Detection of Central Apnea

Abstract

Existing apnea monitors are unable to detect clinically significant apnea events because they cannot distinguish cardiac artifacts from the thoracic impedance signal and therefore are unable to detect pauses in breathing. A system and method are disclosed that provides improved apnea detection, particularly in the neonatal setting. The disclosed technique filters out cardiac artifacts from the thoracic impedance signal and allows the probability of an apnea event to be determined. Detection of an apnea event can then be used to trigger an alarm, initiate automatic physical stimulation of the patient, or both.

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This patent application claims priority based on U.S. Provisional Patent Application No. 63 / 265,817, entitled "Detection of Central Apnea", filed on December 21, 2021. The disclosure of the prior application is considered to be a part of this patent application and is incorporated herein by reference.

[0002] [Technical Field] The present invention relates to the technical field of apnea detection, and more particularly to the detection of central apnea.

Background Art

[0003] Apnea is a temporary cessation of breathing. Apnea can occur at any stage of development and is particularly common in premature infants, sometimes referred to as apnea of prematurity (AOP). AOP is completely different from adult sleep apnea. AOP is a developmental disorder, but the reasons behind the propensity for apnea in premature infants are not fully clear. The pathogenesis of AOP is poorly understood, but immature pulmonary reflexes and breathing responses to hypoxia and hypercapnia may contribute to the occurrence or severity of AOP. It may also be exacerbated by co - existing factors or pathologies.

[0004] AOP is an important and common clinical problem and often serves as a rate-limiting process in the discharge from the Neonatal Intensive Care Unit (NICU). It is clinically essential to accurately detect clinically significant episodes of neonatal apnea using existing chest impedance monitoring.

[0005] Apnea is a serious clinical event that requires immediate medical attention. However, the monitoring of apnea, especially existing monitoring for neonatal infants, is insufficient in that it misses many serious events. For this reason, those existing monitors often fail to recognize apnea and thus cannot provide warning signals to NICU staff to alert them to the fact that the infant is not breathing.

[0006] Thus, there is a need in the art for a technique that provides improved detection of apnea.

Brief Description of the Drawings

[0007] A plurality of attached drawings incorporated herein and constituting a part of this specification illustrate implementations of apparatuses and methods consistent with the present invention and serve to explain the advantages and principles consistent with the present invention together with the detailed description of the invention.

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

DETAILED DESCRIPTION OF THE INVENTION

[0009] In the following description, for the purpose of providing a complete understanding of the present invention, numerous specific details are set forth for purposes of explanation. However, it will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, structures and devices are shown in block diagram form in order to avoid obscuring the present invention. References to numbers without subscripts are understood to refer to all examples of subscripts corresponding to the recited number. Further, the language used in this disclosure has been principally selected for readability and teaching purposes and may not have been selected for the purpose of defining or limiting the inventive subject matter, and reliance should be placed on the claims to determine such inventive subject matter. When reference is made in this specification to "one embodiment" or "an embodiment," it means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention, and when reference is made to "one embodiment" or "an embodiment" multiple times, it should not necessarily be understood that all references are to the same embodiment.

[0010] Some of the following description is written in terms related to software or firmware, but the various embodiments may, as necessary, implement the features and functions described herein by software, firmware, or hardware, including any combination of software, firmware, and hardware. References to daemons, drivers, engines, modules, or routines should not be construed as suggesting a limitation to any type of implementation of the embodiments.

[0011] Apnea is a serious clinical event that requires medical attention within seconds and is very common in premature infants. Newborns tend to have an irregular breathing pattern and periods of apnea lasting several seconds at a time. How to determine which events are clinically important varies among physicians. A common rule of thumb is that apnea is considered a clinical event if (a) the cessation of breathing lasts longer than 20 seconds, or (b) the cessation of breathing lasts longer than 10 seconds and is accompanied by either bradycardia (a slowdown of the heart) or oxygen desaturation. In the case of neonates, bradycardia is typically defined as a heart rate of less than 100 beats per minute, and oxygen desaturation is typically defined as an SpO2 of less than 80%. Bradycardia and desaturation can occur without an accompanying cessation of breathing. There is a high likelihood of further deterioration when these life-related thresholds are exceeded within a certain period from the start or end of a significant apnea event in a neonate.

