performing sDFA. The elements of the method may be implemented as a software component residing in the apparatus. The apparatus may receive the signal to be processed e.g. from a monitoring device and store the signal in the memory. The monitoring device may be any ECG hardware or a wearable monitoring device as described above. A computer program product may be embodied on a non-transitory computer readable medium. The apparatus may comprise means such as circuitry and electronics for handling, receiving and transmitting data, such as information indicating a likelihood of OSA, an ECG signal, PPG signal, a beat rate signal, an IBI sequence and / or a condition of a subject.It should be appreciated that at least in some embodiments, the apparatus 200 may provide an output via at least one output interface. The output may comprise information indicating the determined at least one deviation. Examples of the at least one output interface comprise the user interface 202, an application programming interface and the communication interface 208. The output may comprise output data that is displayed by the user interface, e.g. a display device, or output data that is communicated by the communication interface 208, or output data that is retrievable through the application programming interface. An example of the application programming interface is a Web API, where the output data is accessible by Python code. In an example the output may comprise displaying of information, by the user interface 202, to a user of the apparatus. Examples of the user interface comprise one or more or a combination of a speaker, a display device, a touch screen, light source and a printer. The information output by the user interface may comprise at least one of the following: information indicating a deviation, information indicating a likelihood of OSA, or ECG signal, or PPG signal, or a beat rate signal, or a measured IBI sequence, or alarm. The information output by the user interface may be dependent on reliability of the information, such as deviation and / or likelihood of OSA. The alarm may be a visual alarm or an audio alarm or a haptic alarm or a combination thereof. The alarm may be triggered based on a deviation determined by the apparatus and / or a likelihood of OSA determined by the apparatus. Examples of audio alarms comprise sounds, preferably with an audible volume level, e.g. at least 50 dB. Examples of visual alarms comprise graphical user interface elements for example symbols and light sources whose color may be set, e.g. red, to indicate an alarm. In an example, the haptic alarm may be caused by the apparatus 200 comprising an electric motor whose rotor is caused to generate vibration energy, e.g. by coupling the rotor with an eccentric element, to a housing of the apparatus. When the apparatus is worn by a user the vibration can be sensed by the user, whereby an alarm or other feedback may be communicated to the user. In an example, the alarm may be caused based on the information indicating a likelihood of OSA. In an example the output may comprise the communication interface 208 communicating output data, e.g. information indicating a deviation, information indicating a likelihood of OSA, an ECG signal, PPG signal ora beat rate signal and / or a measured IBI sequence, to a remote apparatus.The remote apparatus, e.g. a server, may host a computer program for processing the output data from the apparatus 200. In an example, the remote apparatus may process the measured IBI sequence received from the apparatus 200, use any commands received from the apparatus 200 for controlling the processing and send results of the processing back to the apparatus 200. The results may comprise e.g. information indicating a likelihood of OSA. Using a separate remote apparatus for processing the output data enables off-loading processing from the apparatus 200 to the remote apparatus. In this way a likelihood for OSA of the subject may be determined even if capabilities and / or processing resources of the apparatus 200 are limited. The remote apparatus may have sufficient resources for processing output data received from a plurality of apparatuses. An example of the remote apparatus is a cloud computing service.

[0047] It should be appreciated that the apparatus 200, for example a wearable monitoring device, a PPG monitoring device, an electrocardiogram monitoring device or a wearable monitoring device, may be further caused to display, by the user interface, one or more results determined based on an electrocardiography recording performed by the device or based on a beat rate measurement performed by the device or based on a sleep period, together with information indicating a deviation and / or the likelihood of OSA. In this way, the user of the apparatus may be assisted to correctly evaluate results of the electrocardiography recording or the beat rate measurement or the sleep period, and any alarm caused by the apparatus e.g. based on the deviation and / or the likelihood for OSA for continued interaction with the apparatus. The results of the electrocardiography recording or the beat rate measurement may be displayed by the user interface e.g. together with the deviation and / or likelihood for OSA. Examples of the results of the sleep period comprise sleep data. Examples of the results of the electrocardiography recording comprise or at least indicate: an electrocardiogram, sinus rhythm, sinus tachycardia, sinus bradycardia, atrial fibrillation, atrial flutter, ventricular, tachycardia, ventricular fibrillation and / or heart rate. Examples of the results of the beat rate measurement comprise or at least indicate: a beat rate, a HRV and an exercise level. In an example, when the deviation and / or likelihood for OSA is displayed with the results of the electrocardiography recording, the user may be assisted to correctly interpret the results of the electrocardiography recording. In an example, when the deviation and / or likelihoodfor OSA is displayed with the results of the beat rate measurement, the user may be assisted to correctly interpret the results of the beat rate measurement. In another example, displaying the deviation and / or likelihood for OSA may provide that the user may be assisted to interpret an alarm caused by the device and to determine to input a command to reset or not to reset the alarm such that continued use of the apparatus may be facilitated.

