Systems, devices, and methods for evaluating and predicting sleep-related disorders

Abstract

Devices, systems, and methods herein relate to evaluating and predicting sleep-related disorders. In some variations, a method of graphically representing health of a user may include the steps of: outputting, using a computing device, a notification for a user to input a sleep score, a physical health score, and a mental health score; and generating a user health graph on a graphical user interface of the computing device. For example, a plurality of shapes including respective colors may be generated based on respective sleep scores, physical health scores, and mental health scores. Positions of the plurality of shapes relative to a first longitudinal axis of the user health graph may be arranged based on a sleep score, a physical health score, and a mental health score.

Description

[0001] Cross-reference to related applications This application claims the benefits of U.S. Provisional Application No. 63 / 454,599, filed March 24, 2023, and U.S. Provisional Application No. 63 / 543,888, filed October 12, 2023, the contents of each of which are incorporated herein by reference in their entirety. Technical Field

[0002] The apparatus, systems, and methods described herein relate to the remote evaluation and prediction of medical conditions, including but not limited to sleep-related disorders. Background Technology

[0003] Millions of people suffer from chronic medical conditions, including sleep-related disorders such as sleep apnea, orthopnea, and insomnia. The direct cost of chronic medical conditions to the U.S. healthcare system is approximately $7,000 per person per condition annually, with sleep disorders alone accounting for roughly $7,000 per person per year. About 47% of all insured Americans have multiple chronic medical conditions. Therefore, it may be desirable to provide novel and useful methods for monitoring and proactively addressing chronic medical conditions. Summary of the Invention

[0004] This paper describes systems, devices, and methods for remotely assessing and predicting medical conditions such as sleep-related disorders. These systems and methods may, for example, receive user input data and sleep measurement data, and analyze the received data to identify trends and / or the risk of sleep disorders. In some variations, user health graphs can be generated on a graphical user interface based on user data, thus graphically representing user health. For example, this could allow for insights into user health and well-being on a continuous or semi-continuous, real-time basis.

[0005] In some variations, a method for graphically representing a user's health may include using a computing device to output a notification for the user to input sleep scores, physical health scores, and mental health scores, and generating a user health graph on a graphical user interface of the computing device. This generation may include generating a first shape including a first color based on the sleep score, a second shape including a second color based on the physical health score, and a third shape including a third color based on the mental health score, and arranging the positions of the first, second, and third shapes relative to a first axis of the user health graph based on the sleep score, physical health score, and mental health score.

[0006] In some variations, the first axis may be the vertical axis of the user health graph. In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. The first center, the second center, and the third center may be located on the first axis.

[0007] In some variations, the first shape can include a first center, the second shape can include a second center, and the third shape can include a third center, and two of the first, second, and third centers can be located on the first axis, and a third of the first, second, and third centers can be offset relative to the first axis.

[0008] In some variations, the first shape can include a first center, the second shape can include a second center, and the third shape can include a third center, and one of the first, second, and third centers can be located on the first axis, and the other two of the first, second, and third centers can be offset relative to the first axis and on opposite sides of the first axis. In some variations, the first axis can be an angled axis between a vertical axis of the user health graph and a horizontal axis of the user health graph. In some variations, a center-to-center distance between the first shape and the second shape can be based on a difference between two of the sleep score, the physical health score, and the mental health score.

[0009] In some variations, centers of two or more of the first shape, the second shape, and the third shape can be spaced apart from each other along the first axis. In some variations, centers of two or more of the first shape, the second shape, and the third shape can be offset relative to each other with respect to the first axis. In some variations, the first shape can include a first center, the second shape can include a second center, and the third shape can include a third center, and the first, second, and third centers can be laterally offset from each other. In some variations, the first shape, the second shape, and the third shape can partially overlap along the first axis. In some variations, the first shape can include a first center, the second shape can include a second center, and the third shape can include a third center, and the first, second, and third centers can be spaced apart from each other along the first axis at equal center-to-center distances.

[0010] In some variations, generating the user health graph can include generating a plurality of lines, where each line of the plurality of lines overlaps with two of the first shape, the second shape, and the third shape. In some variations, the plurality of lines can include a first line between the center of the first shape and the center of the second shape, and a second line between the center of the second shape and the center of the third shape.

[0011] In some variations, the sleep score, the physical health score, and the mental health score can each correspond to a predetermined scale. In some variations, the predetermined scale can be a Likert scale.

[0012] In some variations, each of the first shape, the second shape, and the third shape can include a two-dimensional geometric shape. In some variations, each of the first color, the second color, and the third color can include a color gradient. In some variations, each of the first color, the second color, and the third color can include an opacity gradient. In some variations, the background of the graphical user interface can include a color gradient.

[0013] In some variations, the method can further include periodically updating the user health graph. In some variations, the method can further include generating an animation including the updated user health graph and one or more previous user health graphs. In some variations, the notification can be output at a predetermined interval.

[0014] In some variations, the method can further include modifying a computing device setting based on the user health graph. In some variations, the method can further include referring a sleep service to the user based on the user health graph.

[0015] Methods of predicting sleep disorders are also described herein. In some variations, a method of predicting sleep disorders can include receiving user data including a sleep score, a physical health score, and a mental health score from a computing device and receiving sleep measurement data from a measurement device; predicting a risk of one or more sleep disorders based on the user data and the sleep measurement data; and referring a sleep service to the user based on the predicted risk of the one or more sleep disorders.

[0016] In some variations, the method can further include outputting, using the computing device, a notification for input user data. In some variations, the sleep measurement data can include one or more sleep parameters. In some variations, the one or more sleep parameters can include one or more of a sleep start time, a sleep end time, a sleep duration, a sleep onset time, a number of awakenings, a wake period duration, a snoring status, a snoring duration, an exercise duration, an exercise end time, a number of alcoholic beverages consumed, a time of last alcoholic beverage consumed, a number of caffeinated beverages consumed, a time of last caffeinated beverage consumed, a daytime sleepiness status, a daytime sleepiness severity, an average sleep oxygen saturation, an average sleep heart rate variability, a minimum sleep heart rate, a maximum sleep heart rate, an average sleep heart rate, a set of medications taken, and user demographic data. In some variations, the one or more sleep parameters can further include a user wake time record and a user bedtime record. In some variations, the user demographic data can include one or more of a medical history and test results.

[0017] In some variations, the sleep score, the physical health score, and the mental health score can each correspond to a predetermined scale. In some variations, the predetermined scale can be a Likert scale. In some variations, the sleep score can include a sleep quality state, the physical health score can include a physical state, and the mental health score can include an emotional state. In some variations, the sleep quality state can include a reason for waking. In some variations, the physical state can include a physical ailment type, a physical ailment location, and a physical ailment intensity. In some variations, the emotional state can include a wake-up time emotion and a bedtime time emotion.

[0018] In some variations, the method can further include generating sleep data based on the user data and the sleep measurement data. In some variations, generating the sleep data can include coordinating the user data and the sleep measurement data. In some variations, the method can further include generating one or more sleep trends by analyzing the sleep data. In some variations, the risk of one or more sleep disorders can be based on the one or more sleep trends.

[0019] In some variations, the method can further include generating a graphical user interface including one or more of the sleep trends and the sleep disorder risk. In some variations, the method can further include modifying a computing device setting based on one or more of the sleep trends and the sleep disorder risk. In some variations, the sleep service referral can be based on one or more of the sleep trends and the sleep disorder risk. In some variations, the user data and the sleep measurement data can be received at a predetermined interval.

[0020] In some variations, the predetermined interval can be at least once per day. In some variations, the predetermined interval can be at a wake-up time and a bedtime. In some variations, the sleep disorder can include one or more of: obstructive sleep apnea, central sleep apnea, hypopnea, orthopnea, nocturnal atrial fibrillation, nocturnal hypertension, nocturnal discomfort, chronic obstructive pulmonary disease that worsens at night, heart failure, asthma, sleep quality, and wake-up discomfort.

[0021] This document also describes a method for graphically representing user health, which may include: receiving user data including a sleep score, multiple physical health parameters, and a mental health score from a computing device, and receiving sleep measurement data from a measuring device. A sleep quality score may be generated based on the sleep score and sleep measurement data, a physical health quality score may be generated based on the multiple physical health parameters, and a mental health quality score may be generated based on the mental health score. The user health graph may be generated on a graphical user interface of the computing device and may include generating a first shape based on the sleep quality score, a second shape based on the physical health quality score, and a third shape based on the mental health quality score. The positions of the first, second, and third shapes may be arranged relative to a first axis of the user health graph based on the sleep quality score, physical health quality score, and mental health quality score.

[0022] In some variations, the method may also include periodically generating sleep quality scores, physical health quality scores, and mental health quality scores. In some variations, sleep measurement data may include one or more of the following: sleep duration, sleep efficiency, sleep latency, number of awakenings, wakefulness time, and sleep quality. In some variations, the sleep quality score may be based on a weighted sum of the sleep score and sleep measurement data. In some variations, the weighting may be time-based.

[0023] In some variations, the multiple health parameters may include one or more of the following: health score, number of discomforts, maximum number of discomforts, and average severity of discomforts. In some variations, the health quality score may be based on a weighted sum of the multiple health parameters. In some variations, the weighting may be time-based. In some variations, each of the multiple health parameters may correspond to a pre-defined scale. In some variations, the pre-defined scale may be a Likert scale.

[0024] In some variations, generating a user health graph may include alphanumeric representations of sleep quality scores, physical health quality scores, and mental health quality scores. In some variations, user data and sleep measurements may be received at predetermined intervals. In some variations, the predetermined intervals may be at least once a day.

[0025] In some variations, the first axis may be the vertical axis of the user health graph. In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center, wherein the first center, the second center, and the third center may be located on the first axis. In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. Two of the first center, the second center, and the third center may be located on the first axis, and the third center may be offset relative to the first axis.

[0026] In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. One of the first, second, and third centers may be located on the first axis, and the other two of the first, second, and third centers may be offset relative to the first axis and located on opposite sides of the first axis.

[0027] In some variations, the first axis can be an angled axis between the vertical and horizontal axes of the user health graph. In some variations, the center-to-center distance between the first and second shapes can be based on the difference between two of the sleep score, physical health score, and mental health score.

[0028] In some variations, the centers of two or more of the first, second, and third shapes may be spaced apart from each other along the first axis. In some variations, the centers of two or more of the first, second, and third shapes may be offset from each other relative to the first axis.

[0029] In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. The first, second, and third centers may be laterally offset from each other. In some variations, the first, second, and third shapes may partially overlap along a first axis. In some variations, the first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. The first, second, and third centers may be spaced apart along the first axis at equal center-to-center distances.

[0030] In some variations, generating a user health graphic may include generating multiple lines. Each of these lines may overlap with two of the first, second, and third shapes. In some variations, the multiple lines may include a first line between the center of the first shape and the center of the second shape, and a second line between the center of the second shape and the center of the third shape. In some variations, each of the first, second, and third shapes may include a two-dimensional geometry. In some variations, each of the first, second, and third colors may include a color gradient. In some variations, each of the first, second, and third colors may include an opacity gradient.

[0031] In some variations, the background of the graphical user interface may include a color gradient. In some variations, the method may also include periodically updating the user health graph. In some variations, an animation may be generated that includes the updated user health graph and one or more previous user health graphs. In some variations, a computing device may be used to output notifications based on input user data. Notifications may be output at predetermined intervals.

[0032] In some variations, the method may also include modifying computing device settings based on the user's health graph. In some variations, the method may also include referring a user to a sleep service based on their health graph. Attached Figure Description

[0033] This patent or application document contains at least one color drawing. Upon request and payment of the necessary fees, the Patent Office will provide a published copy of this patent or application with the color drawing.

[0034] FIG. 1 This is a block diagram of a variant of a sleep assessment system.

[0035] FIG. 2 It is a block diagram of a variant of a computing device.

