Computer-implemented method, system, computer program product and non-transitory computer-readable medium

Abstract

The system and method provide patient data stored in a data repository, apply a first patient identification algorithm to the patient data to identify an initial population of individuals associated with selected physical and health characteristics, apply a second patient identification algorithm to the patient data associated with the initial population of individuals to identify narrower subpopulations associated with selected behavioral characteristics, and generate patient identifiable information from the patient data to enable notification. The identification of the initial population is based on a determined likelihood of obstructive sleep apnea (OSA) for individuals meeting or exceeding a first threshold criterion. The identification of the narrower population is based on a determined likelihood of long-term adherence to OSA treatment for individuals meeting or exceeding a second threshold criterion. The notification that one or more individuals in the narrower subpopulation are OSA-suitable individuals has a designated entity.

Description

[Technical Field]

[0001] The present disclosure relates generally to systems and methods for identifying individuals with certain physical and health characteristics indicative of obstructive sleep apnea, and specifically to systems and methods for further identifying individuals with behavioral characteristics indicative of long-term adherence to obstructive sleep apnea treatment. [Background technology]

[0002] Many individuals suffer from sleep-related and / or breathing-related disorders, such as sleep-disordered breathing (SDB), including periodic limb movement disorder (PLMD), restless legs syndrome (RLS), obstructive sleep apnea (OSA), central sleep apnea (CSA), other types of apnea, including mixed apneas and hypopneas, respiratory effort-related arousals (RERA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular diseases (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream actout (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disorders. These disorders are often treated using respiratory therapy systems. Summary of the Invention [Problem to be solved by the invention]

[0003] However, for some users, such systems are uncomfortable, difficult to use, expensive, aesthetically unpleasing, and / or the benefits associated with using the system are not recognized. As a result, some users never begin using a respiratory therapy system or discontinue use of the respiratory therapy system without evidence of the severity of their symptoms when respiratory therapy treatment is not being used. As a result, some users discontinue use of the respiratory therapy system without the encouragement and affirmation that the respiratory therapy system is improving their sleep quality and reducing the symptoms of these disorders. The present disclosure is directed to solutions to these and other problems. [Means for solving the problem]

[0004] According to some implementations of the present disclosure, a method includes providing patient data stored in a data repository. The patient data includes physical data, health data, and behavioral data corresponding to an identifiable individual. The method also includes applying a first patient identification algorithm to process at least a portion of the patient data to identify an initial population of individuals associated with selected physical and health characteristics. The identification of the initial population of individuals is based on a determined likelihood of obstructive sleep apnea for the identifiable individual meeting or exceeding a first threshold criterion. The method also includes applying a second patient identification algorithm to process at least a portion of the patient data associated with the initial population of individuals to identify narrower subpopulations of individuals associated with selected behavioral characteristics. The identification of the narrower subpopulations is based on a determined likelihood that individuals within the narrower subpopulation meeting or exceeding a second threshold criterion will adhere to obstructive sleep apnea treatment over time. Patient identifiable information is generated from the patient data to enable notification to one or more designated entities that one or more individuals within the narrower subpopulations are suitable for obstructive sleep apnea treatment.

[0005] According to some implementations of the present disclosure, a system includes a control system including one or more processors and a memory having machine-readable instructions stored therein, the control system being coupled to the memory, and the method being performed when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system.

[0006] According to some implementations of the present disclosure, a system identifies individuals who are likely to have an underlying sleep disorder and who are likely to adhere to a prescribed long-term treatment plan, the system including a control system configured to implement the method.

[0007] According to some implementations, a computer program product contains instructions that, when executed by a computer, cause the computer to perform a method.

[0008] According to some implementations, the computer program product is a non-transitory computer-readable medium. [Brief explanation of the drawings]

[0009] [Figure 1A] FIG. 1 is a functional block diagram of an exemplary system for analyzing data to identify individuals with sleep disorders and long-term trends in adopting a sleep disorder treatment plan, according to some implementations of the present disclosure. [Figure 1B] FIG. 1 is a functional block diagram of another exemplary system for analyzing data for the purpose of identifying individuals with sleep disorders and long-term trends in adopting a sleep disorder treatment plan, according to some implementations of the present disclosure. [Figure 2] FIG. 1 is a process flow diagram of an exemplary method for identifying individuals with sleep disorders and a longitudinal tendency to adopt a sleep disorder treatment plan, according to some implementations of the present disclosure. [Figure 3] FIG. 1 is a process flow diagram of an exemplary method for training an algorithm to identify individuals with sleep disorders and long-term trends in adopting a sleep disorder treatment plan, according to some implementations of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0010] The above summary is not intended to describe each implementation or every aspect of the present disclosure. Additional features and benefits of the present disclosure will be apparent from the following detailed description and drawings.