[0048] Fig. 3 illustrates, by way of example, a method for supporting detection of OSA. The method is based on deriving information from the autonomic nervous system of the subject with the help of scale-dependent detrended fluctuation analysis (sDFA). The sDFA performs better than conventional heart rate variability (HRV) analysis for detecting obstructive sleep apnea (OSA) because it captures the subtle, multi-scale fluctuations in autonomic nervous system regulation that are often missed by conventional HRV metrics. This leads to enhanced sensitivity in detecting the presence of OSA, even when the apnea-hypopnea vary from night to night. The method may be performed by an apparatus described with Fig. 2. Phase 302 of the method comprises obtaining, by the apparatus, an inter-beat interval (IB I) sequence of the heart of the subject. Phase 304 of the method comprises performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject. Phase 306 of the method comprises obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject. Phase 308 of the method comprises determining, by the apparatus, at least one deviation. The at least one deviation in phase 308 is determined based on the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale. Phase 310 of the method comprises providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus. The information indicating the determined at least one deviation serves for assisting / supporting detection of the OSA from signals measured from the heart which carry information about electrical activity of the heart. sDFA uses characteristic patterns of scaling exponent alphas within specific time scales, wherebythe sDFA based analysis facilitates detection of the OSA without detecting individual apneic events.

[0049] In an example, phase 302 comprises that the IBI sequence is obtained by the apparatus from a transmitting device over a data transfer connection or from a memory. The apparatus may be e.g. a signal analyzer. The transmitting device may be a wearable monitoring device, heart monitoring device, PPG monitoring device, electrocardiogram monitoring device, or a computer connected to such a device. The data transfer connection may be an Internet Protocol (IP) connection, or a Bluetooth connection.

[0050] In an example in accordance with at least some embodiments, phase 302 comprises performing the sDFA to the IBI sequence obtained between a sleep onset and a sleep offset of the subject. In this way the IBI sequence may be measured during the sleep of the subject and the IBI sequence carries the information of characteristic fluctuations in autonomic nervous system regulation that are disrupted during apneic events may be detected for supporting detection of OSA. In an example, the sleep onset, i.e. the time the subject falls asleep, and sleep offset, i.e. the time the subject wakes up, may be determined using a combination of sensors for measuring the subject and algorithms for processing signals obtained by the measurements. In an example, the sleep onset and offset may be determined based on at least some of the following components provided at the apparatus or operatively connected to the apparatus:

[0051] 1. Accelerometer: This sensor detects movement. By analyzing periods of low movement, the apparatus can infer that the subject is likely asleep. Conversely, increased movement can indicate wakefulness.

[0052] 2. Heart mate monitor: During sleep, heart rate typically decreases and becomes more regular. Sudden changes in heart rate can signal transitions between sleep and wakefulness.

[0053] 3. Gyroscope: This sensor helps to detect the orientation and rotation of the apparatus. Therefore, when worn by the subject, for example as included to the apparatus, the gyroscope can provide additional data to distinguish between different types of movements, such as rolling over in bed versus getting up.4. Algorithms: The data from the sensors are processed using sophisticated algorithms that can identify patterns associated with sleep and wakefulness. These algorithms are often based on machine learning models trained on large datasets of sleep behavior.