[0036] FIG. 3A This is an illustrative flowchart of a variation of the sleep disorder prediction process. FIG. 3B This is an illustrative flowchart of a variation of the first evaluation process. FIG. 3C This is an illustrative flowchart of a variation of the second evaluation process.

[0037] FIG. 4 It is an exemplary flowchart of a variation used to graphically represent a user's health status.

[0038] FIG. 5A to FIG. 5D It is a set of exemplary variants of the wake-up time graphical user interface.

[0039] FIG. 6A to FIG. 6D It is a set of exemplary variations of the graphical user interface for objective sleep data.

[0040] FIG. 7A to FIG. 7H It is a set of exemplary variations of the graphical user interface for subjective sleep data.

[0041] FIG. 8 It is an exemplary variant of the graphical user interface for recording wake-up time.

[0042] FIG. 9A and FIG. 9B It is a set of exemplary variations of the graphical user interface for bedtime.

[0043] FIG. 10A to FIG. 10G It is a set of exemplary variants of the Sleep Insight graphical user interface.

[0044] FIG. 11A and FIG. 11B It is a set of exemplary variants of the graphical user interface for predicting sleep disorders.

[0045] FIG. 12 It is an exemplary variant of the operable graphical user interface.

[0046] FIG. 13 It is an exemplary variant of the referral graphical user interface.

[0047] FIG. 14A and FIG. 14B These are a set of exemplary variations of health status reports.

[0048] FIG. 15A and FIG. 15B It is a set of exemplary variations of the user health graph.

[0049] FIG. 16 This is a schematic diagram of a variation of the user health graphic legend.

[0050] FIG. 17A to FIG. 17AA It is another set of exemplary variations of the user health graph.

[0051] FIG. 18 It is an exemplary variant of the user health graphical user interface.

[0052] FIG. 19 It is another exemplary variant of the graphical user interface for user health insights. Detailed Implementation

[0053] This paper describes systems, devices, and methods for providing actionable recommendations to users when predicting the risk of chronic conditions such as sleep disorders. These systems, devices, and methods may, for example, obtain sleep data from one or more of the user and the measuring device for analysis and / or display, and generate trends, insights, and predictions that can be presented to the user and / or a pre-determined group of contacts (e.g., healthcare professionals, family, friends, caregivers), as well as one or more recommendations that the user can take action based on the trends, insights, and predictions. This can, for example, give the user a holistic understanding of their health and provide concrete steps for improvement. For some users, viewing their sleep data and trends can be complex and cumbersome. However, the systems and methods described herein can provide intuitive insights into sleep data and trends (e.g., in plain language). For example, a user's health status, represented by a set of parameters (e.g., sleep, physical, mental), can be graphically visualized on a graphical user interface (GUI) to facilitate a holistic and intuitive understanding of the user's health. In some variations, actionable recommendations can be generated based on data and / or trends. The recommendations may include one or more steps that a user, computing device, and / or referral service (e.g., healthcare professional) may perform for the user's health.

[0054] Sleep provides a valuable opportunity to monitor and evaluate sleep-related and non-sleep-related health conditions. Sleep states, wakefulness states, and / or lying positions can provide a high signal-to-noise ratio for symptoms of many non-sleep health conditions (e.g., heart failure, COPD). For example, reducing external stimuli during bedtime and / or sleep (e.g., reducing light, activity) can help users become aware of symptoms of health conditions that may be present throughout the day. Therefore, sleep tracking (e.g., self-reported sleep proximity symptoms, multimodal sensor measurements) can be useful for tracking overall health. Furthermore, some sleep-related disorders highly overlap with many non-sleep-related disorders. For example, obstructive sleep apnea and insomnia may be comorbid with a range of chronic physical and mental health conditions. Sleep disorders can often be indicators of chronic physical and / or mental health conditions (e.g., waking up in the early morning is a sign of depression).

[0055] Generally, the systems and methods described herein can receive data from measurement devices (e.g., sleep trackers, heart monitors, activity trackers) configured to measure one or more user health characteristics during and / or related to sleep. Data generated from each of these devices can be automatically uploaded at predetermined intervals to the user's computing device (e.g., smartphone, laptop, PC) and / or database (e.g., cloud storage). This data can be coordinated (e.g., integrated) with user data (e.g., subjective user-input sleep data) for trend analysis and / or insight generation. For example, trends can be presented to the user on any device (e.g., sleep measurement device, smartphone, laptop) at a selectable level of complexity (e.g., detailed, concise, summary, colloquial, long-term, medium-term, short-term). Presenting trends to users in an accessible and / or customizable manner can increase the user's understanding of how behaviors (e.g., sleep, physical health, mental health) are related to health. Healthcare professionals can also be authorized to access user sleep data and trend data.

[0056] Furthermore, the system and method can generate actionable recommendations in response to one or more of sleep data, trends, and predictions. These recommendations may include actions that the user can perform themselves (e.g., reducing caffeine and / or alcohol intake, establishing a regular nighttime sleep schedule) and / or actions to be performed by a computing device (e.g., presenting sleep disorder information, encouraging healthy behaviors). The actionable recommendations may be output as a prompt on the computing device, which the user can select to confirm the execution of the actionable recommendations. In some variations, the recommended actions may be performed automatically without user input. In some variations, the actionable recommendations may be based on observations derived from user data (e.g., subjective sleep data entered by the user), sleep measurement data, and trends. In some variations, the actionable recommendations may include sleep service referrals, which may be useful when the user has a predicted high risk of sleep disorders.

[0057] Generally, the system described herein includes one or more of a computing device and a sleep measurement device. The sleep measurement device can be configured to generate measurement data (e.g., sleep data, cardiac data), which can be transmitted for processing and analysis. Data analysis can include trend analysis to discover relationships between user data (e.g., subjective user input data) and sleep data measured by the measurement device, as well as relationships using derived values ​​(such as sleep quality scores, physical health quality scores, and mental health quality scores). Trend analysis of different datasets (e.g., user data, sleep measurement data, sleep quality scores, physical health quality scores, and mental health quality scores) associated with one or more of sleep, physical health, and mental health can provide a holistic insight into a user's overall health. The analysis results can be used to generate one or more prompts to be output to the user on a graphical user interface. For example, data analysis showing a trend (e.g., high risk) of a user exhibiting a sleep disorder (e.g., sleep apnea) can be used to output a user prompt that refers the user to a healthcare professional and / or adds actionable recommendations (e.g., reducing caffeine intake) to promote desired behaviors (e.g., higher quality sleep). Users can receive prompts from the system to modify computing device settings (e.g., add alerts, measure additional parameters) in response to one or more of data analysis, trend analysis, and / or forecasting. As another example, data analysis showing a user is in a positive trend can be used to generate prompts that provide positive reinforcement to the user.

[0058] As used herein, a specific output and any corresponding data or signal will be referred to as a “prompt”. A specific user input and any corresponding data or signal will be referred to as a “command”. In some variations, the prompt may suggest a command to the user. For example, the prompt may output a command that the user can confidently input into the device (e.g., an actionable suggestion, recommendation, observation). For example, the prompt may be displayed on the user’s device (e.g., a touchscreen of a computing device) and may suggest that the user discuss their predicted risk of sleep disorders with a healthcare professional, while displaying a prompt suggesting scheduling an appointment with their healthcare professional (e.g., “Would you like to consult a specialist?”). The user can confirm the execution of the prompt to schedule an appointment by inputting a selection into the device (e.g., selecting the corresponding icon on the touchscreen of a computing device), thus providing a command.

[0059] I. System A sleep assessment system may include one or more of the components necessary for measuring and analyzing user data using the apparatus described herein. Additionally, the system may be configured to generate and output predictions and / or prompts to encourage healthy behaviors based on data and / or analysis of that data. FIG. 1This is a block diagram of a variant of the sleep assessment system (100). The system (100) may include a computing device (110) (e.g., a user device) and a measuring device (120) (e.g., a sleep measuring device) configured to measure one or more sleep parameters of a user, such as sleep start time, sleep end time, sleep duration, minutes to fall asleep, number of awakenings, sleep quality, and as further described herein. The computing device (110) and the measuring device (120) may be communicatively coupled via one or more wired or wireless communication channels. For example, the computing device (110) and the measuring device (120) may be coupled to one or more of a network (130), a database (140), a server (150), and a healthcare professional (HCP) device (160) via one or more wired or wireless communication channels. Processing and analysis may be performed at any of the devices in the system (100) or distributed across multiple devices.

[0060] FIG. 2 This is a block diagram of a variant of the computing device (200). For example, the computing device (200) may correspond to the reference... FIG. 1 The described sleep assessment system (100) includes a computing device (110). While a single computing device is schematically depicted, it should be understood that the system described herein may include multiple (e.g., two, three, four, five, or more) computing devices. In some variations, the computing device (200) (or any other device of the system (100)) may be configured to evaluate and predict sleep disorders and may provide one or more of the following: actionable recommendations and sleep service referrals. The computing device (200) may include an integration of a full-stack technology that includes one or more of the following: collecting raw data from a set of devices (e.g., computing devices, measurement devices, servers, databases), data storage, feature extraction, and analysis to identify trends and predict the risk of sleep disorders.

[0061] The computing device (200) may include a processor (210), a memory (220), and at least one input / output interface (240). The memory (220) may be configured to store instructions associated with one or more of the following: an evaluation module (222) configured to receive user data; a data processing module (224) configured to process raw data; a visualization module (226) configured to generate visual graphics; a trend module (228) configured to generate sleep trends; a prediction module (230) configured to predict the risk of sleep disorders; a recommendation module (232) configured to generate actionable recommendations; and a referral module (234) configured to refer sleep services.

[0062] In some variations, the assessment module (222) may be configured to receive user input data in response to a set of sleep and / or health-related questions from one or more of the computing device and sleep measurement device described herein. These questions may be based on a set of clinically recognized sleep questionnaires as described herein. In some variations, the assessment module (222) may be configured to output notifications to the user at predetermined intervals for user input of user data, including, for example, sleep scores, physical health scores, and mental health scores. In some variations, the sleep scores, physical health scores, and mental health scores may each correspond to a predetermined scale. For example, the predetermined scale may be a Likert scale (e.g., a 3-point scale, a 5-point scale, a 10-point scale, an n-point scale). In some variations, the assessment module (222) may be configured to receive sleep measurement data from one or more of the measurement device and data source (e.g., database 140, server 150, HCP device 160).

[0063] In some variations, sleep scores may include sleep quality status, physical health scores may include physical condition, and mental health scores may include emotional state. In some variations, sleep quality status may include the reason for waking up. In some variations, physical condition may include the type of physical discomfort, the location of the discomfort, and the intensity of the discomfort. In some variations, emotional state may include mood at wake-up time and mood at bedtime.

[0064] In some variations, user data and sleep measurement data can be received at predetermined intervals. For example, the predetermined intervals could be at least once a day, at least twice a day, at least three times a day, at least four times a day, at least five times a day, between once and twice a day, between once and three times a day, between once and four times a day, between once and five times a day, between twice and three times a day, between twice and four times a day, and between twice and five times a day. In some variations, the predetermined intervals can correspond to specific times of day. For example, in some variations, the predetermined intervals could be wake-up and bedtime times set by the user.

[0065] In some variations, user data and sleep measurement data can be integrated into user data that includes one or more sleep parameters. For example, sleep parameters may include one or more of the following: sleep start time, sleep end time, sleep duration, sleep stage, sleep onset time, number of awakenings, duration of wakefulness, snoring status, snoring duration, exercise duration, exercise end time, number of alcoholic beverages consumed, time of last alcoholic beverage consumption, number of caffeinated beverages consumed, time of last caffeinated beverage consumption, daytime sleepiness status, severity of daytime sleepiness, mean sleep oxygen saturation, mean sleep heart rate variability, minimum sleep heart rate, maximum sleep heart rate, mean sleep heart rate, a set of medications taken, and user demographic data. In some variations, user demographic data may include one or more of medical history and examination results. In some variations, sleep parameters may also include records of the user's wake-up time and bedtime. This document describes in more detail the processes associated with assessing user health (e.g., FIG. 3A to FIG. 3C and FIG. 5A to FIG. 9B ).