[0011] While the present disclosure is susceptible to various modifications and alternative forms, specific implementations and embodiments thereof have been shown by way of example in the drawings and are herein described in detail. It is to be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but rather, the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the disclosure as defined by the appended claims.

[0012] Many individuals suffer from sleep-related disorders and / or breathing disorders. Examples of sleep-related disorders and / or breathing disorders include sleep-disordered breathing (SDB), such as periodic limb movement disorder (PLMD), restless legs syndrome (RLS), obstructive sleep apnea (OSA), central sleep apnea (CSA), and other types of apnea, such as mixed apnea and hypopnea, respiratory effort-related arousals (RERA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream enactment (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disorders.

[0013] Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) characterized by events involving the obstruction or closure of the upper airway during sleep due to an abnormally small upper airway in combination with the normal loss of muscle tone in the areas of the tongue, soft palate, and posterior oropharyngeal wall. These disorders are characterized by specific events that occur during an individual's sleep (e.g., snoring, apnea, hypopnea, restless legs, sleep disturbances, choking, increased heart rate, labored breathing, asthma attacks, epileptic episodes, seizures, or any combination thereof).

[0014] When suffering from obstructive sleep apnea (OSA), a patient's breathing typically stops for periods of 30 to 120 seconds, sometimes 200 to 300 times per night. This often results in excessive daytime somnolence, which can lead to cardiovascular disease and brain damage. This syndrome is a common disorder, particularly among middle-aged, overweight men, but sufferers may not be aware of the problem. See U.S. Patent No. 4,944,310 (Sullivan).

[0015] Respiratory pressure therapy (RPT) devices can be used individually or as part of a system to deliver one or more of several therapies, such as by operating the device to generate an airflow for delivery to an interface to the airway. The airflow can be pressure-controlled (for respiratory pressure therapy) or flow-controlled (for flow therapy such as HFT). As such, RPT devices can also function as flow therapy devices. Examples of RPT devices include continuous positive airway pressure (CPAP) devices.

[0016] CPAP therapy has been used to treat obstructive sleep apnea (OSA). Its mechanism of action is that continuous positive airway pressure (CPAP) acts as a pneumatic splint, preventing upper airway closure by pushing the soft palate and tongue forward and backward toward the posterior oropharyngeal wall. CPAP therapy is highly effective in treating certain breathing disorders if patients comply with the therapy. Patients may not comply with therapy if the mask is uncomfortable or difficult to use. Because patients are often encouraged to clean their masks regularly, if the mask is difficult to clean (e.g., difficult to assemble or disassemble), patients may not wash the mask, which may affect patient compliance. Because OSA treatment with CPAP therapy can be voluntary, patients may choose not to comply if they perceive one or more of the following about the device used to deliver such therapy: discomfort, difficulty to use, high cost, and poor aesthetics.

[0017] Not all respiratory therapies aim to deliver a prescribed therapeutic pressure. Some respiratory therapies aim to deliver a prescribed respiratory volume, perhaps by targeting a flow profile for a target duration. In other cases, the interface to the patient's airway is "open" (unsealed), and respiratory therapy may supplement only the patient's spontaneous breathing. In one example, high-flow therapy (HFT) provides a continuous, heated, humidified airflow to the entrance to the airway through an unsealed or open patient interface at a "therapeutic flow" that remains nearly constant throughout the respiratory cycle. The therapeutic flow is nominally set to exceed the patient's peak inspiratory flow. HFT has been used to treat OSA, CSR, COPD, and other respiratory disorders. One mechanism of action is that a high flow of air at the airway entrance improves ventilatory efficiency by flushing or sweeping exhaled CO2 from the patient's anatomical dead space. Therefore, HFT is sometimes referred to as dead-space therapy (DST). In other flow therapies, the therapeutic flow rate may follow a profile that varies over the respiratory cycle.