[0054] 5. User input: The user input may be received by the user interface, whereby the apparatus may receive a annual indication from the subject about when the subject is going to sleep and when the subject has woken up. This input can based used to calibrate the algorithms and improve accuracy.

[0055] In an example, phase 308 comprise that the one or more second scaling exponent alphas are reference data. The reference data may comprise scaling exponent alphas from one or more sDFAs. In an example, the reference data may be obtained by measurements of IBI sequences and sDFA analysis performed in accordance with phases 302 to 306 for a plurality of subjects, who are healthy subjects, thus diagnosed not having OSA. In an example, the reference data may be obtained by measurements of IBI sequences from the subject and sDFA analysis performed in accordance with phases 302 to 306 for the subject over a plurality of earlier sleep periods, for example three or more, sleep periods, or nights. Thus, reference data may be obtained from sleep periods of the subject measured over days, weeks or months.

[0056] In an example in accordance with at least some embodiments, phase 310 comprises that the information indicating the at least one deviation comprises a likelihood for OSA. The likelihood for OSA serves supporting detection of OSA. In an example, the likelihood for OSA may be indicated by the determined at least one deviation, or textual information indicating a high likelihood for OSA, or textual information indicating a low likelihood for OSA, or a graphical indicator, or numerical information indicating a high likelihood for OSA, or numerical information indicating a low likelihood for OSA, or a color. In an example, the likelihood for OSA may be determined directly based on a value of the at least one deviation. In an example, the likelihood for OSA may be determined directly based on the at least one deviation exceeding a threshold value. The textual information and / or graphical indicator may be derived based on a comparison of the at least one deviation and the threshold value. In an example, the numerical information indicating a likelihood for OSA may be a value from a range of 1 to 5, where 1 denotes a low likelihoodfor OSA and with higher values indicating correspondingly a higher likelihood for OSA. In an example, the textual information may be “low” or “intermediate” or “high”. In an example, a graphical symbol may be an exclamation mark for denoting an increased likelihood for OSA. In an example, a green color may be used to indicate a low likelihood for OSA and a red color may be used to indicate an increased likelihood for OSA.

[0057] In an example in accordance with at least some embodiments, phase 310 comprises that the likelihood for OSA is provided to the at least one output interface of the apparatus after the sleep offset of the subject. In this way the likelihood of OSA may be determined based on the IBI sequence from the latest sleep period of the subject for supporting detection of OSA. Examples of the at least one output interface comprise at least the following: an application program interface, or a communication interface 208 or a user interface 202.

[0058] In an example in accordance with at least some embodiments, phase 310 comprises that the at least one output interface comprises at least one of the following: a communication interface for data transfer; or an application programming interface; or a user interface. In this way output data, such as information indicating the determined at least one deviation, may be transmitted over a data transfer connection provided by the communication interface, for example an Internet Protocol (IP) connection, or a Bluetooth connection. Alternatively or additionally, the output data may be transmitted on a data bus inside the apparatus. Alternatively or additionally, the output data may be provided inside the apparatus or to a remote apparatus via the application programming interface.

[0059] In an example in accordance with at least some embodiments, phase 310 comprises that the user interface comprises a display device that is controlled to display the likelihood for OSA as part of a sleep data view. In this way the likelihood of OSA measured during the sleep period and the sleep data are provided in combination for supporting sleep analysis and OSA detection. The sleep data view may be visual presentation of data measured during the sleep of the subject. In an example, a sleep data view comprises metrics regarding sleep patterns and quality, such as:

[0060] 1. Total sleep duration: The total amount of time spent asleep during the night.

[0061] 2. Sleep stages: Breakdown of time spent in different sleep stages, such as:o Light sleep

[0062] o Deep sleep

[0063] o Rapid Eye Movement (REM) sleep

[0064] o Awake time

[0065] 3. Sleep score: An overall score that rates the quality of sleep based on various factors.

[0066] 4. Sleep timeline: A visual representation of sleep stages throughout the night, often displayed as a graph or chart.

[0067] 5. Sleep onset and offset: The times when the user fell asleep and woke up.

[0068] 6. Movement: Data on how much the user moved during sleep, which can indicate restlessness.