[0066] In some variations, the data processing module (226) may be configured to process raw data (e.g., user data, sleep measurement data) from one or more computing devices and sleep measurement devices described herein to generate sleep data. In some variations, data processing may include one or more of filtering, outlier removal, missing value handling, and data integration (e.g., coordination). For example, a user may coordinate (e.g., edit, correct, update) one or more measured sleep parameters, such as wake-up time, number of wake-ups, or any of the other sleep parameters described herein, to ensure data integrity and generate sleep data. In some variations, the data processing module (226) may be configured to output processed sleep data, which may be input to one or more of a trend module (228), a prediction module (230), a recommendation module (232), a referral module (234), and a visualization module (224).

[0067] In some variations, the visualization module (226) may be configured to generate a graphical representation of user health (e.g., a user health graph) based on one or more of the user data, sleep measurement data, and / or sleep data as described herein. In some variations, generating the user health graph may include generating the user health graph on a graphical user interface of a computing device, and generating a first shape including a first color based on a sleep score, a second shape including a second color based on a physical health score, and a third shape including a third color based on a mental health score. The positions of the first, second, and third shapes may be arranged based on the sleep score, physical health score, and mental health score relative to a first axis of the user health graph.

[0068] In some variations, the center-to-center distance between the first and second shapes can be based on the difference between two of the sleep score, physical health score, and mental health score. In some variations, the first, second, and third shapes can partially overlap. For example, the first, second, and third shapes can overlap along a first axis (or any axis). In some variations, generating a user health graph may optionally include generating multiple lines that overlap with at least two of the first, second, and third shapes. In some variations, each of the first, second, and third shapes can include a two-dimensional geometry. In some variations, each of the first, second, and third colors can include a color gradient. In some variations, each of the first, second, and third colors can include an opacity gradient. In some variations, the multiple lines can include a first line between the center of the first shape and the center of the second shape, and a second line between the center of the second shape and the center of the third shape. This document describes in more detail the process associated with graphically representing user health (e.g., FIG. 4 , FIG. 15A to FIG. 17AA ).

[0069] In some variations, the trend module (228) can be configured to generate one or more sleep trends by analyzing sleep data generated by the data processing module (224). Furthermore, the trend module (228) can be configured to generate a graphical user interface that includes the sleep trends and the risk of one or more sleep disorders. The process associated with generating trends is described in more detail herein (e.g., FIG. 10A to FIG. 10G ).

[0070] In some variations, the prediction module (230) can be configured to predict the risk of one or more sleep disorders based on user data and sleep measurement data. In some variations, the risk of one or more sleep disorders can be based on one or more sleep trends. In some variations, a graphical user interface can be generated based on one or more of the sleep trends and the risk of one or more sleep disorders. In some variations, one or more sleep disorders can include one or more of the following: obstructive sleep apnea, central sleep apnea, hypoventilation, orthopnea, nocturnal atrial fibrillation, nocturnal hypertension, nocturnal discomfort, nocturnal exacerbation of chronic obstructive pulmonary disease, heart failure, asthma, sleep quality, and waking discomfort. The process associated with generating the prediction is described in more detail here (e.g., FIG. 11A to FIG. 11B In some variations, the prediction module (230) may include one or more machine learning models, as described in more detail herein.

[0071] In some variations, the recommendation module (232) can be configured to generate one or more actionable suggestions. In some variations, actionable suggestions may include modifying computing device settings based on one or more of user data, sleep measurement data, processed data, and user health graphs. The process associated with generating recommendations is described in more detail herein (e.g., FIG. 12 ).

[0072] In some variations, the referral module (234) may be configured to refer sleep services to users using computing devices based on one or more of sleep trends and the risk of one or more sleep disorders. The process associated with generating referrals is described in more detail herein (e.g., FIG. 13 to FIG. 14B ).

[0073] Measuring device The term "measuring device" as used herein can refer to any device configured to measure, receive, and / or analyze one or more characteristics of a user. Measuring devices may, for example, measure sleep parameters, user activity, and / or nutrition. Non-limiting examples of measuring devices include sleep trackers, wearable activity devices (e.g., pedometers or other activity trackers), hydration trackers, blood pressure monitors, heart rate monitors, ultrasonic (e.g., sonar) sensors, cholesterol monitors, scales, geolocation devices (e.g., GPS, GLONASS), smartphones, refrigerators, PCs, implantable diagnostic devices, ingestible diagnostic devices, and other diagnostic devices. Measuring devices may include one or more sensors configured to measure one or more user parameters. Parameters that sensors can measure may generally include, but are not limited to: sleep, hydration, cholesterol, oxygen saturation, carbon dioxide saturation, pH, respiratory rate, respiratory sounds, human voice (e.g., cough), ultrasonic audio, accelerometers with step counts and / or location data, impedance, resistance, temperature, air quality, weight, blood pressure, heart rate, heart rate variability, etc. In some variations, ultrasonic audio (e.g., sonar data) can be generated by a sonar system configured to emit ultrasonic audio signals and receive reflected ultrasonic audio signals. Additionally, sleep parameters can include one or more of the following: sleep onset time, sleep end time, sleep duration, sleep onset time, number of awakenings, duration of wakefulness, snoring status, audio, snoring duration, exercise duration, exercise start time, exercise end time, number of alcoholic beverages consumed, time of last alcoholic beverage consumption, number of caffeinated beverages consumed, time of last caffeinated beverage consumption, daytime sleepiness status, severity of daytime sleepiness, mean sleep oxygen saturation, mean sleep heart rate variability, minimum sleep heart rate, maximum sleep heart rate, mean sleep heart rate, a set of medications taken, and user demographics. For example, snoring status can indicate whether a user snores during a sleep cycle.

[0074] Measurement data generated by the measuring device may include, but is not limited to, sleep duration, sleep quality, mood / feelings, stress, nutritional data (e.g., dietary markers, carbohydrate intake, calorie intake, etc.), activity or exercise (e.g., calories burned, steps, degree or intensity of activity (e.g., based on heart rate level), duration of activity, etc.), user weight, oral or other medications, hydration, etc. Data generated by the measuring device may be transmitted to any device within the system (100) and may include one or more features, elements, and / or functions of a computing device as described herein. For example, the measuring device may include a controller comprising: a processor and memory for performing data analysis on the measurement data generated by the measuring device; and a communication interface configured to transmit measurement data to another device. The measuring device may be coupled to the device using any known wired or wireless connection method and communication protocol.

[0075] Furthermore, while in some variations the measuring device may be a wearable device as described above, it should be understood that in other variations the measuring device may be configured as a non-wearable device. An example of a non-wearable measuring device for measuring one or more sleep parameters is an implantable device or external monitor, such as a bedside monitor or home virtual assistant device (e.g., similar to Amazon Echo® or Google Home™ devices), a set-top box service (e.g., similar to Apple TV®), or other smart home appliances such as clocks, radios, etc. In some variations, the system described herein may include multiple measuring devices, one or more of which may be wearable devices, and one or more of which may be configured as non-wearable devices.

[0076] Computing device Generally, the computing device described herein may include a controller, which includes a processor (e.g., a CPU) and memory (which may include one or more computer-readable storage media). The processor may combine data received from the memory and user input to control one or more components of the system (e.g., a measuring device (120), a database (140), a server (150), an HCP device (160)). The memory may also store instructions to cause the processor to execute modules, processes, and / or functions associated with the methods described herein. As used herein, a computing device may refer to... FIG. 1 Any of the computing device (110), database (140), server (150), and HCP device (160) depicted herein. In some variations, the memory and processor may be implemented on a single chip. In other variations, they may be implemented on separate chips.

[0077] The computing device (110, 200) can be configured to receive and process user input to the computing device and measurement data from one or more measuring devices. The computing device can be configured to receive, compile, store, and access data. In some variations, the computing device can be configured to access and / or receive data from various sources. The computing device can be configured to receive data directly input by a user, and / or it can be configured to receive data from separate devices (e.g., measuring devices, smartphones, tablets, computers) and / or from storage media (e.g., flash drives, memory cards). The computing device can receive data via a network connection, as discussed in more detail herein, or via a physical connection to a device or storage medium (e.g., via a Universal Serial Bus (USB) or any other type of port). Computing devices can include any of a variety of devices such as cellular phones (e.g., smartphones), tablets, laptops, desktop computers, portable media players, wearable digital devices (e.g., digital glasses, wristbands, watches, brooches, armbands, virtual reality / augmented reality headsets, jewelry (e.g., bracelets, necklaces, rings)), televisions, set-top boxes (e.g., cable TV boxes, video players, video streaming devices), gaming systems, etc.

[0078] The computing device can be configured to receive various types of data. For example, the computing device can be configured to receive personal data (e.g., gender, weight, birthday, age, height, diagnosis date, anniversary of device use, etc.), user data (e.g., sleep scores, physical health scores, and mental health scores), nutritional data (e.g., the amount of food consumed daily, the amount of alcoholic beverages consumed, the amount of carbohydrates consumed, etc.), activity data (e.g., if the user exercised, when the user exercised, the duration of the exercise, the type of exercise performed (e.g., cycling, swimming, running, etc.), exercise intensity (e.g., low, medium, high), heart rate during exercise, etc.), measurement data from a measuring device, or any other information. In some variations, the computing device can be configured to create, receive, and / or store user profiles. User profiles can contain any of the user-specific information described above.

[0079] While the aforementioned information can be received by a computing device, in some variations, the computing device can be configured to use software stored on or outside the device to calculate any of the aforementioned data based on the information it has received. In some variations, the computing device can be configured to compare subjective data, measurement data, nutritional data, activity data, or any other relevant data with historical data (e.g., a user's historical trends), data preloaded onto the computing device and compiled from an external source (e.g., other devices), or data received from a set of separate devices (e.g., historical data or data compiled from an external source).

[0080] A processor can be any suitable processing device configured to run and / or execute a set of instructions or code, and may include one or more data processors, image processors, graphics processing units, physical processing units, digital signal processors, and / or central processing units. A processor can be, for example, a general-purpose processor, a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc. A processor can be configured to run and / or execute application processes and / or other modules, processes, and / or functions associated with the system and / or the network associated with the system. Underlying device technologies can be provided in various component types (e.g., metal-oxide-semiconductor field-effect transistor (MOSFET) technologies such as complementary metal-oxide-semiconductor (CMOS), bipolar technologies such as emitter-coupled logic (ECL), polymer technologies (e.g., silicon conjugated polymers and metal conjugated polymer-metal structures), analog and digital mixed-signal technologies, etc.).

[0081] In some variations, the memory may include a database (not shown) and may be, for example, random access memory (RAM), a memory buffer, a hard disk drive, erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), read-only memory (ROM), flash memory, etc. The memory may store instructions to cause a processor to execute modules, processes, and / or functions associated with a communication device, such as measurement data processing, measurement device control, communication, and / or device setup. Some variations described herein relate to computer storage products having non-transitory computer-readable media (also referred to as non-transitory processor-readable media) on which instructions or computer code for performing operations of various computer implementations are present. A computer-readable medium (or processor-readable medium) is non-transitory in the sense that it does not itself contain transient propagation signals (e.g., electromagnetic waves carrying information on a transmission medium such as space or a cable). The medium and the computer code (also referred to as code or algorithm) may be designed and constructed for one or more specific purposes.

[0082] Examples of non-transitory computer-readable media include, but are not limited to: magnetic storage media such as hard disks, floppy disks, and magnetic tapes; optical storage media such as optical discs / digital video discs (CDs / DVDs); optical disc read-only memories (CD-ROMs) and holographic devices; magneto-optical storage media such as optical discs; solid-state storage devices such as solid-state drives (SSDs) and hybrid solid-state drives (SSHDs); carrier signal processing modules; and hardware devices specifically configured to store and execute program code, such as application-specific integrated circuits (ASICs), programmable logic devices (PLDs), read-only memories (ROMs), and random access memories (RAMs). Other variations described herein relate to computer program products that may include, for example, the instructions and / or computer code disclosed herein.