[0018] A wide variety of individual physical and health characteristics can be caused by or impacted by OSA. For example, physical characteristics that directly or indirectly cause or impact OSA can include an individual's neck circumference, weight, gender, blood pressure, age, body mass index, and other characteristics. Health characteristics that directly or indirectly cause or impact OSA can include a history of snoring, heart disease, fatigue history, observed apnea, diabetes, and other characteristics. Furthermore, specific behavioral characteristics of individuals who have or are likely to have OSA and who are likely to follow a long-term OSA treatment plan can include the individual's demographic information, such as education, employment, place of residence, marital status, etc. Further behavioral characteristics of individuals who have or are likely to have OSA and who are likely to follow a long-term OSA treatment plan can include the individual's motivation, fitness level, exercise habits, adherence to prescribed medication protocols, adherence to previous physician recommendations, and other characteristics.

[0019] Data associated with an individual's physical, health, and behavioral characteristics can be collected by various sources and stored as historical patient data, which may be part of a medical record. Data can be collected by a healthcare provider during a patient visit and stored, for example, in a care management platform. Data can also be collected by integrated delivery networks, health management systems, healthcare payers, and other administrators. In some cases, data can be provided directly or indirectly by the patient. In some cases, data can be collected by a physician or other healthcare professional. In still other cases, data such as behavioral information can be collected from third-party sources to the extent that it can be attributed to an individual's behavioral, physical, and health characteristic data. All of this data can be stored in a data repository. A desirable implementation of the disclosed system and method is to identify individuals from the data repository who have specific physical and health characteristics suggestive of obstructive sleep apnea, and further identify individuals who have specific behavioral characteristics suggestive of long-term adherence to OSA treatment.

[0020] OSA significantly impacts the quality of life of individuals with OSA and is a contributing factor to many other medical problems that increase long-term costs for healthcare providers and payers. If a patient with a medical problem is determined to have OSA, treating the OSA disease can minimize or even eliminate the medical problem. This can be desirable because it minimizes long-term medical costs and improves the individual's quality of life, especially if OSA is treated early. While OSA has many positive benefits, not all individuals prescribed an OSA treatment plan adhere to the treatment over the long term, which can reduce the benefits of treatment. A desirable aspect of the present disclosure is to identify individuals from a repository of historical patient data who are likely to adhere to an OSA treatment plan, initially identified as likely to have OSA based on the individuals' physical and health characteristic data.

[0021] A system is contemplated that receives data from or has access to a database, such as a database of patient health records, and uses a first trained algorithm to identify current patients who are likely to have OSA to generate an initial population of individuals. Some or all of the data for each individual in the initial population is then processed by a second trained algorithm to identify current patients who are likely to adopt and / or adhere to OSA treatment therapies (e.g., CPAP, mandibular repositioning devices, stimulation therapy, lifestyle changes) over the long term to generate subpopulations of the initial population of individuals. In some embodiments, the subpopulations are a primary output of the contemplated system and may have patient-identifiable information associated with each individual in the subpopulation. The subpopulations can then inform healthcare providers, healthcare payers, or individuals that they are candidates for counseling regarding OSA treatment and the expected benefits of minimizing long-term healthcare costs and improving quality of life.

[0022] 1A and 1B, the system 100, 100′ includes a data repository 200, 200′, a memory 300, 300′, a control system 400, 400′, and one or more terminal devices 500, 500′ (hereinafter terminal devices 500, 500′). As described herein, the system 100, 100′ can generally be used to identify individuals (e.g., patients of a healthcare provider) who are likely to have an underlying sleep disorder (e.g., obstructive sleep apnea) and who are likely to adhere to a long-term treatment plan prescribed (e.g., by a physician or other prescriber).

[0023] Although systems 100, 100' are shown as including various elements, systems 100, 100' may include any portion and / or subset of the elements shown and described herein, and / or systems 100, 100' may include one or more additional elements not specifically shown in FIG. 1A or 1B. Data repositories 200, 200' are communicatively coupled to respective networks 250, 250'. In some implementations, data repositories 200, 200' are communicatively connected to respective control systems 400, 400' and / or to one or more respective terminal devices 500, 500' via respective networks 250, 250' or via another network 255, 255'.

