Patent Application
20220016371
The present invention relates to systems and methods for assisting a patient in avoiding obstructive sleep apnea (OSA) and/or for assisting a patient in weaning from a PAP therapy.
Obstructive sleep apnea (OSA) is a common disorder that involves repetitive closure of the upper airway during sleep. OSA is mostly preventable and has severe comorbidities, including daytime somnolence, high blood pressure, and other cardiovascular sequelae, amongst others. Sleep apnea can be prevented in most people by maintaining a healthy weight and avoidance of exacerbating influences, such as alcohol.
Sleep apnea is most often diagnosed by measuring patients' Apnea-Hypopnea Index (AHI) using polysomnography in a sleep lab, although portable diagnostic devices to provide home sleep testing (HST) have become more popular. Recent innovations in wearable devices utilize photo plethysmography (PPG) technology to diagnose suspected OSA based on heart rate, heart rate variability, estimated respiratory effort, and SpO2.
Sleep apnea is most often treated by positive airway pressure (PAP), provided by a non-invasive mask, hose, and pressure generation device. PAP can be continuous (CPAP) or vary with inhalation and exhalation (BiPAP) and can be set at a fixed pressure or provided by a device that automatically titrates the pressure level(s). PAP therapy often remains difficult for patients to adhere to.
While care pathways are defined to diagnose OSA and onboard patients into PAP therapy, presently there are no defined interventions to help users avoid a diagnosis of OSA, or to offboard or wean them from PAP therapy and reverse an OSA diagnosis. Patients may require reduced (or completely weaned off) therapy with changes in lifestyle, weight, etc.
While there are many common risk factors for OSA, e.g., weight, sleep debt, body position while sleeping, daytime activity levels, daytime stress metrics, alcohol usage, smoking, fluid/salt intake, medication(s), body fat percentage and/or distribution, individuals are differently susceptible to each risk factor. Embodiments of the present invention help individuals target which risk factor(s) to improve in order to avoid and/or cure themselves from OSA, and thus avoid or eliminate the need (over time) for PAP therapy.
As one aspect of the present invention a method for assisting a patient in avoiding obstructive sleep apnea and/or for assisting the patient in weaning from a PAP therapy is provided. The method comprises: receiving in a controller health related data of the patient obtained from the patient by one or more electronic devices associated with the patient; analyzing the health related data with the controller; determining in the controller from the analyzing of the health related data, an OSA risk factor having a correlation to OSA severity in the patient; and providing the OSA risk factor to the patient.
The controller may be structured and configured to implement a predictive AI system, and the analyzing and determining may be performed by the predictive AI system.
The predictive AI system may be an artificial neural network trained using previous health related data of the patient.
The one or more electronic devices associated with the patient may comprise a wearable device. The wearable device may comprise a smartwatch.
The method may further comprise providing a correlation between values of the OSA risk factor and AHI values of the patient.
The method may further comprise providing a target value for the OSA risk factor to reduce an AHI value of the patient to below a predetermined threshold. The method may further comprise providing a projected time at which the target value may be reached by the patient.
Providing the OSA risk factor to the patient may comprise providing the OSA risk factor to the patient via one of the one or more electronic devices associated with the patient. The one or more electronic devices associated with the patient may comprise a smartwatch. The one or more electronic devices associated with the patient may comprise a smartphone.
As another aspect of the present invention a system for assisting a patient in avoiding obstructive sleep apnea and/or for assisting the patient in weaning from a PAP therapy is provided. The system comprises: a number of electronic devices, each structured to capture health related data from the patient; a controller in communication with the number of electronic devices and structured to carry out an analysis of the health related data and determine an OSA risk factor having a correlation to OSA severity in the patient; and an output display structured to convey the OSA risk factor to the patient.
The controller may comprise a predictive AI system that is structured to carry out the analysis of the health related data and determine the OSA risk factor having the correlation to OSA severity in the patient.
The number of electronic devices may comprise a smartwatch.
As yet another aspect of the present invention, a predictive artificial intelligence system is provided. The artificial intelligence system is trained to: receive in a controller health related data of the patient obtained from the patient by one or more electronic devices associated with the patient; analyze health related data received from one or more electronic devices associated with a patient; and determine an OSA risk factor having a correlation to OSA severity in the patient.
These and other objects, features, and characteristics of the present invention, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are provided for the purpose of illustration and description only and are not intended as a definition of the limits of the invention.
As used herein, the singular form of “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
As used herein, the term “number” shall mean one or an integer greater than one (i.e., a plurality).
As used herein, the terms “user”, “patient”, and “individual” are used interchangeably to refer to a person who is the subject to which the methods and/or systems described herein are helping to avoid OSA or to wean from a PAP therapy.