[0083] The systems, apparatus, and / or methods described herein can be implemented by software (executing on hardware), hardware, or a combination thereof. Hardware modules may include, for example, general-purpose processors (or microprocessors or microcontrollers), field-programmable gate arrays (FPGAs), and / or application-specific integrated circuits (ASICs). Software modules (executing on hardware) can be expressed in various software languages ​​(e.g., computer code), including C, C++, Java®, Python, Ruby, Visual Basic®, and / or other object-oriented, procedural, or other programming languages ​​and development tools. Examples of computer code include, but are not limited to, microcode or microinstructions, machine instructions (such as instructions generated by a compiler), code for generating web services, and files containing high-level instructions executed by a computer using an interpreter. Additional examples of computer code include, but are not limited to, control signals, encryption code, and compression code.

[0084] In some variations, the computing device (110) may also include a communication interface configured to allow a user to control one or more devices in the system. The communication interface may include a network interface configured to connect the computing device to another system (e.g., the Internet, a remote server, a database) via a wired or wireless connection. In some variations, the computing device (110) may communicate with other devices via one or more wired and / or wireless networks. In some variations, the network interface may include a radio frequency receiver, transmitter, and / or an optical (e.g., infrared) receiver and transmitter configured to communicate with one or more devices and / or networks. The network interface may communicate with one or more of the measuring device (120), network (130), database (140), server (150), and HCP device (160) via wired and / or wireless means.

[0085] A network interface may include RF circuitry capable of receiving and transmitting RF signals. RF circuitry can convert electrical signals into electromagnetic signals / convert electromagnetic signals into electrical signals, and communicate with communication networks and other communication devices via electromagnetic signals. RF circuitry may include known circuitry for performing these functions, including but not limited to antenna systems, RF transceivers, one or more amplifiers, tuners, one or more oscillators, digital signal processors, codec chipsets, Subscriber Identity Module (SIM) cards, memory, and so on.

[0086] Wireless communication via either a computing device or a measuring device can use any of a variety of communication standards, protocols, and technologies, including but not limited to Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), High-Speed ​​Downlink Packet Access (HSDPA), High-Speed ​​Uplink Packet Access (HSUPA), Evolved Data Optimized (EV-DO), HSPA, HSPA+, Dual-Cell HSPA (DC-HSPDA), Long Term Evolution (LTE), Near Field Communication (NFC), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, and Wi-Fi (e.g., IEEE 802.11a, IEEE 802.11b, IEEE 802.11g, IEEE...). Protocols include 802.11n, VoIP, Wi-MAX, protocols for email (e.g., Internet Messaging Access Protocol (IMAP) and / or Post Office Protocol (POP)), instant messaging (e.g., Extensible Messaging and Presence Protocol (XMPP), SIP-based Instant Messaging and Status Extension Protocol (SIMPLE), Instant Messaging and Status Service (IMPS)) and / or Short Message Service (SMS), and any other applicable communication protocols. In some variations, the devices described herein can communicate directly with each other without transmitting data over a network (e.g., via NFC, Bluetooth, WiFi, RFID, etc.).

[0087] The communication interface may also include a user interface configured to allow users (e.g., users, pre-defined contacts such as partners, family members, healthcare professionals, coaches, etc.) to control the computing device. The communication interface may allow users to interact with and / or control the computing device directly and / or remotely. For example, the user interface of the computing device may include input devices for users to enter commands and output devices for users to receive output (e.g., trends, insights, prompts displayed on the device).

[0088] The output device of the user interface can output data analysis and actionable prompts corresponding to the user, and may include one or more of a display device and an audio device. For example, the display device of the computing device can be used to facilitate video conferencing between the user and a healthcare professional. The display device can allow the user to view trend analysis, forecasts, insights, and / or other data processed by the controller. Data analysis generated by the server (150) can be displayed by the output device (e.g., a monitor) of the computing device (110). Measurement data from one or more measuring devices (120) can be received via a network interface and output visually and / or audibly via one or more output devices of the computing device (110). In some variations, the output device may include a display device, which includes at least one of light-emitting diodes (LEDs), liquid crystal displays (LCDs), electroluminescent displays (ELDs), plasma display panels (PDPs), thin-film transistors (TFTs), organic light-emitting diodes (OLEDs), electronic paper / electronic ink displays, laser displays, and / or holographic displays.

[0089] The audio device can audibly output user data, measurement data, predictions, system data, alarms, and / or notifications. For example, the audio device can output an audible alarm when a user fails to perform an assessment within a predetermined time period (e.g., a morning assessment performed within fifteen minutes of a regular wake-up time). In some variations, the audio device may include at least one of a loudspeaker, a piezoelectric audio device, a magnetostrictive loudspeaker, and / or a digital loudspeaker. In some variations, a user can use the audio device and a communication channel to communicate with other users. For example, a user can establish an audio communication channel with a telehealth professional (e.g., a VoIP call).

[0090] In some variations, the user interface may include an input device (e.g., a touchscreen) and an output device (e.g., a display device), and is configured to receive input data from one or more of a measuring device (120), a network (130), a database (140), a server (150), and an HCP device (160). For example, user control of the input device (e.g., a keyboard, buttons, a touchscreen) may be received by the user interface and then processed by the user interface's processor and memory for outputting control signals to one or more measuring devices (120). Some variations of the input device may include at least one switch configured to generate control signals. For example, the input device may include a touch surface for the user to provide input corresponding to the control signals (e.g., finger contact with the touch surface). Input devices including touch surfaces may be configured to detect contact and movement on the touch surface using any of a variety of touch sensitivity technologies, including capacitive, resistive, infrared, optical imaging, scattering signal, acoustic pulse recognition, and surface acoustic wave technologies. In variations of the input device that include at least one switch, the switch may include at least one of the following: a button (e.g., a hard key, a soft key), a touch surface, a keyboard, an analog joystick (e.g., a joystick), a direction pad, a mouse, a trackball, a micro dial, a step switch, a rocker switch, a pointer device (e.g., a stylus), a motion sensor, an image sensor, and a microphone. The motion sensor may receive user movement data from an optical sensor and classify the user's posture as a control signal. The microphone may receive audio data and recognize the user's voice as a control signal.

[0091] Haptic devices can be incorporated into one or more input and output devices to provide additional sensory outputs (e.g., force feedback) to a user. For example, a haptic device can generate a haptic response (e.g., vibration) to acknowledge a user's input to an input device (e.g., a touch surface). As another example, haptic feedback can notify a user that their input has been overridden by a computing device.

[0092] network In some variations, the systems and methods described herein can communicate with other computing devices via, for example, one or more networks, each of which can be any type of network (e.g., wired network, wireless network). The communication may or may not be encrypted. A wireless network can refer to any type of digital network not connected by any kind of cable. Examples of wireless communication in a wireless network include, but are not limited to, cellular, radio, satellite, and microwave communications. However, a wireless network can connect to a wired network to access the Internet, other carrier voice and data networks, business networks, and personal networks. Wired networks are typically carried on copper twisted-pair, coaxial, and / or fiber optic cables. Many different types of wired networks exist, including wide area networks (WANs), metropolitan area networks (MANs), local area networks (LANs), Internet regional networks (IANs), campus networks (CANs), global area networks (GANs) such as the Internet, and virtual private networks (VPNs). In the following text, "network" refers to any combination of wireless, wired, public, and private data networks typically interconnected via the Internet to provide a unified networking and information access system.

[0093] Cellular communications can include technologies such as GSM, PCS, CDMA or GPRS, W-CDMA, EDGE or CDMA2000, LTE, WiMAX, and 5G network standards. Some wireless network deployments combine networks from multiple cellular networks or use a hybrid of cellular, Wi-Fi, and satellite communications.

[0094] II. Methods This paper also describes methods for assessing and predicting the risk of chronic medical conditions in users using the systems and devices described herein. Analysis of user data and sleep measurement data can be used to generate one or more of the following: insights into user health (e.g., trends or other observations related to sleep, physical health, and / or mental health), predictions of the risk of medical conditions such as sleep disorders, and one or more recommendations (e.g., actionable tips) that can advise users to take practical steps, such as changing behavior and / or changing device settings. Insights generated from sleep data can improve the understanding that sleep is fundamental to overall health and encourage users to continue self-reporting results. In some cases, recommendations can encourage users to translate their sleep data into clinical action (e.g., seeking referrals to sleep services).

[0095] In some variations, users can download and run a mobile application and / or register via a web portal. In some variations, user registration and onboarding can be automated or semi-automated. As part of the onboarding process, user demographics (e.g., age, gender, height, weight), medical history (e.g., comorbidities, symptoms, medications), and / or any appropriate user information can be entered into the system and added to the user profile.

[0096] During user onboarding, users can optionally complete an intake questionnaire or other suitable intake form (e.g., dynamic or static questionnaires, such as self-screening tools). For example, the questionnaire could be tailored to sleep-related disorders. Users might be asked to complete questionnaires related to their personal medical history (e.g., symptoms, diagnosis of chronic diseases, medication), family medical history, and / or current sleep-related symptoms (e.g., insomnia). Additionally, the questionnaire may optionally include generalized questions that are not necessarily specific to a medical condition (e.g., sleep habits, sleep goals, mental health goals, physical health goals, nutrition).

[0097] Generally speaking, the methods described herein may include objective and subjective assessments of patient sleep, generating sleep insights for users, and providing sleep recommendations for users' considerations and actions. It should be understood that any systems and devices described herein can be used in the methods described herein.

[0098] FIG. 3AThis is a flowchart outlining a sleep disorder prediction process (300). The process (300) may include a sleep assessment process (302), a sleep insight process (304), and a sleep recommendation process (306). The sleep assessment process (302) may include using a computing device to output user input notifications (e.g., user input of subjective sleep data) based on user data (310). For example, the computing device may display prompts at predetermined intervals as reminders for user input assessments (e.g., wake-up time, bedtime). Notifications may be provided periodically, such as at least once a day, twice a day (e.g., morning and evening), three times a day (e.g., morning, afternoon, and evening), and so on. In some variations, notifications may be output at approximately a predetermined wake-up time (e.g., approximately 6 a.m.) and approximately a predetermined bedtime (e.g., approximately 10 p.m.), which may be set as a default value or input by the user. While this document describes notifications and assessments twice a day, any number of notifications and assessments may be performed daily. For example, afternoon notifications and assessments may be performed to receive user data corresponding to a nap. In some variations, notifications may be additionally or alternatively configured to be output at predetermined times for a predetermined duration and / or frequency. For example, notifications may include audible notifications (e.g., sounds such as musical tones, beeps, chirps), visual notifications (e.g., flashlights, graphic displays), physical notifications (e.g., haptic feedback via a vibration motor), and any combination thereof. In some variations, if the user fails to respond to the notification (e.g., perform an evaluation) within a predetermined time period after receiving the notification (e.g., 1 minute, 2 minutes, 5 minutes, 10 minutes, etc.), the notification may be provided again. Alternatively, in some variations, notifications may be omitted.

[0099] User data and / or sleep measurement data can be received at a device (320), such as a computing device (110), a measurement device (120), a database (140), a server (150), and an HCP device (160) as described herein. In some variations, user data may include sleep scores, physical health scores, and mental health scores. For example, a sleep score may include sleep quality status, a physical health score may include physical status, and a mental health score may include emotional status. Furthermore, sleep quality status may include the reason for waking up. Physical status may include the type of physical discomfort, the location of physical discomfort, and the intensity of physical discomfort. Emotional status may include mood at the time of waking up and mood at the time of going to bed. In some variations, sleep scores, physical health scores, and mental health scores may each correspond to a predetermined scale. For example, the predetermined scale may be a Likert scale (e.g., a 3-point scale, a 5-point scale, a 10-point scale, an n-point scale).