[0069] 7. Heart rate: Average heart rate during sleep, and sometimes heart rate variability (HRV).

[0070] 8. Respiration rate: The number of breaths per minute during sleep.

[0071] 9. Pulse oximetry (SpO2): Blood oxygen levels during sleep, if the device supports it.

[0072] 10. Stress levels: Some wearable devices track stress levels during sleep.

[0073] In an example, phase 310 comprises that the likelihood of OSA may be communicated to another apparatus, for example a remote apparatus, via the communication interface. In this way the detection of OSA may be supported away from the apparatus that performs measurement of IB I sequence. It should be noted that the remote apparatus may receive likelihoods of OSA from a plurality apparatuses that perform sDFA analyses to IBI sequences of a plurality of subject in accordance with phases 304 to 308.

[0074] In an example, phase 310 comprises that the likelihood of OSA may be communicated via the application programming interface to an application that is hosted at the same apparatus, where the sDFA analysis is performed or to an application that is hosted at aremote apparatus connected to the apparatus performing the sDFA analysis over a data network connection.

[0075] In an example, phase 304 comprises performing scale-dependent detrended fluctuation analysis (sDFA) which provides removing trends from the data before analyzing the fluctuations. By detrending the data, accuracy of identifying the intrinsic fluctuations at different scales may be supported, which is particularly useful for detecting subtle patterns in physiological signals such as heart rate variability (HRV). In an example, phase 308 comprises determining the at least deviation based on a difference between one or more values of the first scaling exponent alphas and one or more values of the second scaling exponent alphas, and / or based on a difference between one or more values of derivatives of the first scaling exponent alphas with respect to scale and one or more values of derivatives of the second scaling exponent alpha with respect to scale. For example, the difference may be determined based on a maximum value of the first scaling exponent alphas, and / or their derivatives, and a minimum value of the second scaling exponent alphas, and / or their derivatives. On the other hand the at least one deviation may be determined based on a maximum value of the second scaling exponent alphas, and / or their derivatives and a minimum value of the first scaling exponent alphas, and / or their derivatives. It should be noted that the maximum value and minimum value may be determined for at a range of scales. Accordingly, the one or more values of the first scaling exponent alphas, or their derivatives, and one or more values of the second scaling exponent alphas, or their derivatives, may be evaluated at a range of scales for determining the at least deviation at that range of scales. In an example, the range may be or may be selected from scales 4 to 100 or more such as from scales 4 to 1000. The IBI sequence may be measured from the heart during sleep, whereby detection of the OSA may be supported by determining the at least one deviation at larger scales such as at scale 100 or higher.

[0076] In an example, the phase 308 comprises that the at least one deviation is an aggregated deviation determined based on both the first scaling exponent alphas and one or more second scaling exponent alphas and their derivatives. In an example, the aggregated deviation may be formed based on based ona difference between one or more values of the first scaling exponent alphas and one or more values of the second scaling exponent alphas, and

[0077] - a difference between one or more values of derivatives of the first scaling exponent alphas with respect to scale and one or more values of derivatives of the second scaling exponent alpha with respect to scale.

[0078] The aggregated deviation may be derived by an arithmetic operation from the determined differences. The determined differences may be weighted.

[0079] In an example, phase 302 comprises that the IBI sequence may be obtained by a body-connected device such as a wearable monitoring device, a smart mattress, a heart monitoring device, a PPG monitoring device or an electrocardiogram monitoring device, a signal representing electrical activity of the heart of a subject and determining an IBI sequence from the signal. Examples of the signal comprise at least an ECG signal, PPG signal and a beat rate signal.

[0080] In an embodiment, phase 302 comprises that the IBI sequence, or information for determining the IBI sequence such as an ECG signal, a PPG signal or a beat rate signal, may be received from a transmitting device over a data transfer connection. The data transfer connection may be a data network connection, for example an Internet Protocol (IP) connection. The transmitting device may be a wearable monitoring device, a heart monitoring device, a PPG monitoring device or an electrocardiogram monitoring device, or a computer connected to a wearable monitoring device, a heart monitoring device, a PPG monitoring device or an electrocardiogram monitoring device for receiving the IBI sequence.