As used herein, the term “controller” shall mean a number of programmable analog and/or digital devices (including an associated memory part or portion) that can store, retrieve, execute and process data (e.g., software routines and/or information used by such routines), including, without limitation, a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a programmable system on a chip (PSOC), an application specific integrated circuit (ASIC), a microprocessor, a microcontroller, a programmable logic controller, or any other suitable processing device or apparatus. The memory portion can be any one or more of a variety of types of internal and/or external storage media such as, without limitation, RAM, ROM, EPROM(s), EEPROM(s), FLASH, and the like that provide a storage register, i.e., a non-transitory machine readable medium, for data and program code storage such as in the fashion of an internal storage area of a computer, and can be volatile memory or nonvolatile memory.
As previously mentioned, there are many common risk factors for OSA, however the susceptibility to such risk factors, and thus the relevance or various risk factors, varies from person to person. Embodiments of the present invention help individuals target a particular risk factor or factors to improve in order to avoid and/or cure themselves from OSA, and thus avoid or eliminate the need (over time) for PAP therapy.
Embodiments of the present invention generally “coach” a user to avoid OSA or wean from PAP therapy by analyzing health related data of a user obtained from the user by one or more electronic devices associated with the user. As used herein, “health related data” refers to data/information obtained passively or actively from the patient that is indicative of present health or predictive of the future health of the patient. The example embodiments discussed herein discuss various examples of health related data that may be employed, however, it is to be appreciated that other health related data may be employed without varying form the scope of the present invention.
Referring now to
Continuing to refer to
In other example embodiments of the present invention, one or more in-room sensors 32 may be utilized as part(s) of OSA Probability/Severity Monitor 14. For example, a piezoelectric in- (or under-) mattress sensor can be utilized to provide an estimation of a user's OSA score based on movements by the user while in bed. As another example, OSA score monitoring for a user may be provided by an in-room microphone source, such as a smartphone app or a home audio assistant that monitors the loudness and frequency of snoring by the user as well as indications of the cessation and recurrence of breathing (apnea episodes and arousals) by the user. As yet another example, OSA score monitoring for a user can be provided by an active radar/sonar source that monitors breathing (and the cessation of breathing) by the user as well as arousal events associated with sleep disordered breathing.
In another example embodiment, a user's OSA score is determined from an analysis of usage of a PAP device 34 utilized by the user for receiving their PAP therapy. In such embodiment, the OSA severity can be provided directly from the PAP device 34 when in a fixed pressure mode (e.g. AHI=7.5 at a CPAP pressure of 9 cmH2O). Alternatively, OSA severity can be estimated from the PAP device as a function of the pressures throughout the night (or a function of pressure, e.g. “90% pressure”, the pressure which the device was at or below for 90% of the night, typically the lower the 90% pressure the less severe the OSA) when in an auto-titrating mode (e.g. 90% pressure of 13.2 cmH2O).
In yet another example embodiment, an OSA score estimate for a user can be determined by a combined metric from PAP therapy device 34 and another monitoring device from among wearable device(s) 30 and/or “in-room sensor(s) 32 previously discussed. The combined metric utilizes information from the external monitoring device while PAP therapy device 34 is not being used, and from the PAP therapy device 34 while in use. The combined metric is most helpful when a patient uses PAP therapy for only a portion of the night.
In yet a further example embodiment, the OSA score estimate for a user may be provided by a self- or bed partner-questionnaire about the noted severity of sleep disordered breathing on a given night. For all embodiments, the OSA score estimate for a user is provided on a nightly basis.
Continuing to refer to
OSA risk factors that are monitored by user reports provided via user input device(s) 38 include (without limitation): alcohol usage, smoking, and fluid/salt intake. Optionally, subjective stress may be self-reported. As an example, OSA self-reported risk factors may be provided by the user in a pre-bedtime questionnaire and may be aggregated for the day (e.g. 3 alcoholic drinks) or may list times and amounts (e.g. 1 alcoholic drink at each 5 pm, 7 pm, and 10 pm).
Controller 12 is in communication with, and structured to receive inputs 20 from one or both of OSA Probability/Severity Monitor 14 and/or OSA Risk Factor Monitor 16 (i.e., from one or more of: wearable device(s) 30, in-room sensor(s) 32, PAP therapy device 34, external sensor(s) 36, and/or user input device(s) 38)). Controller 12 is also in communication with, and is structured to provide output(s) 22 to, output display 18 and/or a suitable processing device associated therewith.