[0100] In some variations, user data can be entered on the computing device's GUI, as shown in the reference. FIG. 5A to FIG. 9B In more detail, in some variations, user-inputted data may respond to a predefined set of sleep and / or health-related questions. These questions may be based on a set of clinically recognized sleep questionnaires, including but not limited to: the Functional Outcomes in Sleep Questionnaire (FOSQ), the Idiopathic Somnolence Severity Scale (IHSS), the Epworth Somnolence Scale, the Berlin Sleep Apnea Questionnaire, the simplified morning / evening type questionnaire (rMEQ), the Insomnia Severity Index, the Sleep Inertia Questionnaire (SIQ), the PHQ-9, and the American Thoracic Society Sleep-Related Questionnaire, etc.

[0101] In some variations, the questions to be asked can be generated based on a pre-defined list of questions. At least some of the questions asked to the user can be static or set as the default questions. Additionally or alternatively, at least some of the questions asked to the user can be asked at different frequencies (e.g., daily, weekly, bi-weekly, monthly). Additionally or alternatively, at least some of the questions asked to the user can be dynamic or set to be asked in response to current user data (e.g., the user's answers to static questions). For example, in response to a predicted high risk of sleep disorders, dynamic questions can be generated to gather further information to help characterize the risk of sleep disorders. In other words, dynamic questions may include one or more follow-up questions customized to be associated with different risk levels. The type of dynamic questions can additionally or alternatively be medical condition-specific and user-specific.

[0102] In some variations, one or more of the computing device and the measuring device may be configured to measure sleep measurement data corresponding to one or more sleep parameters of a user. The sleep measurement data may be transmitted to the computing device (or any device described herein) for processing and analysis. For example, a communication channel may be established between the measuring device and the computing device. The communication channel may be a wired or wireless connection and may use any communication protocols, including but not limited to those described herein. The communication channel may be established at predetermined intervals based on one or more of the following: time (e.g., hourly, daily, weekly, etc.), device usage (e.g., after wake-up time, when the device is powered on), connection requests, etc.

[0103] In some variations, sleep measurement data may include one or more sleep parameters. These parameters may include one or more of the following: sleep onset time, sleep end time, sleep duration, sleep onset time, number of awakenings, duration of wakefulness, snoring status, snoring duration, exercise duration, exercise start time, exercise end time, number of alcoholic beverages consumed, time of last alcoholic beverage consumption, number of caffeinated beverages consumed, time of last caffeinated beverage consumption, daytime sleepiness status, severity of daytime sleepiness, mean sleep oxygen saturation, mean sleep heart rate variability, minimum sleep heart rate, maximum sleep heart rate, mean sleep heart rate, a set of medications taken, and user demographic data. In some variations, sleep parameters may also include user wake-up time records and user bedtime records. In some variations, user demographic data may include one or more of medical history and examination results.

[0104] Additionally or alternatively, suitable speech-to-text transcription models or services (e.g., Google Voice) may be used to transcribe and / or parse user data. Optionally, the collection and storage of user data may be performed in a HIPAA-compliant manner. Furthermore, in some variations, some or all of the user data may be encrypted and / or de-identified to further ensure user privacy. For example, in these variations, de-identification may be combined with HIPAA-compliant practices to provide an additional layer of security to prevent other third parties from accessing identifiable user data.

[0105] In some variations, user data and sleep measurement data can be integrated to generate sleep data. For example, sleep data can be generated based on user data and / or sleep measurement data (330). In some cases, user data and sleep measurement data may not match due to errors from one or more of the user and the measuring device. For example, the measuring device may measure the wake-up time as 7:00 AM, while the user data may reflect a wake-up time as 6:45 AM. Therefore, during wake-up time assessment or bedtime assessment, the user can reconcile the user data and sleep measurement data by confirming the correct wake-up time between the user data and sleep measurement data to ensure data integrity and generate sleep data. As another example, the measured bedtime (e.g., 11:00 PM) (620) in the GUI (602) may be pre-populated with sleep measurement data, but can be manually confirmed by the user to reflect the actual bedtime. In some variations, sleep data generation (e.g., data integration, reconciliation) may include formatting data to allow comparison and analysis of datasets generated from different devices. In some variations, one or more of, such as computing devices, measuring devices, and servers, can be used to perform data integration.

[0106] In some variations, the sleep assessment (302) can be performed at a predetermined time of day. For example, in some variations, the sleep assessment (302) can be performed twice a day, once in the morning and once in the evening. In some variations, the sleep assessment (302) may include a wake-up assessment (321) (i.e., at or close to the user's wake-up time (e.g., within 30 to 60 minutes)) and a bedtime assessment (326) (i.e., at or close to the user's bedtime (e.g., within approximately 30 to 60 minutes)). FIG. 3B This is a flowchart summarizing the wake-up assessment process (321). The wake-up assessment process (321) may include using a computing device to output user input notifications for user data (e.g., user input for subjective sleep data) (322). Sleep measurement data may be received from one or more measuring devices (323), and user data may be received at the computing device (324). Sleep data may be generated based on user data and / or sleep measurement data (325). In some variations, the user may be prompted to input one or more of the following during the wake-up time assessment: previous bedtime (e.g., bedtime of the previous night), time of falling asleep, number of awakenings, duration of wakefulness (e.g., total wakefulness time between bedtime and wake-up time), reason for waking, physical condition (e.g., how the body feels (level 1 to 5), discomfort and intensity), emotional state (e.g., how the user feels today (level 1 to 5), emotional feeling, why the user feels that emotion), and wake-up time record.

[0107] FIG. 3C This is a flowchart summarizing the bedtime assessment process (326). The bedtime assessment process (326) may include using a computing device to output user input notifications for user data (e.g., user input of subjective sleep data) (327). Sleep-related user data may be received at the computing device (328). Sleep data may be generated based on previously received user data and / or sleep measurement data (329). In some variations, the user may be prompted to input one or more of the following during the bedtime assessment: emotional state (e.g., how the user feels today (level 1 to 5), emotional feeling, why the user feels that emotion), daytime sleepiness and its severity, and factors that may affect sleep (e.g., medication, alcohol, caffeine, exercise, nap frequency and / or nap duration), and bedtime logs.

[0108] Back FIG. 3AAs shown in the figure, the sleep insight process (304) may include generating one or more trends, and in some variations, optionally generating predicted risks of one or more sleep disorders. For example, one or more trends (e.g., sleep trends, health trends) may be generated based on sleep data (340). FIG. 10A to FIG. 10G The described approach involves analyzing sleep data to generate one or more trends that can be output to a GUI. For example, sleep trends may include one or more of the following: sleep quality, average sleep time, average net sleep time, average sleep onset time, average wake-up time, average snoring time, physical discomfort, sleep heart rate (e.g., maximum, minimum, and / or average), sleep interruptions, average sleep oxygen saturation, average heart rate variability, sonar data, etc. In some variations, the user can select the time period used for trend analysis (e.g., one week, two weeks, three weeks, one month, two months, n weeks, n months). In some variations, trend analysis may combine user data (e.g., the user's perception of physical pain levels) and sleep measurement data (e.g., average heart rate, sonar data). Any combination of user data and sleep measurement data described herein can be used. In some variations, trends may use one or more of the following: colloquial language (e.g., "Your morning headaches are becoming more frequent."), graphical visualizations, charts, graphs, summaries, etc. In some variations, one or more of the sleep data, trends, and predictions may be transferred to pre-determined contacts such as sleep service providers (e.g., clinicians, specialists, physicians, healthcare professionals) and / or pre-determined contacts (e.g., family members, friends, caregivers). In some variations, one or more GUIs in the GUI may include one or more selectable segment navigation headers (not shown) to facilitate navigation to the desired trends, data, and predictions.

[0109] In some variations, the risk of sleep disorders can be predicted based on sleep data (350). For example, the prediction step may include performing analysis to assess sleep data for predicting the risk of one or more sleep disorders. In some variations, sleep data may be analyzed via machine learning and / or other artificial intelligence techniques, and an output may be created as a prediction of a user's risk of a sleep disorder (e.g., the predicted severity, the probability of a medical condition such as sleep apnea). In some variations, sleep data from multiple users may be analyzed to characterize the risk of sleep disorders or other conditions for each user. In some variations, appropriate alert conditions may be selected, such as thresholds and / or other conditions for triggering notifications associated with high-risk users.

[0110] In some variations, methods, systems, and apparatuses for predicting the risk of sleep disorders can utilize one or more predictive models (e.g., machine learning models) such as logistic regression, decision trees, and neural networks. For example, a system may receive sleep data from multiple users (e.g., as described herein), process the data into an encoded representation, and generate one or more predictions based on that data. Neural networks can be trained to process sleep data using recurrent neural networks to predict the risk of one or more sleep disorders. New data collected over time can improve and refine the predictive model. In some variations, the dimensionality of sleep data can be reduced (e.g., using principal component analysis) to discover correlations between features. For example, principal components can be accepted until 90% of the data variance can be explained by principal component mapping. Due to the nature of sleep data collection (e.g., forgetfulness during assessment), some users may miss inputting at least some user data for the intended assessment. To compensate for missing user data, in some variations, the missing values ​​can be set to previous input values ​​or the baseline mean of one or more users in the same demographic group as the user. In some variations, recurrent neural network models can be trained to predict assessment values ​​for the following day, such that in the event of missing data, the recurrent neural network can fill in the missing user data with predictions.

[0111] In some variants, recurrent neural networks can take sleep data as input and output the risk (e.g., probability) of a user having one or more sleep disorders. In some variants, one or more sleep disorders may include obstructive sleep apnea, central sleep apnea, hypoventilation, orthopnea, nocturnal atrial fibrillation, nocturnal hypertension, nocturnal discomfort, nocturnal exacerbation of chronic obstructive pulmonary disease, heart failure, asthma, sleep quality issues, and waking discomfort. In some variants, after training the model on an initial dataset for a period of time, the model can be deployed to predict the probability of a user having one or more sleep disorders. In some variants, the results of the model's predictions can be used to generate one or more notifications, actionable suggestions, and referrals.

[0112] To generate suitable training data for training a machine learning model, one or more extracted features can be derived from a suitable training dataset. Generally, a training dataset may include information related to user data, sleep measurements, and clinical diagnoses, and any such information can be extracted as features for training the machine learning model. Any suitable fragments of information from the training dataset (e.g., any information from the training dataset described above) can be extracted as features and / or standardized in format for training the machine learning model. In some variations, some extracted features can be combined or otherwise correlated for training.

[0113] In some variations, the trained machine learning model can be tested to evaluate its performance on another set of sleep data (e.g., consumer data, sample data). The model can then be modified to improve performance. Further validation of the model can be performed using a separate set of sleep data to confirm its effectiveness. Once deployed, the model can be configured to generate predictions in real time (e.g., via a web or mobile application on a computing device). The performance of the deployed model can be monitored over time to identify potential problems and improve accuracy. The model can be periodically retrained with different sleep data to improve performance and accuracy over time.

[0114] Return to reference FIG. 3A Optionally, in some variations, the method may include generating a GUI (360°) that includes one or more trends and risks of sleep disorders. (See also: Regarding...) FIG. 10A to FIG. 10G , FIG. 11A , FIG. 11B , FIG. 13 , FIG. 14A and FIG. 14B In more detail, trends and forecasts can provide users with insights into one or more of their sleep, physical health, and mental health.

[0115] In some variations, the sleep recommendation process (306) may include providing the user with one or more of actionable recommendations and clinical referrals based on sleep insights. In some variations, actionable recommendations (370) may be provided to the user based on generated trends and predicted sleep disorder risks (e.g., via a computing device). In some variations, actionable recommendations may include modifying computing device settings based on one or more of user data, sleep measurement data, sleep data, and user health graphs. For example, the microphone of the measurement device may be configured to record audio of the user snoring during sleep in response to the user's selection of a corresponding actionable recommendation (e.g., a notification to reduce alcohol intake).