[0012] Clinical apneas occur in more than half of infants with a birth weight less than 1500 g and in almost all infants with a birth weight less than 1000 g. Apneas can be the cause or result of numerous other clinical problems such as hypoxemia, hypoglycemia, neurological injury, or sepsis. Apneas are also a common manifestation of the immature neurological system in infants who were born very preterm but otherwise have no clinical pathology. Three types of apnea, obstructive apnea, central apnea, and mixed apnea, are common in premature infants. Obstructive apnea is airway obstruction and is typically associated with struggling or thrashing movements of the infant. Central apnea is cessation of respiratory drive, and the infant usually remains extremely still without attempting to breathe. Mixed apnea typically begins with an obstructive event and then changes to central apnea. There is evidence, however, that central apnea can also become obstructive apnea, and some sources suggest that the distinction between these two types should not be made too rigidly. In many cases, apnea is combined with or induces bradycardia (a significant decrease in heart rate).When accompanied by bradycardia, a decrease in oxygen saturation, or both, these apneas are serious clinical events that require immediate medical attention and an investigation for associated pathology. Furthermore, central apnea is thought to indicate immaturity of control of respiration, and discharge from the NICU is typically postponed until the apnea has been absent for 3 to 8 days. As a result of these regulations, when infants are at home, by reducing the likelihood that those infants will experience an episode of apnea without a monitoring device and clinicians, those infants are able to be discharged safely.

[0013] A bedside monitor attempts to detect apnea based on continuous monitoring of physiological data of chest impedance (CI). Using the electrodes used to monitor an electrocardiogram (ECG), a small high-frequency voltage (such as 52.6 [kHz]) is applied to the chest, and the resulting high-frequency current is measured. The impedance Z measured is equal to the value obtained by dividing the applied voltage V by the observed current. The measured impedance typically exists within the range of 50 to 300 ohms and is related to the conductivity of muscle, skin, other tissues, and the contact between the electrode and the skin. When the infant is breathing, the impedance varies with each breath. In the case of a central apnea event, since breathing ceases, the change in chest impedance decreases. On the other hand, the beating of the heart also causes impedance fluctuations each time the heartbeat pumps blood from the thorax. In this way, even during an apnea event, the chest impedance may vary and reach a threshold for detection as respiration, foiling the monitor’s apnea alarm.

[0014] The more malleable rib cage of neonates moves with the heartbeat, so detecting the cessation of breathing in neonates is particularly difficult. Chest impedance leads may mistake the resulting change in rib cage diameter for respiration. Current apnea detectors do not address this problem, so in these cases, clinicians need to rely on alarms indicating subsequent deterioration of the patient, such as bradycardia.

[0015] As a result of these cardiac artifacts, some of the central apnea episodes in newborns are completely missed, and some of these episodes are severe. Some of the multiple studies have found that conventional apnea monitors miss more than 10% of even extreme apnea events due to cardiac artifacts in the chest impedance signal.

[0016] The multiple techniques described below remove these cardiac artifacts from the chest impedance waveform used to measure respiration. Although described below with respect to real-time physiological data, the same techniques may be used on historical physiological data for retrospective analysis.

[0017] Due to the increased detection of apnea events, in certain embodiments, automated interaction may be utilized to stimulate premature infants during apnea events.

[0018] The following disclosure describes techniques for improving the detection of central apnea. More specifically, the standard CI signal used to monitor the respiration rate is analyzed to filter out the contribution to the chest impedance signal resulting from the pulsating heart, indicating an index of the apnea event.

[0019] FIG. 1 is a screenshot illustrating a graphical user interface 100 according to one embodiment, in which an index of central apnea is displayed. Two waveform lanes of a CI waveform 110 and an ECG waveform 120 are illustrated in the graphical user interface 100. The exemplary waveform data in FIG. 1 is not intended to be medically accurate. In this example, although the CI waveform 110 is not flat, the patient is experiencing an apnea condition indicated by line 130. The CI waveform is the variation experienced as a result of the heartbeat illustrated by the ECG waveform 120. This is known to be because both waveforms periodically repeat at the same rate. In some of the embodiments, one or both of an audible alarm index and a visual alarm index may be generated in response to a determination that an apnea condition exists, in addition to the index shown by line 130. In other embodiments, an automatic response may be triggered to physically stimulate an infant, and the automatic response can cause a cessation of the apnea event.