[0081] Fig. 4 illustrates results of scale-dependent detrended fluctuation analysis for detecting OSA. The results show distributions 402 of scaling exponents from a nighttime recording of RR intervals of healthy controls (N=22) and distributions 404 of scaling exponents from a nighttime recording of RR intervals of apnea patients (N=48). The difference between the groups is maximized at scale 21 marked by a vertical line 406. This difference can be used to determine a likelihood for OSA index which serves as an indicator for a deviation between the scaling exponent alphas of the healthy controls and the apnea patients. Detecting OSA based on the scale-dependent detrended fluctuation analysis providedROC-AUC score of 0.97 408. Detecting OSA based on other metrics that are based on HRV provided ROC-AUC scores as follows for each metric: LF / HF, score 0,89 410; Poincare SD2 / SD1 , score 0.86412; RMSSD, score 0.80414; Mean RR, score 0.77416. The LF / HF refers to ratio between low- and high-frequency components (LF / HF) of a IBI sequence for detecting OSA. The RMSSD refers to a root means square of standard deviation of a IBI sequence for detecting OSA. The means RR refers to a mean RR-interval for detecting OSA. Poincare SD2 / SD1 refers to a ratio between Standard Deviation 1 and Standard Deviation 2 from Poincare plots for detecting OSA. Therefore, the performance of sDFA for detecting OSA is higher than the performance of the other methods.

[0082] An example implementation of the sDFA for steps 304 and 306 of the method of Fig. 3 is described in the following.

[0083] sDFA

[0084] DFA provides that collective behaviour of the obtained IBI sequence may be characterized by a single value, a scaling exponent a. In particular, DFA considers collective correlations within windows of specific number of steps. This is in contrast to the correlations determined by, e.g., the autocorrelation function that considers pointwise correlations that are specific number of steps (“lag”) apart from each other.

[0085] The DFA processes the obtained IBI sequence that is a time series X of N samples, i.e. , X = (_x1,x2, ...,xN). The IBI sequence is uniformly sampled in the sense that the intervals correspond to subsequent beats one after another, i.e., the unit of “time” in this time series is a single beat. First, a cumulative summation is performed:

[0086]

[0087] where Xj is an individual interbeat interval (IBI), (X) is an arithmetic mean of the original time series, and N is a number of IBI samples in a processed segment of the IBI sequence. In this way an integrated time series Y = (y1,y2, ->yN ) isobtained. When each IBI sample is interpreted as a step length of a random walk theory, the time series Y represents a random walk. This facilitates interpretation of scaling exponent a for determining a likelihood for OSA. Formula (1) is an example, of the IBI sequence obtained in phase 302 of Fig. 3. Detrended variances of the fluctuations of the IBI sequence from a local trend may be calculated. A trend may be determined by a least-squares fit of a low-order polynomial to data. The detrended variances of fluctuations are computed as the variance from the trends within each window:

[0088]

[0089] where [■] gives the fluctuation for a local trend within a window / for index j, s is the window length, or scale, and / is index of the window. Scale s is the length of the window, in number of consecutive elements of the time series, through which the behaviour of the time series is studied. In the random walk formalism scale s is equivalent to the number of steps taken. fs,i(j) is the trend within the window at scale s and index / . The indices / may take values i e {1, 2, ...,N - s + 1}. In this notation, index / corresponds to the index of the first element y, of the time series Y that belongs to a particular window of length s. Furthermore, conventionally the windowing is non-overlapping, i.e., only indices / = 1 , s + 1 , 2s + 1 , 3s + 1 , . . . would be included. However, the statistical properties of the analysis may be improved by maximally overlapping windows, i.e., considering all the possible windows (in the IBI sequence), where / = {1 , 2, ..., N-s+1}, at increased computational cost. Formula (2) is an example, of processing the obtained IBI sequence according to phase 304 of Fig. 3.

[0090] The detrended variances can be used to calculate a fluctuation function F(s)

[0091]

[0092] where the angle brackets denote the arithmetic mean (computed over all the indices i separately for each scale s).Allowing the windows to overlap enhances the statistical properties of this estimate, i.e. , F(s). The procedure may be repeated for different window sizes, or scales s. The fluctuation function F(s) may follow the power-law, whereby F(s) ~ sa, where a is the scaling exponent.