[0116] Optionally, in some variations, clinical referrals may be offered to users based on trends, risks, and / or user health graphs (e.g., via a computing device) of sleep disorders (460). In some variations, clinical referrals may include sleep services (380). For example, users may be prompted to share sleep and health reports generated by the computing device with their physicians (e.g., a GUI (1300)).

[0117] Consistent user engagement with the systems, apparatus, and methods described herein can improve the accuracy and validity of the resulting insights and predictions. However, some users may be discouraged from consistently engaging with the system (e.g., due to stress and / or poor health, or other reasons). Therefore, in some variations, methods for remotely assessing and predicting sleep-related disorders can benefit from displays of graphical visualizations configured to enhance user engagement and morale. Additionally or alternatively, users who successfully complete daily assessments may be provided with pleasant (e.g., relaxing, soothing) content. For example, methods may include providing pleasant audio and / or visual feedback (e.g., musical snippets, encouragement).

[0118] FIG. 4 This is a flowchart summarizing a graphical user health status process (400). The process (400) may include using a computing device to output user input notifications (410) based on user data. For example, the computing device may display prompts at predetermined intervals as reminders for user input assessments (e.g., wake-up time, bedtime). User data and / or sleep measurement data may be received at a device (420), such as a computing device (110), a measurement device (120), a database (140), a server (150), and an HCP device (160) as described herein. In some variations, user data may include sleep scores, physical health scores, and mental health scores, as described herein. For example, sleep scores, physical health scores, and mental health scores may each correspond to a predetermined scale. For example, the predetermined scale may be a Likert scale (e.g., a 3-subscale, a 5-subscale, a 10-subscale, an n-subscale).

[0119] like FIG. 15A , FIG. 15B and FIG. 17A to FIG. 17AA As shown, the process (400) may include generating a user health graphic (430) on a graphical user interface of a computing device. In some variations, the user health graphic may be generated by generating a first shape based on a sleep score, a second shape based on a physical health score, and a third shape based on a mental health score. Additionally or alternatively, the user health graphic may be generated by generating a first color based on a sleep score, a second color based on a physical health score, and a third color based on a mental health score. The first shape may be associated with a first color, the second shape may be associated with a second color, and the third shape may be associated with a third color. For example, FIG. 16This is a schematic diagram of a set of shapes with colors corresponding to different sleep and health scores. For example, a negative (e.g., below standard) sleep score may correspond to a first sleep shape (1610) with a first color (e.g., red), a neutral (e.g., moderate) sleep score may correspond to a second sleep shape (1612) with a different second color (e.g., yellow), and a positive (e.g., good) sleep score may correspond to a third sleep shape (1614) with a third color (e.g., green) different from the first and second colors. In some variations, a sleep quality score of 1 or 2 on a 5-point Likert scale may correspond to a negative sleep score, a sleep quality score of 3 may correspond to a neutral score, and a sleep quality score of 4 or 5 may correspond to a positive sleep score.

[0120] As discussed in this paper, sleep scores, physical health scores, and mental health scores each correspond to user input from user data. In some variations, sleep quality scores may be based at least on sleep scores and may include additional sleep parameters as discussed in this paper. Similarly, physical health quality scores may be based at least on physical health scores and may include additional physical health parameters as discussed in this paper.

[0121] In some variations, negative sleep quality scores can be below approximately 75% (e.g., on a 100% scale), below approximately 70%, below approximately 65%, or below approximately 60%, including all subranges and values ​​in between. In some variations, neutral sleep quality scores can be between approximately 60% and approximately 85%, between approximately 65% ​​and approximately 80%, between approximately 70% and approximately 80%, between approximately 75% and approximately 80%, or between approximately 60% and approximately 80%, including all subranges and values ​​in between. In some variations, positive sleep quality scores can be above approximately 70%, above approximately 75%, above approximately 80%, or above approximately 85%, including all subranges and values ​​in between. Sleep quality scores can be determined based on multiple subjective and / or objective sleep parameters, such as sleep score, sleep duration, sleep heart rate variability, etc.

[0122] In some variations, a sleep quality score can be determined based on multiple subjective and / or objective sleep parameters, such as the sleep score (e.g., user input for subjective sleep quality), sleep duration, sleep efficiency, sleep latency, number of awakenings (e.g., awakenings lasting longer than a predetermined threshold (e.g., 4 minutes, 5 minutes, 6 minutes, 7 minutes, or longer), wakefulness time (e.g., wakefulness after falling asleep (WASO)), sleep heart rate variability, sleep duration regularity (e.g., regularity of sleep onset time), sleep duration regularity (e.g., regularity of sleep duration), check-in regularity (e.g., regularity of user data input), and so on. In some variations, the number of sleep parameters used to determine the sleep quality score can vary over time as data is collected. For example, sleep duration regularity can be determined using multiple sleep durations over multiple nights and can be a sleep parameter added to the determination of the sleep quality score after a predetermined number of nights (e.g., 3 nights, 5 nights, 7 nights, 14 nights).

[0123] In some variations, sleep quality scores can be based on a weighted combination of multiple subjective and / or objective sleep parameters. For example, a sleep quality score can be based on a weighted combination of two or more of the following: sleep duration, sleep efficiency, sleep latency, number of awakenings, wakefulness time, and sleep score. In some variations, each sleep parameter can be weighted equally or differently. For example, each sleep parameter such as sleep duration, sleep efficiency, sleep latency, number of awakenings, wakefulness time, sleep heart rate variability, etc., can be given equal weight, while the sleep score can be given a higher relative weight. As discussed above, sleep scores can correspond to predetermined scales such as Likert scales (e.g., a five-point scale).

[0124] An exemplary sleep quality score can be determined as shown in Table 1, where user data and sleep measurement data correspond to predetermined sleep score values ​​and are weighted to determine the sleep quality score.

[0125] Table 1 In some variations, the time range x Percentage range y Numerical range z ,score aThe score ranges (e.g., minimum, median, maximum) can be predetermined. For example, sleep duration can have a sleep quality score based on threshold sleep durations (e.g., less than 7 hours, between 7 and 9 hours, more than 9 hours) based on different age ranges (e.g., young adults, adults, older adults). However, any sleep parameter can be subgrouped based on age or other demographic categories. Sleep efficiency can have a sleep quality score based on predetermined scales (e.g., 0% to 100%) based on different age ranges, which may be the same as or different from the age range for sleep duration. Sleep latency and wakefulness time (e.g., sleep-onset wakefulness time (WASO)) can each have a sleep quality score based on predetermined time thresholds (e.g., up to 30 minutes, between 30 and 45 minutes, etc.). The number of awakenings can have a sleep quality score based on predetermined ranges (e.g., 0 to 1, 2 to 3, etc.). Sleep quality can be subjectively rated on a Likert scale of 1 to 5 and has corresponding scores.

[0126] In some variations, the sleep quality score can be the sum of the sleep quality values ​​for each sleep parameter, allowing the score to fall between a minimum and a maximum. In other variations, the sleep quality score can be proportionally adjusted so that the maximum score corresponds to a sleep quality score of 100. For example, ... FIG. 19 As shown, a below-standard health quality score (e.g., a below-standard sleep quality score) can be less than about 60 (e.g., less than about 60%), a moderate health score (e.g., a moderate physical health quality score) can be between about 60 and about 80 (e.g., between about 60% and about 80%), and a good health score (e.g., a mental health quality score) can be greater than about 80 (e.g., greater than about 80%).

[0127] In some variations, sleep quality scores can be determined periodically or at predetermined intervals (e.g., periodically, twice daily, daily, twice weekly, weekly, twice monthly, monthly). In some variations, sleep quality scores can be the same or different. For example, a weekly sleep quality score may include the average of daily sleep quality scores from the previous week (e.g., the past 7 days, the previous calendar week), while a monthly sleep quality score may include a weighted average of weekly sleep quality scores from the previous month (e.g., the past 4 weeks, starting from the first day of the calendar month) (e.g., where recent weeks are given greater weight than past weeks).

[0128] In some variations, a physical health quality score can be determined based on multiple subjective and / or objective physical health parameters, such as a physical health score (e.g., user input of subjective physical health), the number of physical discomforts, a maximum number of physical discomforts (e.g., the maximum discomfort input by the user, 5 / 5), the average severity of physical discomforts, etc. In some variations, the number of physical health parameters used to determine the physical health quality score can vary over time as data is collected.

[0129] In some variations, each physical health parameter can be weighted the same or different. For example, if no discomfort is reported, the physical health quality score can correspond only to the physical health score, or if no maximum discomfort is reported, the physical health quality score can correspond to the physical health score, the number of discomforts, and the average severity of discomfort. As discussed above, physical health parameters can correspond to predetermined scales such as Likert scales (e.g., a five-point scale).

[0130] If a user does not accurately input their discomfort, their physical health quality score may be inaccurately boosted. In some variations, if no discomfort is inputted within a predetermined amount of time, the user may receive one or more additional prompts to input their discomfort (e.g., 7 days, “For more personalized insights into your physical condition, make sure to track your specific discomfort when you check in in the morning”).

[0131] An exemplary physical health quality score can be determined as shown in Table 2, where user data corresponds to pre-determined physical health score values ​​and is equally weighted to determine the physical health quality score.

[0132] Table 2 In some variations, scoring a Numerical range x, y, z The score ranges (e.g., minimum, median, maximum) can be predetermined. For example, a physical health score can be subjectively assessed on a Likert scale of 1 to 5 and assigned a corresponding score. The number of physical discomforts, the maximum number of physical discomforts, and the average severity of physical discomforts can have corresponding physical health quality scores based on predetermined numerical ranges (e.g., 0, 1, 2, 3, 4, 5, 6 or more, 0 to 2, 3 to 5, etc.) for different age ranges (e.g., young people, adults, older people).

[0133] In some variations, the physical health quality score can be the sum of the physical health quality values ​​for each physical health parameter, such that the physical health quality score falls between a minimum and a maximum score. In some variations, the physical health quality score can be proportionally adjusted so that the maximum possible predetermined score corresponds to a physical health quality score of 100.

[0134] In some variations, physical health quality scores can be determined at predetermined intervals (e.g., periodically, twice daily, daily, twice weekly, weekly, twice monthly, monthly). In some variations, physical health quality scores can be weighted in the same or different ways. For example, a weekly physical health quality score may include the average of daily physical health quality scores from the previous week (e.g., the past 7 days, the previous calendar week), while a monthly physical health quality score may include the weighted average of weekly physical health quality scores from the previous month (e.g., the past 4 weeks, starting from the first day of the calendar month) (e.g., where recent weeks are given greater weight than past weeks).

[0135] In some variations, one or more of the sleep quality score, physical health quality score, and mental health quality score may be output to the user independently or in combination with the user health graph described herein. Additionally or alternatively, one or more of the sleep quality score, physical health quality score, and mental health quality score may be used to generate one or more of the shape and color of the user health graph.

[0136] In some variations, a negative physical health (e.g., body) score may correspond to a first physical health shape with a first color (e.g., red) (1620), a neutral physical health score may correspond to a second physical health shape with a different second color (e.g., yellow) (1622), and a positive sleep score may correspond to a third physical health shape with a third color (e.g., green) different from the first and second colors (1624). In some variations, a physical health score of 1 or 2 on a 5-point Likert scale may correspond to a negative physical health score, a physical health score of 3 may correspond to a neutral score, and a physical health score of 4 or 5 may correspond to a positive physical health score.

[0137] In some variations, a negative mental health (e.g., psychiatric) score may correspond to a first mental health shape with a first color (e.g., red) (1630), a neutral mental health score may correspond to a second mental health shape with a different second color (e.g., yellow) (1632), and a positive sleep score may correspond to a third mental health shape with a third color (e.g., green) different from the first and second colors (1634). In some variations, a mental health score of 1 or 2 on a 5-point Likert scale may correspond to a negative mental health score, a mental health score of 3 may correspond to a neutral score, and a mental health score of 4 or 5 may correspond to a positive mental health score. In some variations, the predetermined scale may be an n-subscale.