[0024] Data repositories 200, 200′ include multiple storage devices for storing patient or patient-attributable data. In some implementations of the present disclosure, data repositories 200 and 200′ may include electronic health data records for individuals and may have physical characteristic data 210 (or 210′ ​​in FIG. 1B ) for multiple individuals, along with health characteristic data 220 (or 220′ in FIG. 1B ) and behavioral characteristic data 230 (or 230′ in FIG. 1B ). Although data repositories 200 and 200′ (FIG. 1B ) are shown as including various storage devices, data repositories 200 and 210′ ​​may include any subset of the elements shown and described herein, and / or data repositories 200 and 210′ ​​may include one or more additional elements not specifically shown in FIG. 1

[0025] The data stored in data repository 200 or 200′ (FIG. 1B) may include a wide variety of types and / or contents of data. For example, in some implementations, the data stored in data repository 200 or 200′ includes physical characteristic data that directly or indirectly contributes to or contributes to OSA, such as neck circumference, weight, gender, blood pressure, age, and / or body mass index. In another example, the data includes health characteristic data that directly or indirectly contributes to or contributes to OSA, such as snoring history, cardiac disease, fatigue history, observed apnea, and / or diabetes. In another example, the data includes certain behavioral characteristics of individuals who have or are likely to have OSA and are likely to follow a long-term treatment plan for OSA, e.g., demographic information such as education, employment, location of residence, marital status, and / or health care payer information. In some implementations, the data includes additional behavioral characteristic data of individuals who have or are likely to have OSA and are likely to follow a long-term treatment plan for OSA, such as motivation, fitness level, exercise habits, adherence to prescribed medication protocols, and / or adherence to previous physician recommendations. The data stored in data repository 200 or 200′ includes historical patient data, such as physical characteristic data, health characteristic data, and behavioral characteristic data corresponding to identifiable individuals (e.g., current or former patients).

[0026] Additional data stored in data repository 200 or 200′ corresponding to the identifiable individual is further detailed. As another example, in some implementations, the data includes adherence data associated with multiple individuals similar to the individual. As another example, in some implementations, the data includes a determination of whether the individual experiences dyspnea during sleep. As another example, in some implementations, the data includes relationship information for the individual. As another example, in some implementations, the data includes web searches performed by the individual. As another example, in some implementations, the data includes a determination of whether the individual is likely to exhibit binge eating behavior, a determination of whether the individual is likely to change behavior, or both. As another example, in some implementations, the data includes a summary of at least a portion of a past description of clinical behaviors changed by the individual. As another example, in some implementations, the data includes one or more daily health assessments including the occurrence and / or frequency of headaches and / or migraines experienced by the individual. As another example, in some implementations, the data includes dependent information for the individual. As another example, in some implementations, the data includes the individual's subscription to a mobile or web-based health application, social media information associated with the individual, or any combination thereof. As another example, in some implementations, the data includes determining the individual's propensity to be an early adopter of technology. As another example, in some implementations, the data includes information associated with whether the individual is a substance user, information associated with whether the individual consumes alcohol, or any combination thereof. As another example, in some implementations, the data includes information such as age, gender, BMI, health information, whether the individual is a smoker or non-smoker, whether the individual drinks alcohol, or any combination thereof. As another example, in some implementations, the data includes information such as self-reported pain points such as daytime sleepiness, snoring, fatigue, exercise level (duration, intensity, type), difficulty maintaining sleep, or any combination thereof.It is understood that the data stored in data repository 200 or 210' may include any combination of the above types of data and / or other types of data not specifically described herein.