[0020] Figure 2 is a screenshot illustrating a graphical user interface 200 according to one embodiment similar to the graphical user interface 100. In this example, graph 220 is one exemplary CI waveform, graph 230 shows the heart rate determined from photoplethysmogram data, graph 240 shows the heart rate determined from ECG data, graph 250 shows the SpO2 data determined from photoplethysmogram data, and graph 260 shows the respiration rate calculated based on the CI waveform only. In this example, an apnea event indicating that the patient has ceased breathing and meets the criteria for bradycardia and oxygen desaturation is shown as indicated by the horizontal line 210. In one embodiment, the apnea event is shown to start only after a threshold time (e.g., 20 seconds) has elapsed during which the cessation of breathing has been identified and bradycardia and a decrease in oxygen saturation have occurred. This reduces the nuisance alarm indicators for short apnea events that end without intervention.

[0021] Both FIGS. 1 and 2 illustrate a real-time display of information indicating the presence of an apnea event, but some of the multiple embodiments in which real-time data is archived for research or clinical purposes are capable of investigating historical patient data, analyzing that data, and providing the ability to indicate the presence of apnea events in that historical data. Such a historical investigation may be useful for detecting previously unnoticed prior apneas and providing clinicians with better information for evaluating a patient's health.

[0022] For clarity, the following description focuses on events of cessation of breathing events that are apnea events. On the other hand, multiple different healthcare providers may define an apnea event as a cessation of breathing without other factors, or a cessation of breathing combined with one or more other factors such as bradycardia or a decrease in oxygen saturation. The system may be configured for any combination of these additional factors as needed. For example, a patient may stop breathing for longer than a threshold time but maintain a normal heart rate and oxygen saturation, in which case some of the system configurations described below may not indicate an apnea event. Embodiments of the system described below can enable a clinician to select a combination of criteria used to determine an apnea event.

[0023] Inputs to a central apnea detector may include CI waveforms, ECG waveforms, and the vital signs of heart rate and oxygen saturation (SpO2). Each of the signals can be cleaned to remove data artifacts if required.

[0024] As described below, it is possible to identify the cardiac artifact component of chest impedance based on its shared phase (frequency progression) with any signal that captures the movement of the heart (e.g., an ECG signal, etc.). The first step is to model the progression of the cardiac phase. This modeling may be done in a plurality of ways using any signal that captures the movement of the heart. For example, the cardiac phase may be calculated by utilizing the phase of the Hilbert transform applied to a photoplethysmogram waveform.

[0025] In one embodiment, to determine the cardiac phase, standard peak / trough detection is performed to find the R peaks in the ECG signal that occur in each cardiac cycle. The cardiac phase signal φ is set to 0 in phase at each R peak time, and having the phase increase linearly with time to 2π = 0 radians for samples in between each set of consecutive R peaks, is created to model the heart's frequency at any given time. In this way, the cardiac phase signal φ for a segment of data containing N samples is an N×1 vector

Number

[0026] The measured chest impedance signal CI corresponding to and measured at the cardiac phase init component (i.e., the cardiac artifact) may then be extracted using a Fourier series approximation of CI that is a function of the determined cardiac phase. The following description is written in terms of Fourier series, but other frequency or time domain analysis and approximation techniques may be used. init The Fourier series approximation uses M harmonics stored as a 1×M vector H = [1 2 … M].

[0027]

[0028] ​In some of the embodiments, M = 3 sufficiently captures the frequency components included in the cleaned CIs, but other numbers of harmonics may be used as needed.

[0029] This results in an N×M cardiac phase harmonic matrix φH

Number

[0030] The frequency components F of the Fourier series approximation of the cardiac artifact can be calculated from the cardiac phase and are an N×2M matrix

Number

[0031] Next, the Fourier series coefficients of the cardiac artifact can be determined using the above cardiac artifact frequency components and the chest impedance signal. Those Fourier series coefficients may be represented as a 2M×1 vector

Number

[0032] The Fourier series coefficients of the cardiac artifact are

Number

[0033] Cardiac artifact CI art The approximation formula is then, [Number] may be calculated as.

[0034] Cardiac artifact CI art may then be removed from the measured chest impedance signal, and the filtered chest impedance signal CI filt = CI init - CI art is generated.

[0035] When cardiac artifacts are removed from chest impedance, it is possible to identify events of apnea, bradycardia, and decreased oxygen saturation using standard signal processing techniques for filtered chest impedance and vital threshold processing of heart rate and oxygen saturation. When there is little lung movement (low standard deviation) in the filtered chest impedance signal, the neonate is considered not to be breathing, and an apnea event is identified.