[0093] It is a known result from the random walk theory that for an uncorrelated walker 1

[0094] we get F(s) o s?. A more general case with correlated (or anticorrelated) steps may be characterized by a scaling exponent a

[0095]

[0096]

[0097] F(s) o sa(4)

[0098] Correlated steps, i.e., the steps are more likely to be to the same direction with approximately the same magnitude, result in a > with higher values indicating

[0099]

[0100] higher degree of correlations. Consequently, anticorrelated steps, i.e., the steps are more likely to be to opposite directions with approximately the same magnitudes, result in a < with lower values for greater anticorrelations.

[0101]

[0102] In conventional DFA, the power law scaling of Eq. 5 is transformed into linear relationship by a logarithmic transformation. The scaling exponent a is determined as the slope of a simple regression line fit on a log-log plot of the fluctuation function versus scale. In the context of HRV, two scaling exponents are conventionally determined: Short-scale a±for scales 4-16 and long-scale a2for scales 16-64.

[0103] Many processes, including HRV, do not exhibit strict scaling over all the scales. Therefore, instead of relying on line-fitting over ranges of scales, it is useful to study a whole spectrum of exponents a(s) as the function of the scale s. The scale-dependent exponent is conveniently defined as the local slope of the logarithmic fluctuation function on logarithmic scale

[0104]

[0105] where the derivatives are first calculated with respect to the logarithmic scale and then evaluated at scale s.The invention further provides an apparatus. The apparatus comprises:

[0106] - means for obtaining, by the apparatus, an inter-beat interval ( I B I) sequence of the heart of the subject;

[0107] - means for performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject;

[0108] - means for obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject;

[0109] - means for determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined based on

[0110] - the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or

[0111] - one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale;

[0112] - means for providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.

[0113] Fig. 5 illustrates a method for determining reliability of sDFA analysis of IBI for supporting detection of obstructed sleep apnea using sDFA. The method supports reliable detection of OSA. The method may be performed by the apparatus in accordance to described with Fig. 2 in connection with one or more phases of Fig. 3, for example before phase 310 and after phase 308. Phase 502 comprises determining a plurality of deviations and / or likelihoods for OSA based on sDFA analyses of IBI sequences from a subject. Phase 504 comprises determining whether the determined plurality of deviations and / or likelihoods for OSA are reliable. If the determined plurality of deviations and / or likelihoods for OSA are not reliable, the method proceeds to phase 502, where further plurality of deviations and / or likelihoods for OSA are determined, or at least one further deviation and / or likelihood for OSA is determined. Phase 506 comprises enabling, by the apparatus, support for detection of OSA if the determined plurality of deviations and / or likelihoods for OSA are reliable. In this way the measurements for OSA can be carried out consistentlyand reproduced, whereby further deviations and / or likelihoods for OSA may be reliably measured.

[0114] In an example in accordance with at least some embodiments, phase 502 comprises determining a predetermined number of deviations and / or likelihoods for OSA. Each of the deviations and / or likelihoods for OSA may be determined in accordance to described with the sDFA analysis of IBI sequence in phases 302 to 308 of Fig. 3. The predetermined number of deviations and / or likelihoods for OSA may be two or three, or higher number for example five. In this way the analysis provided by phases 302 to 308 of Fig. 3 may be carried out for the predetermined number of sleep periods before any deviations and / or likelihoods for OSA are provided to output in accordance with phase 310. Thus, it should be note that each of the plurality of deviations and / or likelihoods may be determined based on an IBI sequence obtained during a sleep period. Accordingly, before, the predetermined number of number of deviations and / or likelihoods for OSA have been determined, or the predetermined number of sleep periods have been analyzed, by the phases 302 to 308, the detection of OSA cannot be positively ascertained, and the method may not proceed to phase 506. Thus, the predetermined number of deviations and / or likelihoods for OSA may correspond to a number of sleep periods to be analysed by phases 302 to 308. The number of sleep periods to be measured may be analysed may be updated after each sleep period and the number of sleep periods to be further analysed by the phases of 302 to 308 may be provided to an output interface of the apparatus, for example displayed.