Controller 12 may be provided locally as a computing device (e.g., smartphone, tablet computer, etc.) or a portion thereof, or remotely as a cloud based arrangement accessible via suitable wired or wireless arrangement. A memory portion of controller 12 has stored therein a number of routines that are executable by a processor portion of controller 12. One or more of the aforementioned routines implement (by way of computer/processor executable instructions) a software application that is configured (by way of one or more algorithms) to, among other things, receive inputs 20 from one or more of the elements of OSA Probability/Severity Monitor 14 and/or OSA Risk Factor Monitor 16 and analyze such inputs 20 in order to determine information for coaching a user toward reducing one or more particular risk factors in order to avoid OSA or lessen a user's OSA so as to wean the user from PAP therapy.
In the example embodiment of
Predictive AI system 24 includes an OSA Risk Factor Target Module 26 and a Behavior Modification and Prediction Module 28. OSA Risk Factor Target Module 26 observes the longitudinal increases or decreases in OSA probability/severity for a user determined form inputs 20 from OSA Probability/Severity Monitor 14 and searches for correlations with monitored risk factors. Examples of data used for such correlation purposes is shown in
Behavior Modification and Prediction Module 28 assists users to modify the most meaningful behaviors that contribute to their risk/severity of OSA. Behavior Modification and Prediction Module 28 can predict at which point(s) (as multiple OSA risk factors may be determined to correlate to AHI severity and/or over time a different risk factor may be determined to more strongly to correlate to AHI severity) no OSA will persist and provide the user with such point(s) as a target goal or goals. Behavior Modification and Prediction Module 28 helps users see progress on their path to reducing OSA severity/probability by providing feedback on progression toward, or regression from, such target goal. Such target goal or goals may be adjusted over time by Behavior Modification and Prediction Module 28 as further data in regard to the user is received/analyzed.
In one example embodiment, Behavior Modification and Prediction Module 28 uses a curve fit using the OSA severity data and the risk factor being tracked in order to determine the point at which OSA severity is low. In the example shown in
As the user makes progress with behavior change to decrease the severity of OSA, Behavior Modification and Prediction Module 28 projects the time at which OSA symptoms may be resolved. In the example shown in
In some example embodiments, Behavior Modification and Prediction Module 28 runs iteratively through a list of risk factors to modify and may provide the user with a suggested prioritized list of risk factors to modify and let the user choose which to accomplish first, second, etc.
In one example embodiment, Behavior Modification and Prediction Module 28 continuously tracks each of the modifiable variables on a nightly basis in order to determine if the current factor being coached/modified is still the most valuable to the user. For example, body position may have a high degree of correlation until the user learns to avoid the supine position. At that time, the next modifiable factor may be daytime activity level, amount of sleep debt, weight, etc. At the time when a new modifiable factor is determined to be more valuable for the user to modify, the user may be asked if they want to take on a new factor or continue with the current factor.
In one example embodiment, Behavior Modification and Prediction Module 28 determines if the user is not making progress on a given modifiable factor (e.g. stall in weight loss) and suggests working on the next most important modifiable factor.
Behavior Modification and Prediction Module 28 may be implemented in a phone app or other suitable application through in-app suggestions with the help of components such as dashboards. Dashboards help the users (patients) see trends and correlations between OSA data (AHI) and wearable data (e.g., smartwatches, smart rings, etc.) and other sensors (connected weighing scale etc.). Such views can be further augmented with simple alerting algorithms to prompt users about critical metrics, disease progression, and different milestones.
In another embodiment, this data will enable health coaches (e.g., without limitation, such as those involved in Philips Patient Adherence Management System, PAMS) to adequately advise the patients about appropriate intervention. This embodiment involves a collation of data variables from the list of patients subscribing to this service. This can be supported by population-level analytics that help the coaches identify the patients to be contacted.
Referring now to
From the foregoing it is thus to be appreciated that embodiments of the present invention provide systems and methods that help individuals target particular risk factor(s) to improve in order to avoid and/or cure themselves from OSA, and thus avoid or eliminate the need (over time) for PAP therapy.
Although the invention has been described in detail for the purpose of illustration based on what is currently considered to be the most practical and preferred embodiments, it is to be understood that such detail is solely for that purpose and that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present invention contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment.
In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word “comprising” or “including” does not exclude the presence of elements or steps other than those listed in a claim. In a device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The word “a” or “an” preceding an element does not exclude the presence of a plurality of such elements. In any device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The mere fact that certain elements are recited in mutually different dependent claims does not indicate that these elements cannot be used in combination.
This application claims the benefit of U.S. Provisional Application No. 63/054,197, filed on 20 Jul. 2020. This application is hereby incorporated by reference herein.
| Number | Date | Country | |
|---|---|---|---|
| 63054197 | Jul 2020 | US |