[0036] The apnea event probability is, [Number] may be estimated using a Fermi function such as.

[0037] In the above formula, σ is the standard deviation of CI filt . The parameters of the above Fermi function are exemplary and are only one example in this book. Other Fermi functions or other types of functions may be used for CI filtThe probability of apnea may be calculated based thereon. In some of the embodiments, when the probability of an apnea event exceeds a pre-determined threshold, the system is triggered, and the system displays an alarm indication of an apnea event on a graphical user interface such as the graphical user interfaces illustrated in FIGS. 1 and 2. Further, a set of alarm criteria may be developed based on the relative probability of apnea events over a defined period. Additionally, in embodiments where one or more of bradycardia and a decrease in oxygen saturation are considered apnea criteria, the results of measurements of heart rate and SpO2 data may be combined with the probability calculated above to trigger an alarm indication.

[0038] During a defined period at the start or end of a respiratory arrest event, identify a respiratory arrest with an event of bradycardia and a decrease in oxygen saturation when these vital thresholds are passed. The techniques described herein may be used to determine apnea events in pediatric and adult patients, although specific criteria such as a decrease in heart rate and oxygen saturation may vary in the non-neonatal population.

[0039] The improved system resulting from detecting apnea events avoids missing apnea events masked by the patient's heart beat in existing apnea detection systems.

[0040] Figure 3 is a flowchart illustrating a technique 300 for detecting an apnea event and automatically acting on the apnea event according to one embodiment. In block 310, the system receives real-time CI and cardiac data from a plurality of sensors attached to a patient. In block 320, as described above, perform a phase analysis of the cardiac data (e.g., ECG, etc.) to generate a phase signal Φ and a cardiac artifact phase harmonic matrix ΦH. In block 330, use the algorithm described above to calculate the cardiac artifact component CI art (cardiac artifact component CI art ) of the chest impedance. Next, in block 340, calculate the filtered chest impedance CI init (filtered chest impedance CI init ) by subtracting the cardiac artifact component CI art (cardiac artifact component CI art ) from the measured chest impedance CI filt (measured chest impedance CI filt ). In block 350, the filtered chest impedance CI filtWhen apnea is indicated, an alarm may be triggered in a graphical user interface such as the graphical user interfaces illustrated in FIGS. 1 and 2, either as an audible alarm or in any other manner known in the art for generating an alarm. In some of the plurality of embodiments, apnea may be detected when the probability of an apnea event calculated as described above reaches or exceeds a predefined threshold over a predefined duration, or when a set of criteria is met. In some of the plurality of implementations, rather than using a strict time threshold, the overall duration that meets the threshold is evaluated. For example, if there are two 12-second periods that are 1 second apart and meet the threshold, those two segments may be combined and considered as one apnea event lasting 25 seconds.

[0041] If apnea is not detected at block 350, the technique continues to receive CI and cardiac data at block 310. If apnea is detected at block 350, an alarm is signaled at block 360. At block 370, if available, automatic actions such as generation of vibration, puff of air, or initiation of other physical stimuli capable of restarting breathing in the patient may be performed to physically stimulate the patient in response to the apnea event. If the system implementing technique 300 is configured to use one or more of bradycardia and a decrease in oxygen saturation as part of the evaluation of the apnea event threshold, technique 300 may include other operations not illustrated in FIG. 3 for detecting bradycardia and a decrease in oxygen saturation from the heart rate and SpO2 data received from the patient monitor. If automatic physical stimulation of the patient is not available, a clinical staff member may approach the patient and manually provide a tactile stimulus such as gently tapping the sole of the foot or rubbing the back. If spontaneous breathing is not initiated by the physical stimulation, the apnea event may require additional intervention such as oxygen inhalation.

[0042] FIG. 4 is a block diagram illustrating a system 400 for collecting, archiving, and processing any data in a medical environment according to one embodiment. System 400 is described in detail in U.S. Patent No. 10,889,2045, entitled "Distributed Grid Computing Platform for Collecting, Archiving, and Processing Any Data in a Medical Environment," which is incorporated by reference in its entirety for all purposes.