[0027] In some implementations, the control system 400 (or 400′ of FIG. 1B ) executes machine-readable instructions (stored in the respective memory 300 of FIG. 1A or 300′ of FIG. 1B , or a different memory, or both) to apply a first patient identification algorithm and process at least a portion of the patient data to identify an initial population of individuals associated with selected physical and health characteristics. The identification of the initial population of individuals is based on a likelihood of obstructive sleep apnea for identifiable individuals meeting or exceeding a first threshold criterion or a predetermined threshold. The control system 400 or 400′ further executes machine-readable instructions (stored in the respective memory 300 or 300′, or a different memory, or both) to apply a second patient identification algorithm and process at least a portion of the patient data associated with the initial population of individuals to identify narrower subpopulations of individuals associated with selected behavioral characteristics. The identification of the narrow population of individuals is based on a determined likelihood that individuals within the narrow subpopulation who meet or exceed a second threshold criterion or a predetermined threshold will adhere to obstructive sleep apnea treatment over time. Finally, the control system 400 or 400′ executes machine-readable instructions (stored in the respective memory 300 or 300′, a different memory, or both) to generate patient-identifiable information from the patient data and notify one or more designated entities that one or more of the individuals within the narrow subpopulation are suitable individuals for obstructive sleep apnea treatment. In some implementations, the patient-identification algorithm can be a machine learning algorithm. In some implementations, the patient-identification algorithm can be a pre-programmed algorithm. In some implementations, the pre-programmed algorithm can be updated at predetermined intervals desired by the user.

[0028] In some implementations, the data stored in the data repository 200 or 200′ may include training data (e.g., historical, real-time) associated with multiple individuals. In some such implementations, the control system 400 or 400′ executes machine-readable instructions (stored in the respective memory 300 or 300′, or a different memory, or both) to train the machine-learning patient identification algorithm(s) 330 of FIG. 1A or 330′ of FIG. 1B (stored in the memory 300 or 300′, or a different memory, or both) with the training data. Using the training data, the machine-learning patient identification algorithm(s) 330 or 330′ is configured to receive as input at least a portion of the data stored in the data repository 200 or 200′ associated with identifiable individuals.

[0029] One or more terminal devices 500 of FIG. 1A or 500′ of FIG. 1B can be associated with an individual, a healthcare provider, an integrated delivery network, a healthcare payer, an administrator, or another designated entity. In some implementations, terminal device 500 (or 500′) is configured to receive one or more notifications from control system 400 or 400′. In some implementations, the notification includes that one or more of the individuals within a narrow subpopulation as identified by a patient identification algorithm are suitable for OSA treatment (e.g., likely to adhere to long-term treatment). One or more terminal devices 500 or 500′ can include a personal computer 510 (or 510′ of FIG. 1B), a mobile device 520 (or 520′ of FIG. 1B), or any combination thereof. In some implementations, the terminal device 500 or 500′ can communicate data to and / or receive data from the data repository 200 or 200′, such as patient data, which may be transmitted to the data repository, whether that data is part of a medical record or is data received directly from an individual (e.g., a patient).

[0030] In some implementations, memory 300 or 300′ stores machine-readable instructions 320 or 320′ and first and second patient-identification algorithms. Control system 400 or 400′ is communicatively coupled to respective memory 300 or 300′ and includes one or more processors 410 or 410′. Control system 400 is generally used to control (e.g., operate) various components of system 100 and / or analyze data acquired and / or generated by components of system 100. Control system 400′ is likewise used to control (e.g., operate) various components of system 100′ and / or analyze data acquired and / or generated outside the system by components 200′ and / or 500′. The processor 410 (or 410′ in FIG. 1B) executes the respective machine-readable instructions 320 (or 320′ in FIG. 1B) stored in the respective memory device 300 or 300′ and may be a general-purpose or special-purpose processor or microprocessor.

[0031] Although one processor 410 is shown in FIG. 1A and one processor is shown in FIG. 1B, each control system 400 or 400′ may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.). Each memory 300 or 300′ may be any suitable computer-readable storage device or medium, such as, for example, a random or serial access memory device, a hard drive, a solid-state drive, a flash memory device, etc. The control system 400 and / or memory 300 may be coupled to and / or located within one or more housings of the terminal device 500. The control system 400 and / or memory 300 may be centralized (within one housing) or distributed (within two or more physically separate housings). The control system 400′ and / or memory 300′ may be centralized (within one housing) or distributed (within two or more physically separate housings).

[0032] In some implementations of the present disclosure, processor 410 (or 410′ in FIG. 1B ) is configured to execute machine-readable instructions 320 (or 320′ in FIG. 1B ) to receive at least a portion of data stored in data repository 200 or 200′ (FIG. 1B ). In some such implementations, the received portion of the data corresponds to identifiable individuals. First and second patient identification algorithms in memory 300 or 300′ (FIG. 1B ) process the received data, or portions thereof, to determine identifiable individuals suitable for OSA treatment (e.g., likely to adhere to treatment over time).