[0115] In an example phase 504 may be performed prior to phase 310 of Fig. 3.

[0116] In an example phase 504 comprises determining a difference between the plurality of deviations and / or likelihoods for OSA and determining whether the difference is statistically significant. If the difference is statistically significant the deviations and / or likelihoods for OSA may be determined unreliable and the method may proceed to phase 502. On the other hand if the difference is not statistically significant the deviations and / or likelihoods for OSA may be determined reliable and the method may proceed to phase 506. It should be note that the difference may be determined between deviations and / or likelihoods for OSA that have been determined based on IBI sequences obtained from distinct sleep periods, such as from sleep periods at different nights.In an example statistical significance of the difference between the plurality of deviations and / or likelihoods for OSA may be evaluated based on a statistical test such as the t-test or the Mann-Whitney ll-test (also known as the Wilcoxon rank-sum test). Performing the t-test may comprise calculating t-statistics and finding a p-value corresponding to the calculated t-statistics. Performing the ll-test may comprise calculating U-statistics and finding a p-value corresponding to the calculated U-statistics. The statistical significance may be evaluated in both the t-test and U-test based on comparing the p-value with a chosen significance level for the given test.

[0117] In an example, phase 506 comprises determining at least one further deviation and / or likelihood for OSA in accordance with phases 302 to 308 and providing information indicating the determined at least one further deviation and / or likelihood for OSA to at least one output interface of the apparatus in accordance with 506. In this way the information indicating the determined at least one further deviation and / or likelihood for OSA is provided after the reliability of the measurements have been assessed and positively determined.

[0118] In an example, phase 506 comprises enabling sleep data view to display the at least one further deviation and / or likelihood for OSA. If displaying of the at least one further deviation and / or likelihood for OSA has not been enabled, the sleep data view may display information indicating a number of sleep periods to be analysed by the phases 302 to 308 until the predetermined number of sleep periods have been analysed and deviation and / or likelihood for OSA may be displayed by the sleep data view.

[0119] Fig. 6 illustrates a method for interaction with user for supporting detection of obstructed sleep apnea. The method supports reliable detection of OSA. The method may be performed by the apparatus in accordance to described with Fig. 2 in connection with one or more phases of Fig. 3, for example before phase 310 and after phase 308. Phase 602 comprises determining at least one deviation and / or a likelihood for OSA in accordance with phases 302 to 310 of Fig. 3. Phase 604 comprises determining if user input has been received which indicates reliability of the determined at least one deviation and / or a likelihood for OSA. Phase 606 comprises using the determined at least one deviation and / or a likelihood for OSA for reference data if the received user input has indicated that the determined at least one deviation and / or a likelihood for OSA is reliable. In this waynew reference data may be obtained to be used for supporting detection of OSA from the subject. Phase 608 comprises omitting further use of the determined at least one deviation and / or a likelihood for OSA, for example as reference data, if the received user input has indicated that the determined at least one deviation and / or a likelihood for OSA is not reliable. In an example the at least one deviation and / or a likelihood for OSA may be deleted from memory of the apparatus.

[0120] In an example, phase 604 comprises receiving user input indicating reliability of the at least one deviation and / or a likelihood for OSA. The user input may be received by the apparatus, e.g. by a touch via a touch screen, or by a button, or by voice.

[0121] In an embodiment, the means of the apparatus are configured to perform the method according to the invention.

[0122] In an embodiment, the means comprise at least one processor and at least one memory including computer program code. In an embodiment, the at least one memory and the computer program code are configured to, with the at least one processor, cause the performance of the apparatus.

[0123] In an embodiment, the apparatus is a server, a smart phone, a wearable monitoring device, a smart mattress, a heart monitoring device, a PPG monitoring device or an electrocardiogram monitoring device. In an embodiment, the wearable monitoring device may be worn, e.g., around a torso or a limb, such as a wrist, an upper arm, or a leg of the subject.

[0124] A computer program according to the invention comprises computer program code that is configured to, when executed on at least one processor, cause an apparatus to perform the method of the invention.