[0043] As shown, there are five types of servers: a data acquisition (DAQ) server 487, informatics server(s) 480, a database server 485, an HL7 server 483, and a web server 490. Any number and any type of servers may be arranged in response to requests. All of the servers 480 - 490 are connected to each other via one or more hospital networks 430 and to bedside monitors. Although shown as a single hospital Ethernet network 430, any number of interconnected networks may be used, using any desired network protocol and technology.

[0044] In addition, a plurality of bedside monitors for monitoring the physiological data of patients in the bed 410 are connected to the hospital network 430. The plurality of bedside monitors may include a network-connected monitor 420A capable of delivering digital physiological data to the hospital network 430, a serial device 420B that is not directly connected to the network but generates digital data, and an analog device 420C that is not directly connected to the network but generates analog data. The communication boxes 440A and 440B typically enable the serial device 420B and the analog device 420C to be connected to the hospital network 430 via the network switch 450, respectively. In addition, the branch office 460 may also be connected to the network 430 via the network switch 450 to perform data manipulation and time synchronization, as described below. Any number of bedside monitors 420 may be used as desired by physicians and other clinical staff for patients in the bed 410.

[0045] FIG. 4 illustrates bedside monitors and related communication devices directly or indirectly connected to the hospital network 430, and as part of the system 400, remote bedside monitoring devices such as home monitoring devices indirectly connected to the hospital network 430 by the Internet or other communication technologies may be used.

[0046] Additionally, one or more research computers 470 may be connected directly or indirectly to the hospital network 430 to enable researchers to access the aggregated data (aggregated information) collected from the bedside monitors 420 for analysis and development.

[0047] The web server 490 is configured to communicate with personal devices such as the laptop 495A, the tablet 495B, or the smartphone 495C via a web browser interface using the Hypertext Transport Protocol (HTTP).

[0048] Here, referring to FIG. 5, one exemplary system 500 for use as one of the servers 480 - 490 is illustrated in the form of a block diagram. The exemplary computer 500 optionally includes a system unit 510 that may be connected to an input device or system 560 (e.g., keyboard, mouse, touch screen, etc.) and a display 570. A program storage device (PSD) 580 (which may sometimes be referred to as a hard disk) is included in the system unit 510. A network interface 540 for communicating via a network with other computing devices and enterprise infrastructure devices (not shown) is also included in the system unit. The network interface 540 may be included within the system unit 510 or may exist external to the system unit 510. In either case, the system unit 510 will be communicatively coupled to the network interface 540. The program storage device 580 represents any medium of a non - volatile memory device including all forms of optical and magnetic, including solid - state memory elements including removable media, and may be included within the system unit 510 or may exist external to the system unit 510. The program storage device 580 may be used for storing software that controls the system unit 510 when executed, data used by the computer 500, or both.

[0049] The system unit 510 may be programmed to execute a method according to the present disclosure (an example is shown in FIG. 3). The system unit 510 includes a processor unit (PU) 520, an input / output (I / O) interface 550, and a memory 530. The processor unit 520 may include any programmable controller device such as a microprocessor available from Intel Corporation and other manufacturers. The memory 530 may include one or more memory modules and may include random access memory (RAM), read only memory (ROM), programmable read only memory (PROM), programmable read / write memory, and solid state memory. Those skilled in the art will also recognize that the PU 520 may also include some internal memory, for example, cache memory.

[0050] FIG. 6 is a screenshot illustrating one exemplary graphical user interface 600 for monitoring historical information regarding a patient's apnea events according to one embodiment. Each apnea event may be detected and recorded using the systems and techniques described above and then transmitted to the graphical user interface 600 for display. Aggregate information regarding apnea events may also be transmitted to the graphical user interface 600 for display. In this exemplary graphical user interface 600, a first region 610 provides historical information regarding the number of recent apnea events, in this example, the time from the last apnea event and the number of apnea events in the last 24 hours and the last 5 days. The displays of "last 24 hours" and "last 5 days" are merely examples, and other useful historical periods may be provided in addition to or instead of the historical periods illustrated in FIG. 6. A second region 620 provides historical information regarding the total length of apnea events in the last 12 hours. In this example, recordings related to two types of oxygen saturation (SpO2), SpO2>Max SpO2 Threshold and SpO2<Min SpO2 Threshold, are displayed. Similarly, recordings related to two types of heart rate (HR), HR>Max HR Threshold and HR<Min HR Threshold, are displayed. In addition to or instead of the information illustrated in FIG. 6, other types of historical information may be displayed in the second region 620.