[0033] In some implementations, the determined likelihood of obstructive sleep apnea for individuals identified within the initial population of individuals includes individuals for whom a first threshold criterion (e.g., greater than 95% likelihood of OSA, greater than 90% likelihood of OSA, greater than 80% likelihood of OSA, greater than 70% likelihood of OSA, greater than 60% likelihood of OSA) is met or exceeded. In some implementations, the determined likelihood of an individual's long-term adherence to OSA treatment (for inclusion in a narrower subpopulation of individuals) includes individuals associated with data that meets or exceeds a second threshold criterion (e.g., greater than 95% likelihood of adherence, greater than 90% likelihood of adherence, greater than 80% likelihood of adherence, greater than 70% likelihood of adherence, greater than 60% likelihood of adherence).

[0034] In some implementations, the processor 410 or 410′ executes the machine-readable instructions 320 or 320′ to generate personalized treatment pathway(s) targeted to one or more individuals within a narrow subpopulation of individuals suitable for OSA treatment, the personalized treatment pathway(s) being based on physical, health, and / or behavioral characteristic data corresponding to each of the one or more individuals within the narrow subpopulation.

[0035] It is contemplated that the systems described herein include identifying, via an algorithm-driven module, patients with a threshold likelihood of having OSA and a threshold likelihood of adherence to OSA treatment over time. The described systems and methods are desirable in that they can review historical patient data to identify a healthcare provider's (e.g., cardiologists, endocrinologists, family physicians) previous patients and, based on the data, identify individuals among those previous patients who are likely to have OSA and who are likely to adhere to a treatment plan.

[0036] In some implementations, the system and method can further guide the provider toward a desired treatment pathway that will likely be successful for the identified patient. In the example of a cardiology provider, past patients with cardiac problems or on a pathway to cardiac problems may be identified by the system as having a high likelihood of OSA contributing to the cardiac problem. If the identified patient also has behavioral characteristics suggesting a likelihood of adherence to treatment for OSA, the patient information may be sent to a healthcare provider, healthcare payer, or integrated delivery network to enable this designated entity to consult with the past patient.

[0037] Referring now to FIG. 2, a process flow diagram of a method for identifying individuals with sleep disorders and those with a long-term tendency to adopt a treatment plan is depicted. At step 600, stored or retrieved patient data is provided. The patient data includes physical, health, and behavioral characteristic data corresponding to identifiable individuals. At step 610, a first patient identification algorithm is applied to process at least a portion of the patient data to identify an initial population of individuals associated with selected physical and health characteristics. The physical and health characteristics may be derived from the physical characteristic data 613 and the health characteristic data 616. The identification of the initial population of individuals is based on a likelihood of obstructive sleep apnea for the identifiable individuals meeting or exceeding a first threshold criterion. At step 620, a second patient identification algorithm is applied to process at least a portion of the patient data associated with the initial population of individuals to identify a narrower subpopulation of individuals associated with selected behavioral characteristics. The behavioral characteristics may be derived from the behavioral characteristic data 623. The identification of the narrow population of individuals is based on a determined likelihood that individuals within the narrow subpopulation who meet or exceed a second threshold criterion will adhere to the obstructive sleep apnea treatment over time. In step 630, patient identifiable information is generated from the patient data to enable notifying one or more designated entities that one or more of the individuals within the narrow subpopulation are suitable individuals for obstructive sleep apnea treatment.

[0038] In some implementations, one or more designated entities may be notified and may include at least one of a healthcare provider, an integrated delivery network, a healthcare payer, an administrator, one or more individuals, or any combination thereof.

[0039] In some implementations, a personalized treatment pathway is generated for one or more identified individuals based at least in part on the physical, health, and behavioral data corresponding to each of the one or more individuals within the narrow subpopulation of individuals. For example, the personalized treatment pathway may include identifying a sleep testing method suitable for the identified individuals or analyzing health outcomes that would be improved by treating OSA. Improved health outcomes may include reduced mortality, rehospitalization, hospital stay, or any combination thereof. Other improved health outcomes may include improved clinical, financial, and patient experience. The generated personalized treatment pathway may be sent to the corresponding individuals, healthcare providers, other designated entities, or any combination thereof.