[0138] It should be understood that although the above description uses the same colors to represent the same levels (e.g., negative, neutral, positive) in sleep scores, physical health scores, and mental health scores, this need not be the case, and each of the sleep scores, physical health scores, and mental health scores can have its own color scheme to represent different levels.

[0139] In some variations, the arrangement of the first, second, and third shapes of the user health graph on the graphical user interface can be based on corresponding sleep and health scores. For example, FIG. 17A to FIG. 17AA The different colors and spatial arrangements of the first shape (1730), the second shape (1740), and the third shape (1750) are depicted.

[0140] In some variations, each of the first shape (1730), the second shape (1740), and the third shape (1750) includes a two-dimensional geometric shape. For example, the shape can be any two-dimensional shape, such as a circle, an ellipse, a square, a polygon, a combination thereof, etc. However, in some variations, one or more of the shapes can include a three-dimensional geometric shape. For example, a three-dimensional geometric shape can include a sphere, a cylinder, a cone, a cube, a cuboid, a polyhedron, a torus, a pyramid, a prism, a combination thereof, etc.

[0141] For example, the positions of the first, second, and third shapes can be arranged based on sleep scores, physical health scores, and mental health scores relative to a first axis of the user's health graph. In some variations, the first axis can be the vertical axis of the user's health graph (e.g., the Y-axis). In some variations, the vertical axis of the user's health graph can be the vertical axis of the display, while in other variations, it can be the horizontal axis of the display (e.g., the X-axis). The first shape may include a first center, the second shape may include a second center, and the third shape may include a third center. In some variations, the center-to-center distance between the first and second shapes can be based on the difference between two of the sleep scores, physical health scores, and mental health scores. For example, in FIG. 17H In this context, the center-to-center distance between the first shape (1730) and the second shape (1740) is based on the difference between the ratings of the first shape and the second shape. That is, compared to the distance and rating between the first shape (1730) and the third shape (1750), the relatively long center-to-center distance between the first shape (1730) and the second shape (1740) reflects the large difference between the positive rating of the first shape (1730) (e.g., green) and the negative rating of the second shape (1740) (e.g., red).

[0142] exist FIG. 17A In the variant shown, the first center, second center, and third center are located on the first axis. Similarly, as... FIG. 17A As shown, the centers of two or more of the first, second, and third shapes are spaced apart from each other along the first axis. Furthermore, the first shape (1730), second shape (1740), and third shape (1750) partially overlap along the first axis. FIG. 17A In this model, the first center, the second center, and the third center are spaced apart along the first axis by equal center-to-center distances. Furthermore, in... FIG. 17A In the variation shown, all three shapes have the same color, which indicates that all three scores are within the same range (e.g., all positive). Furthermore, the vertical and linear arrangement of the three shapes indicates that the three scores are within the same range.

[0143] exist FIG. 17B and FIG. 17C In the variant shown, the first and second centers of the first and second shapes (1730, 1740) are located on the first axis, and the third center of the third shape (1750) is offset relative to the first axis (e.g., laterally offset relative to the first axis). For example, the first shape (1730) and the second shape (1740), which have green color and corresponding positive scores, are located on the first axis, while... FIG. 17B The third shape (1750), which has yellow and neutral ratings, is laterally offset relative to the first axis. Similarly,FIG. 17C The third shape (1750), which has red and negative scores, is laterally offset relative to the first axis. The difference in shape scores determines the degree of offset between shapes. For example, the center-to-center distance between the second shape (1740) and the third shape (1750) is... FIG. 17C China and Belgium in FIG. 17B It is larger in the middle.

[0144] In some variations, one of the first, second, and third centers is located on the first axis, and the other two of the first, second, and third centers are offset relative to the first axis and are on the same side or opposite sides of the first axis. FIG. 17F , FIG. 17N , FIG. 17V and FIG. 17AA In the variation shown, the first axis is an angled axis between the vertical axis and the horizontal axis of the user health graph. For example, the angled axis is shown as approximately 45 degrees, but it can be any angle between the vertical and horizontal axes (e.g., approximately 15 degrees, approximately 30 degrees, approximately 45 degrees, approximately 60 degrees, approximately 75 degrees).

[0145] like FIG. 17F , FIG. 17H , FIG. 17L , FIG. 17P , FIG. 17T , FIG. 17V and FIG. 17AA As shown, the centers of two or more of the first, second, and third shapes are offset from each other relative to the first axis, and / or the first, second, and third centers are offset laterally from each other. For example, each of the first, second, and third shapes may have a different color / rating.

[0146] FIG. 18 and FIG. 19 These are a set of exemplary variations of the Health Status Graphics and Sleep Insights graphical user interface, which are configured to facilitate an intuitive and rapid understanding of a user’s overall health (e.g., sleep, physical health, mental health) through a combination of graphical and textual forms.

[0147] FIG. 18 The sixty-second GUI (1800) is depicted, which includes a health status graph (1810) and an insight (1820) that provides a textual summary of the health status graph (1810) for a predetermined time period. In some variations, the health status graph (1810) may include overlays of text (1830) indicating parameters (e.g., sleep, physical health, mental health) and ratings (e.g., below average, average, good).

[0148] FIG. 19The sixty-third GUI (1900) is depicted, comprising a health status graph (1910) and insights (1920) for a predetermined time period (e.g., month), which provide a plain-language text summary corresponding to the health status graph (1910). In some variations, the health status graph (1910) may include overlays of text (1940) indicating parameters (e.g., sleep, physical health, mental health) and ratings (e.g., below average, average, good). In some variations, GUI 1900 may include a set of rating thresholds (1930) corresponding to health quality ratings (e.g., sleep quality rating, physical health quality rating, mental health quality rating).

[0149] Optionally, in some variations, an animation (440) of multiple user health graphs can be generated. For example, the animation can sequentially display updated user health graphs and one or more previous user health graphs corresponding to predetermined time periods (e.g., one week, two weeks, three weeks, one month) to allow users to measure their health status over time.

[0150] Optionally, in some variations, the process (400) may include one or more of providing actionable recommendations (450) to the user based on the user's health graph and clinical referral (460). In some variations, actionable recommendations may include modifying computing device settings based on the user's health graph.

[0151] Example FIG. 5A and FIG. 5B It is a set of exemplary wake-up time graphical user interfaces (GUIs). FIG. 5A The first GUI (500) and FIG. 5B The second GUI (502) may include corresponding prompts (510, 512) configured to prepare and / or instruct the user (e.g., after sleep) to complete a wake-up assessment (e.g., morning check-in) at or shortly after waking up at the start of a new day (e.g., within 15 minutes, 30 minutes, 60 minutes, 15 to 30 minutes, or 15 to 60 minutes of the wake-up time). User data collected before and after this time may include sleep data, physical health data, and mental health data, which can be used to predict the risk of one or more sleep-related disorders. Sleep measurement data may also be collected before and after this time, if available. A forward icon (520, 522) can be selected to proceed to the wake-up assessment GUI (e.g., FIG. 6A to FIG. 8 Upon completion of the assessment, FIG. 5C The third GUI (504) and FIG. 5DThe fourth GUI (506) can include corresponding prompts (514, 516) configured to indicate that the assessment is complete and / or provide encouragement to continue completing the assessment. A forward icon (524, 526) can be selected to proceed to, for example, the Insights GUI.

[0152] FIG. 6A to FIG. 6D , FIG. 7A to FIG. 7H and FIG. 8 This is a set of exemplary wake-up assessment GUIs configured to track wake-up moments based on subjective user-reported outcomes and objective sleep measurement data to predict the risk of one or more sleep-related disorders. For example, FIG. 6A The fifth GUI (600) and FIG. 6B The sixth GUI (602) may include corresponding prompts (610, 612) for the user's sleep data. In some variations, the measurement data (630) received from the measuring device may include the user's sleep data, including bedtime (620), sleep onset time (622), wake-up time (624), and total sleep time (626). These and other measured sleep parameters may be displayed and pre-filled on the fifth GUI (600) and the sixth GUI (602). However, any of these sleep parameters (e.g., 620, 622, 624, etc.) may be selected and modified by the user to confirm and increase the accuracy of the sleep data. In this way, in addition to the sleep data measured from the measuring device, subjective user-reported sleep results may also be entered. In some variations, the GUI may include a sleep data graph (640) based on the sleep data. A forward icon (650) may be selected to proceed to the next GUI, such as a wake-up assessment. FIG. 6C A seventh GUI (604) is depicted, which includes a wake-up count prompt (660), a wake-up duration prompt (662), a wake-up reason prompt (664), and a forward icon (650). The user can select a predetermined wake-up reason and / or input a wake-up reason. In some variations, the user can select a custom icon (not shown) configured to receive user input to add one or more custom wake-up reasons. FIG. 6D An eighth GUI (606) is depicted, which includes snoring status prompts (666) (e.g., I don't know, no, yes) and a forward icon (650).

[0153] FIG. 7A A ninth GUI (700) is depicted, which includes a bodily status prompt (720) for wake-up time assessment and a forward icon (790). For example, a user can select a bodily status based on a five-point scale (e.g., poor, unsatisfactory, average, good, excellent). FIG. 7BA tenth GUI (702) is depicted, which includes a body discomfort location indicator (730) and a forward icon (790). For example, the user can select one or more predefined body parts that exhibit body discomfort (e.g., head, neck, chest, abdomen, arms and hands, legs and feet). FIG. 7C An eleventh GUI (704) is depicted, which includes a bodily discomfort type prompt (740) and a forward icon (790). For example, a user can select one or more predefined types of bodily discomfort (e.g., headache, tension, dizziness, fever, sinusitis, eye pain, runny nose, double vision) associated with a selected body part (e.g., head). In some variations, the user can select a custom icon (not shown) configured to receive user input to add one or more custom bodily symptoms and / or emotions.

[0154] FIG. 7D A twelfth GUI (706) is depicted, which includes a physical discomfort intensity indicator (750) and a forward icon (790). For example, the user can select an intensity level (e.g., on a five-point scale of mild, tolerable, moderate, severe, and serious) corresponding to the selected physical discomfort (e.g., dizziness) and the selected body part (e.g., head). FIG. 7E A thirteenth GUI (708) is depicted, which includes a body discomfort location indicator (760) and a forward icon (790). The GUI (708) can be used as a confirmation screen to ensure that the selected body discomfort location, type, and intensity are accurately reflected. FIG. 7F A fourteenth GUI (710) is depicted, which includes a body discomfort prompt (760) that includes previously entered user data and a forward icon (790). Users can include additional body discomfort as needed. FIG. 7G and FIG. 7H A corresponding fifteenth GUI (712) and a sixteenth GUI (714) are depicted, which include a discomfort type prompt (780, 782) and a forward icon (790). The GUIs (712, 714) can be configured to receive one or more of the following: discomfort location (e.g., back pain), discomfort type (e.g., eye pain), and discomfort intensity (e.g., 2, 4).

[0155] FIG. 8A seventeenth GUI (800) is depicted, which includes a wake-up time recording prompt (810) and a forward icon (820) for optional user input. In some variations, the wake-up time recording may include the user's wake-up time thoughts, which might otherwise not be captured by sleep parameters. If not entered at the wake-up time, these thoughts may be quickly forgotten by the user. In some variations, one or more check-in GUIs in the check-in GUI may include treatment and / or medication prompts for the user to enter one or more of the treatments the user has received and / or completed, and the medications the user has taken.