[0051] Below the first region 610 and the second region 620 is a region that provides historical information regarding individual apnea events. The timeline 650 in this example provides an indication of apnea events in the 24-hour period up to the selected "time zero". A pair of calipers 640 may be placed on the timeline to select a specific window for detailed display within the region 660 below the timeline 650. An export button 630 enables exporting information regarding the selected time window to an electronic medical record (EMR) system.

[0052] Details regarding each apnea event may be displayed within the detailed information area 660. As illustrated in FIG. 6, the information displayed for each event includes the length of the apnea, the minimum HR that occurs during the period specified in relation to that event, the minimum oxygen saturation level that occurs during the period specified in relation to that event, whether the clinician has determined the event detected by the system to be an actual apnea event, the type of clinical intervention being performed in response to the apnea event such as compression, light foot tapping, or no intervention, the designation of the type of apnea event such as obstructive, central, mixed, or unknown, and the start time of the event. Other detailed information may be provided to the user interface 600 as needed.

[0053] The areas and the arrangement of the areas in the exemplary graphical user interface 600 of FIG. 6 are exemplary and are merely one example, and other areas and other arrangements of the areas may be provided as required. Some of the elements of the graphical user interface are illustrated as drop-down type user interaction elements, but other types of user interaction elements may be used as required. Color may be used to improve the operability of the user. For example, in some of the plurality of implementations, indicators within the timeline 650 of a particular apnea event may be displayed in a different color than other indicators, while corresponding rows within the detailed area 660 may be highlighted or shown in a different color.

[0054] In a clinical setting without the disclosed patient monitoring system, a nurse or other clinical staff manually records apnea events occurring during a shift on a flow sheet by writing the data by hand on a single sheet of paper or typing the data in electronic format. In either case, the flow sheet requires clinical attention and is subject to human transcription errors. The disclosed system enables automatically populating clinical flow sheets with apnea event information, which reduces the likelihood of human error in recording the information and significantly reduces the manual effort of the nurse or other clinical staff. This clinical flow sheet may include apnea length, start time, SpO2, and HR information. Other items such as clinical adjudication, type of apnea, and type of clinical intervention may still be entered by the nurse, but will be entered in a standardized form by selecting from a list of possible entries. For example, clinical staff may report that it is difficult to detect the end of an apnea event and thus calculate the length of the apnea event. By automatically detecting both the start and end of an apnea event, the disclosed system can automatically calculate the length of the event, further reducing the burden on clinical staff and reducing manual data entry errors.

[0055] Rather than relying on detection by clinical staff, it is possible to provide better tracking of apnea events by collecting objective data regarding apnea events and improving existing alarm systems. This improved tracking not only results in fewer false alarms but also leads to the detection of apnea events that are not currently detected in the clinical setting. One result of such better data is to reduce the clinical stay of infants, reduce the childcare costs for both the clinical facility and the parents, and improve the quality of life for both the infant and the parents. Since patients are often not released until a certain period of apnea-free time has elapsed, reducing false alarms of apnea events, for example, enables patients to be released earlier.

[0056] Specific exemplary embodiments are described in detail and illustrated in the accompanying drawings, but it should be understood that such embodiments are merely exemplary and have not been devised in derogation of the basic scope determined by the claims that follow.

Claims

1. A method performed by a patient monitoring system for detecting an apnea event in a patient, the method comprising: receiving, by the patient monitoring system, chest impedance physiological data and cardiac physiological data from bedside monitoring equipment associated with the patient; modeling, by the patient monitoring system, a cardiac phase using the cardiac physiological data; calculating, by the patient monitoring system, a frequency domain approximation or a time domain approximation of a cardiac artifact based on the modeled cardiac phase representation and the chest impedance physiological data; removing, by the patient monitoring system, the calculated frequency domain approximation or time domain approximation of the cardiac artifact from the chest impedance physiological data to generate filtered chest impedance data; calculating, by the patient monitoring system, a probability of an apnea event based on the filtered chest impedance data; generating, by the patient monitoring system, an alarm indicator in response to meeting a set of criteria based on the probability of the apnea event over a period of time. A method.

2. The method according to claim 1, further comprising triggering, by the patient monitoring system, an automatic physical stimulus of the patient in response to the apnea event.

3. The method according to claim 1, further comprising calculating, by the patient monitoring system, a length of the apnea event.