[0040] In some implementations, the notification may include an analysis of potential medical cost savings from treating potential obstructive sleep apnea.

[0041] In some implementations, an alert is sent directly to the corresponding individual to inquire about a sleep study with that individual's healthcare provider.

[0042] In some implementations, the generated patient identifiable information may be provided on a network server that is accessible to third parties.

[0043] In some implementations, the data repository may include data associated with the care management platform, the health management system, or both. In some implementations, the patient data includes historical patient data.

[0044] In some implementations, one or more of the selected physical and health characteristics include information provided by an identifiable individual. In some implementations, the selected health, behavioral, or demographic information is data entered by a healthcare provider during one or more prior encounters with the patient.

[0045] In some implementations, the notification to the identified individual includes a direct message or email message delivered through the health portal. In some implementations, the notification to a healthcare provider or administrator associated with the identified individual includes an indication of the communication method most likely to result in patient follow-up. In some implementations, the communication method includes one of a text message, an email, a call, or an invitation to schedule a visit. In some implementations, the communication method may further include the delivery of the text message, email, call, or invitation to schedule a visit being initiated by one of an administrator, a nurse, or a doctor.

[0046] In some implementations, a list of individuals identified within a narrow subpopulation of individuals is generated to direct proactive outreach.

[0047] In some implementations, the systems and methods include identifying missing patient data that will increase the accuracy of identifying individuals for targeted follow-up.

[0048] Referring now to FIG. 3 , a process flow diagram of an exemplary method for training an algorithm to identify individuals with a sleep disorder and a long-term tendency to adopt a treatment plan is depicted. At step 700, patient data is received and may include physical characteristic data 703, health characteristic data 706, and / or behavioral characteristic data 709. At step 710, a first threshold value for identifiable individuals within the training patient data is determined or received and may include patient data associated with individuals known to have OSA. Next, at step 720, a first patient identification algorithm can be trained to identify individuals based on the decision threshold value for having an OSA likelihood. Similarly, at step 715, a second threshold value for identifiable individuals within the training patient data is determined or received and may include patient data associated with individuals known to be long-term adherent to OSA treatment. Next, at step 720, a second patient identification algorithm can be trained to identify individuals based on the decision threshold value for long-term adherence to OSA treatment.

[0049] One or more elements or aspects or steps or any portion(s) thereof from any one or more of claims 1 to 29 below may be combined with one or more elements or aspects or steps or any portion(s) thereof from any one or more of the other claims 1 to 29 or combinations thereof to form one or more further implementations and / or claims of the present disclosure.

[0050] Although the present disclosure has been described with reference to one or more particular embodiments or implementations, those skilled in the art will recognize that numerous modifications may be made thereto without departing from the spirit and scope of the present disclosure. Each of these implementations and obvious variations thereof is contemplated as falling within the spirit and scope of the present disclosure. It is also contemplated that further implementations according to aspects of the present disclosure may combine any number of features from any of the implementations described herein.

[0051] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to and benefit of U.S. Provisional Patent Application No. 63 / 045,397, filed June 29, 2020, the disclosure of which is incorporated herein by reference in its entirety.

Claims

1. providing patient data stored in a data repository, the patient data including physical data, health data, and behavioral data corresponding to an identifiable individual; applying a first patient identification algorithm to process at least a portion of the patient data to identify an initial population of individuals associated with selected physical and health characteristics, wherein the identification of the initial population of individuals is based on a determined likelihood of obstructive sleep apnea for identifiable individuals meeting or exceeding a first threshold criterion; applying a second patient identification algorithm to process at least a portion of the patient data associated with the first population of individuals to identify narrower sub-populations of individuals associated with selected behavioral characteristics, wherein the identification of the narrower sub-populations of individuals is based on a determined likelihood that individuals within the narrower sub-populations of individuals who meet or exceed a second threshold criterion will be adherent to obstructive sleep apnea treatment over time; generating patient identifiable information from the patient data to enable one or more designated entities to be notified that one or more of the individuals within the narrow subpopulation of individuals are individuals likely to be long-term adherent to obstructive sleep apnea treatment; sending a notification to the one or more designated entities through a health portal using the patient identifiable information of the likely individual; A computer-implemented method comprising:

2. 10. The method of claim 1, wherein the one or more designated entities include a healthcare provider, an integrated delivery network, a healthcare payer, an administrator, at least one of the one or more individuals, or any combination thereof.