[0125] Embodiments may be implemented in software, hardware, application logic or a combination of software, hardware and application logic. The software, application logic and / or hardware may reside on memory, or any computer media. In an example embodiment, the application logic, software or an instruction set is maintained on any one of various conventional computer-readable media. In the context of this document, a “memory” or “computer-readable medium” may be any media or means that can contain,store, communicate, propagate or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer.

[0126] The foregoing description has provided by way of exemplary and non-limiting examples a full and informative description of the exemplary embodiment of this invention. However, various modifications and adaptations may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications of the teachings of this invention will still fall within the scope of this invention.

Claims

CLAIMS1. A method for an apparatus for supporting detection of obstructed sleep apnea (OSA), comprising:- obtaining, by the apparatus from a transmitting device over a data transfer connection or from a memory, an inter-beat interval (IBI) sequence of the heart of the subject;- performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject;- obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject;- determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined based on- the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or- one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale;- providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.

2. The method according to claim 1 , comprising:- performing the sDFA to the IBI sequence obtained between a sleep onset and a sleep offset of the subject.

3. The method according to claim 1 or 2, wherein the information indicating the at least one deviation comprises a likelihood for OSA.

4. The method according to claim 3, wherein the likelihood for OSA is provided to the at least one output interface of the apparatus after the sleep offset of the subject.

5. The method according to any of the preceding claims, wherein the at least one output interface comprises at least one of the following: a communication interface for data transfer; or an application programming interface; or a user interface.

6. The method according to claim 5, wherein the user interface comprises a display device that is controlled to display the likelihood for OSA as part of a sleep data view.

7. The method according to any of the preceding claims, comprising:- determining, by the apparatus, a plurality of deviations and / or likelihoods for OSA based on sDFA analyses of IBI sequences from the subject;- determining, by the apparatus, whether the determined plurality of deviations and / or likelihoods for OSA are reliable;- enabling, by the apparatus, support for detection of OSA if the determined plurality of deviations and / or likelihoods for OSA are reliable.

8. The method according to any of the preceding claims, comprising:- determining, by the apparatus, if user input has been received which indicates reliability of the determined at least one deviation; and- using, by the apparatus, the determined at least one deviation for reference data if the received user input has indicated that the determined at least one deviation is reliable; and- omitting, by the apparatus, further use of the determined at least one deviation, if the received user input has indicated that the determined at least one deviation is not reliable.

9. The method according to any of the preceding claims, wherein scaling exponent alpha characterizes a power-law scaling of a detrended fluctuation function as a continuous function of scale.

10. An apparatus for supporting detection of obstructed sleep apnea (OSA), comprising:- means for obtaining, by the apparatus, an inter-beat interval (IBI) sequence of the heart of the subject;- means for performing, by the apparatus, a scale-dependent detrended fluctuation analysis (sDFA) to the obtained IBI sequence from the heart of the subject;- means for obtaining, by the apparatus, one or more first scaling exponent alphas from the sDFA performed to the obtained IBI sequence from the heart of the subject;means for determining, by the apparatus, at least one deviation, wherein the at least one deviation is determined based on- the one or more first scaling exponent alphas and one or more second scaling exponent alphas; and / or- one or more derivatives of the one or more first scaling exponent alphas with respect to scale and one or more derivatives of the one or more second scaling exponent alphas with respect to scale;- means for providing, by the apparatus, information indicating the determined at least one deviation to at least one output interface of the apparatus.11.The apparatus according to claim 10, comprising one or more means configured to perform the method according to any of the claims 2 to 9.

12. The apparatus according to claim 10 or 11, wherein the means comprise at least one processor; at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the performance of the apparatus.

13. The apparatus according to any of claims 10 to 12, wherein the apparatus is a server, a smart phone, a wearable monitoring device, a smart mattress, heart monitoring device, PPG monitoring device or an electrocardiogram monitoring device.

14. A computer program comprising instructions that when executed by at least one apparatus for supporting detection of obstructed sleep apnea (OSA) causes execution of any of the methods of claims 1 to 9.

Images