4. The method according to claim 1, further comprising: recording, by the patient monitoring system, an apnea event for the patient; transmitting, by the patient monitoring system, historical information regarding the apnea event to a graphical user interface; calculating, by the patient monitoring system, aggregated information regarding the recorded apnea event for the patient; transmitting, by the patient monitoring system, the aggregated information regarding the recorded apnea event to the graphical user interface. **Claim 5** The method according to claim 4, wherein the step of recording an apnea event for the patient by the patient monitoring system includes the step of recording data on oxygen saturation and heart rate associated with the apnea event by the patient monitoring system. **Claim 6** The method according to claim 1, further comprising the step of receiving, by the patient monitoring system from the bedside monitoring device, measured values of heart rate and measured values of oxygen saturation. The method according to claim 1, wherein the set of criteria includes criteria for heart rate and oxygen saturation. **Claim 7** The method according to claim 1, wherein the patient is a neonate. **Claim 8** A patient monitoring system for detecting an apnea event of a patient, the patient monitoring system comprising: a bedside monitoring device associated with the patient and generating chest impedance physiological data and cardiac physiological data; a computer system, wherein the computer system: receives the chest impedance physiological data and the cardiac physiological data; models a cardiac phase using the cardiac physiological data; calculates a frequency domain approximation or a time domain approximation of a cardiac artifact based on the modeled cardiac phase representation and the chest impedance physiological data; removes the calculated frequency domain approximation or time domain approximation of the cardiac artifact from the chest impedance physiological data to generate filtered chest impedance data; calculates a probability of an apnea event based on the filtered chest impedance data; and is programmed to generate an alarm indicator responsive to meeting a set of criteria based on the probability of the apnea event over a temporal period. A patient monitoring system. **Claim 9** The patient monitoring system according to claim 8, wherein the computer system is further programmed to trigger an automatic physical stimulus for the patient. **Claim 10** The patient monitoring system according to claim 8, wherein the computer system is further programmed to calculate the length of the apnea event. **Claim 11** The patient monitoring system according to claim 8, wherein the computer system is further programmed to record an apnea event for the patient; transmit historical information regarding the apnea event to a user interface. Calculate aggregated information regarding the recorded apnea events for the patient, and Transmit the aggregated information regarding the recorded apnea events to the user interface, The patient monitoring system according to claim 8, which is programmed to

12. The computer system is further programmed to record data on oxygen saturation and heart rate associated with the apnea events, The patient monitoring system according to claim 11.

13. The computer system is further programmed to receive measurements of heart rate and oxygen saturation from the bedside monitoring device, The set of criteria includes criteria for heart rate and oxygen saturation, The patient monitoring system according to claim 8.

14. The patient is a neonate, The patient monitoring system according to claim 8.

15. A non-transitory storage medium storing software for detecting apnea events in a patient, when the software is executed, the software causes a computer system to Receive chest impedance physiological data and cardiac physiological data from a bedside monitoring device associated with the patient, Model the cardiac phase using the cardiac physiological data, Calculate a frequency domain approximation or a time domain approximation of cardiac artifacts based on the modeled representation of the cardiac phase and the chest impedance physiological data, Remove the calculated frequency domain approximation or time domain approximation of the cardiac artifacts from the chest impedance physiological data to generate filtered chest impedance data, Calculate the probability of an apnea event based on the filtered chest impedance data, and Generate an alarm indicator in response to meeting a set of criteria based on the probability of the apnea event over a temporal period, A non-transitory storage medium.

16. When the software is executed, the software further causes the computer system to Trigger an automatic physical stimulus for the patient, The non-transitory storage medium according to claim 15.

17. When the software is executed, the software further causes the computer system to ​ The non-transitory storage medium according to claim 15, which causes the length of the apnea event to be calculated. **Claim 18** When the software is executed, the software further causes the computer system to record an apnea event for the patient, send historical information regarding the apnea event to a user interface, calculate aggregated information regarding the recorded apnea event for the patient, and send the aggregated information regarding the recorded apnea event to the user interface. The non-transitory storage medium according to claim 15. **Claim 19** When the software is executed, the software further causes the computer system to record data on SpO 2 and heart rate associated with the apnea event. The non-transitory storage medium according to claim 18. **Claim 20** When the software is executed, the software further causes the computer system to receive a measured heart rate value and a measured oxygen saturation value from the bedside monitoring device, The set of criteria includes criteria for heart rate and oxygen saturation. The non-transitory storage medium according to claim 15.

Images