3. 3. The method of claim 1 or claim 2, further comprising generating a personalized treatment pathway for the one or more individuals based at least in part on the physical data, health data, and behavioral data corresponding to each of the one or more individuals within the narrow subpopulation of individuals.

4. The method of claim 3 , further comprising transmitting the personalized care pathway to a corresponding individual, a healthcare provider, other designated entity, or any combination thereof.

5. 5. The method of claim 3 or claim 4, wherein the notification includes an analysis of potential medical cost savings from treating potential obstructive sleep apnea.

6. 5. The method of claim 3 or claim 4, wherein the personalized treatment pathway further comprises an analysis of health outcomes that are improved by treating obstructive sleep apnea.

7. 7. The method of claim 6, wherein the improved health outcome comprises a reduction in mortality, rehospitalization, length of stay in hospital, or any combination thereof.

8. 8. The method of claim 3, further comprising sending an alert directly to a corresponding individual to inquire about the sleep study with the individual's healthcare provider.

9. 9. The method of any one of claims 3 to 8, wherein the personalized treatment pathway includes a recommended sleep study regimen.

10. 10. The method of any one of claims 1 to 9, further comprising providing the patient identifiable information on a network server accessible to a third party.

11. The method of claim 1 , wherein the data repository includes data associated with a care management platform, a health management system, or both.

12. The method of claim 1 , wherein the patient data includes historical patient data.

13. 13. The method of any one of claims 1 to 12, wherein one or more of the selected physical and health characteristics are indirectly caused by or exacerbated by obstructive sleep apnea.

14. The method of any one of claims 1 to 13, wherein the selected physical characteristics include neck circumference, weight, gender, blood pressure, age, body mass index, or any combination thereof.

15. The method of claim 1 , wherein one or more of the selected physical and health characteristics comprises information provided by the identifiable individual.

16. 16. The method of claim 1, wherein the selected health characteristics include a history of snoring, a heart condition, a history of fatigue, observed apnea, diabetes, or any combination thereof. How to do it.

17. The method of claim 1 , wherein the behavioral characteristics include demographic information.

18. 18. The method of claim 17, wherein the demographic information includes education, employment, location of residence, marital status, or any combination thereof.

19. 19. The method of claim 17 or claim 18, wherein the behavioral characteristics include motivation, fitness level, exercise habits, adherence to prescribed medication protocols, adherence to previous physician recommendations, or any combination thereof.

20. 20. The method of any one of claims 17 to 19, wherein any of the health characteristics, behavioral characteristics, or demographic information is data entered into the data repository by a healthcare provider during one or more previous encounters with the patient.

21. The notice: transmitted to a terminal device of an identified individual among the likely individuals; 21. The method of any one of claims 1 to 20, comprising a direct message or an email message.

22. The notice: transmitted to another terminal device of a healthcare provider or administrator associated with the identified individual; 22. The method of claim 21, including identifying communication methods most likely to result in patient follow-up.

23. 23. The method of claim 22, wherein the communication method comprises one of a text message, an email, a phone call, or an invitation to schedule a visit.

24. 24. The method of claim 23, wherein the communication method further comprises: the delivery of the text message, email, call, or invitation to schedule a visit being initiated by one of an administrator, a nurse, or a doctor.

25. 24. The method of any one of claims 1 to 23, further comprising generating a list of individuals identified within the narrow subpopulation of individuals to direct proactive outreach.

26. a control system including one or more processors; a memory having machine-readable instructions stored therein; 26. A system, wherein the control system is coupled to the memory and configured to implement the method of any one of claims 1 to 25 by executing the machine-readable instructions in the memory using at least one of one or more processors of the control system.

27. 26. A system for identifying individuals who are likely to have an underlying sleep disorder and who are likely to adhere to a prescribed long-term treatment plan, the system comprising a control system configured to implement the method of any one of claims 1 to 25.

28. When executed by a computer, the method according to any one of claims 1 to 25 A computer program comprising instructions for causing said computer to carry out the method described above.

29. A non-transitory computer readable medium having recorded thereon a computer program comprising instructions which, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 25.

Images