[0156] FIG. 9A and FIG. 9B The corresponding eighteenth GUI (900) and nineteenth GUI (902) are depicted, which include evaluation prompts (910, 912) that can indicate the evaluation status (e.g., completed, evaluation time, next evaluation time). In some variations, the user can select an edit icon (not shown) configured to receive user input to edit one or more check-ins. In some variations, one or more GUIs (e.g., FIG. 5A to FIG. 5D , FIG. 9A , FIG. 9B This could include a count of consecutive check-ins performed by the user or other elements (such as icons) to encourage regular check-in input.

[0157] FIG. 10A to FIG. 10G This is a set of exemplary variants of the Sleep Insights GUI, which is configured to provide trends, analyses, and insights into a user's sleep and health based on sleep data. The Sleep Insights GUI can provide context and meaning to sleep data that is useful to both users and healthcare professionals. For example, FIG. 10AThe twentieth GUI (1000) may include prompts (1012) corresponding to predetermined time periods (1010) (e.g., daily, weekly, bi-weekly, monthly, bi-monthly, yearly) of common language insights (e.g., trends, patterns, data analysis). Common language facilitates quick, simple, and useful information exchange. Search icons (1020, 1022) (e.g., search fields) may be configured to receive expert-related user input. For example, a user may respond to prompts (1012) by selecting a search icon (1020) to input a query via text or voice. In some variations, the user may input text or audio. A dashboard may be provided that includes one or more sleep trends, including physical (e.g., bodily) discomfort (1030), configured to outline a set of body parts (1032), types of discomfort (e.g., headache, eye pain), and intensity of discomfort (e.g., headache intensity levels of 1, 1, 2, 3, 3, 4, and 5 during the week of January 15-21).

[0158] FIG. 10B A twenty-first GUI (1002) is depicted, which includes a dashboard of sleep trends over a predetermined time period (e.g., January 15 to 21), including physical discomfort (1030), average sleep oxygen saturation (1034), and average sleep heart rate (1036). In some variations, the dashboard view may include data for selectable predetermined time periods (e.g., the past week, past month, past three months, past six months, past year). FIG. 10C A twenty-second GUI (1004) is described, which includes colloquial prompts (1012) summarizing the user's health status based on sleep data. A dashboard including one or more sleep trends, including average sleep quality (1038), can be provided. The one or more sleep trends can be depicted using graphs, charts, and other visualizations. FIG. 10D A twenty-third GUI (1006) is depicted, which includes a dashboard of one or more sleep trends such as body discomfort location (1040) and average time in bed (1042). FIG. 10E The twenty-fourth GUI (1008) is depicted, which includes one or more dashboards of sleep trends such as average snoring time (1044). FIG. 10F A twenty-fifth GUI (1010) is depicted, which includes dashboards for one or more sleep trends such as user input records (1046) and average heart rate (1048). As described herein, sleep trends may include sleep data from both subjective user data and objective sleep measurements.

[0159] FIG. 10G A twenty-sixth GUI (1011) is depicted, which includes a prompt (1012) corresponding to a trend summary (e.g., major sleep disturbances). In some variations, the colloquial prompt may be followed by more detailed sleep trend data, such as a dashboard including snoring data (1050) corresponding to an audio waveform recording that can be heard using a playback icon (1052).

[0160] In some variations, the sleep insight graphical user interface described in this paper (e.g., FIG. 10A to FIG. 10G Either of these can include a default overview view and an optional actionable tip that provides one or more of the actionable suggestions and additional information (e.g., a detail view) about the tip (e.g., tip 1012).

[0161] FIG. 11A and FIG. 11B These are a set of exemplary variants of the sleep disorder risk prediction GUI, which is configured to promote early identification of sleep-related disorders and provide enhanced awareness and education on sleep-related disorders, as well as action recommendations.

[0162] FIG. 11A and FIG. 11B The corresponding 27th GUI (1100) and 28th GUI (1102) are described, which include mean sleep oxygen saturation level (1132) and sleep disorder risk prediction prompts (1112), actionable suggestion prompts for additional sleep disorder information (1120), and mean heart rate variability (1134). In some variations, the actionable suggestion prompts (1120) can encourage users to take proactive clinical action. FIG. 11B In the meantime, actionable suggestions (1120) may include a link (1140) to install a diagnostic application (e.g., an obstructive sleep apnea diagnostic application) on a computing device.

[0163] FIG. 12 A twenty-ninth GUI (1200) is described, which includes actionable suggestion prompts (1230) and a list of selectable actionable suggestions, such as earlier bedtime suggestions, snoring recordings, oxygen saturation information, clinical service referrals (e.g., specialists), and downloading HCP reports (1240). In some variations, the prompts (1230) may be generated based on sleep data (e.g., personalized for each user) to promote improvements in sleep and health. In some variations, the actionable suggestions may encourage healthy behaviors (e.g., earlier bedtime, consulting a specialist).

[0164] FIG. 13 A 30th GUI (1300) is described, which facilitates referrals to sleep services and / or other clinical actions, including prompting (1340) to share sleep and health reports with healthcare professionals for predetermined time periods (1310) (e.g., weekly, monthly). In some variations, mobile applications or web portals, as described herein, can generate sleep and health reports. FIG. 14A and FIG. 14B Corresponding GUIs 31 (1402) and 32 (1404) are described, which include a sleep and health report comprising one or more sleep trends, sleep data, and user records (e.g., wake-up time records, bedtime records). In some variations, one or more of the content and format of the sleep and health report may be customized by a healthcare professional. The sleep and health report may include any of the user data and sleep measurement data described herein.

[0165] In some variations, sleep insights can be derived from a graphical user interface (e.g., FIG. 10A to FIG. 10G ), sleep disorder prediction graphical user interface (e.g., FIG. 11A to FIG. 11B ), referral graphical user interface (e.g., FIG. 13 ) and health status reports (e.g., FIG. 14A to FIG. 14B One or more of the ultrasound audio signals are accessed (e.g., output, graphical representation) in a sleep and health report.

[0166] FIG. 15A and FIG. 15B It is a set of exemplary variations of the health status graphical user interface. FIG. 15A and FIG. 15B The corresponding thirty-third GUI (1500) and thirty-fourth GUI (1502) are depicted, which include a first shape (1510), a second shape (1512), and a third shape (1514). A first line (1520) connects the center of the first shape (1510) to the center of the second shape (1512), and a second line (1522) connects the center of the second shape (1512) to the center of the third shape (1514). In some variations, the health status graph may be displayed on the introductory GUI and / or combined with sleep trends and sleep disorder risk predictions.

[0167] FIG. 17A to FIG. 17AAThis is a set of exemplary variations of a health status graph configured to facilitate an intuitive and rapid understanding of a user's overall health (e.g., sleep, physical health, mental health). The health status graph may include a first shape (1730) with a first color and a first center, a second shape (1740) with a second color and a second center, and a third shape (1750) with a third color and a third center. Optionally, a first line (1735) may connect the centers of the first shape (1730) and the second shape (1740), and a second line (1745) may connect the centers of the second shape (1740) and the third shape (1750). A first axis corresponds to the vertical axis of the health status graph, and a second axis corresponds to the horizontal axis of the health status graph. As discussed herein, colors may correspond to ratings on a scale (e.g., negative, neutral, positive, 1, 2, 3, 4, 5). For example, green may be associated with positive ratings for parameters (e.g., sleep, physical health, mental health), yellow may be associated with neutral ratings, and red may be associated with negative ratings. In this way, health ratings can be based on the color of the shape and / or its relative position. For example, a health rating can be based on the color of the shape and its relative position to each other and / or a predetermined axis.

[0168] In some variations, such as FIG. 17A to FIG. 17AA As shown, each of the first, second, and third colors can include a color gradient. However, in other variations, one or more colors may not have a color gradient. In some variations, such as FIG. 17A to FIG. 17AA As shown, each of the first shape (1730), the second shape (1740), and the third shape (1750) may include an opacity gradient. However, in other variations, one or more of the shapes may not have an opacity gradient.

[0169] In some variations, such as FIG. 17A to FIG. 17AA As shown, the background of a graphical user interface can include a color gradient. However, the background can also include a non-color gradient background (e.g., the default background color).

[0170] FIG. 17AThe thirty-fifth GUI (1700) is depicted, in which a first shape (1730), a second shape (1740), and a third shape (1750) correspond to positive colors. Each of the first shape (1730), the second shape (1740), and the third shape (1750) lies on a first axis (e.g., the vertical axis of the GUI (1700) passing through the midpoint of the GUI (1700), and is not shown). Similarly, the center of each of the first shape (1730), the second shape (1740), and the third shape (1750) lies on the first axis. In addition, a first line (1735) and a second line (1745) also lie on the first axis. The first line (1735) and the second line (1745) each overlap with two of the first, second, and third shapes. More specifically, the first line (1735) overlaps with the first shape (1730) and the second shape (1740), while the second line (1745) overlaps with the second shape (1740) and the third shape (1750). In some variations, the centers of two or more of the first, second, and third shapes may be spaced apart from each other along the first axis. For example, the first shape (1730), the second shape (1740), and the third shape (1750) may partially overlap along the first axis, but the centers of the first, second, and third shapes may be located at different points along the first axis. In some variations, the perimeter of one shape may intersect with the center of another shape, or with the centers of two of the other three shapes. Specifically, see [reference needed]. FIG. 17A In the variant depicted, the periphery (e.g., circumference) of the second shape (1740) may intersect the center of the first shape (1730) and the center of the second shape (1750). In other variants, for example, FIG. 17B In the variant depicted, the periphery of the second shape (1740) may intersect the center of the first shape (1730), but may not intersect the center of the third shape (1750). In other variants, the periphery of the second shape (1740) may not intersect the center of either the first or third shape. FIG. 17A In the diagram, the first center, the second center, and the third center are spaced apart along the first axis by equal center-to-center distances. Although not shown, in some variations, all three shapes may overlap each other (whether or not they are aligned with the axis).

[0171] FIG. 17B The thirty-sixth GUI (1701) is depicted, where the first shape (1730) corresponds to a positive color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a neutral color. FIG. 17BIn this configuration, the first center of the first shape (1730) and the second center of the second shape (1740) are located on the first axis, while the third center of the third shape (1750) is offset relative to the first axis. In other words, the first shape is aligned with the second shape (1730, 1750), but not with the third shape (1750). In this way, the first line (1735) and the second line (1745) form a non-zero angle relative to the first axis. FIG. 17B This illustrates that the overlap of shapes is unrestricted. For example, the second shape (1740) and the third shape (1750) can partially overlap along an angle offset relative to the first axis. FIG. 17D , FIG. 17F , FIG. 17H , FIG. 17J , FIG. 17K And other examples illustrating partial overlap of shapes.

[0172] In some variations, the center-to-center distance between the first and second shapes can be based on the difference between two of the sleep score, physical health score, and mental health score. Furthermore, the color and position of the third shape (1750) relative to the other shapes indicate to the user the difference between the corresponding scores of the third shape (1750) and the first and second shapes (1740). For example, the first and second shapes (1730 and 1740) correspond to positive scores (e.g., positive sleep score, positive physical health score), while the third shape (1750) corresponds to a neutral score (e.g., neutral mental health score).

[0173] FIG. 17C The thirty-seventh GUI (1702) is depicted, in which the first shape (1730) and the second shape (1740) each have green corresponding to a positive rating, and the third shape (1750) has red corresponding to a negative rating. FIG. 17C In the diagram, the first center of the first shape (1730) and the second center of the second shape (1740) are located on the first axis, while the third center of the third shape (1750) is offset relative to the first axis. As described herein, the first line (1735) and the second line (1745) form an angle between the first axis and the horizontal axis. The color and position of the third shape (1750) indicate to the user the difference between the corresponding ratings of the third shape (1750) and the first shape (1730) and the second shape (1740). FIG. 17C The third shape (1750) relative to FIG. 17B The third shape (1750) has a higher score difference.

[0174] FIG. 17DThirty-eight GUIs (1703) are depicted, where the first shape (1730) corresponds to a positive color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a positive color. FIG. 17D In the first shape (1730), the first center and the third center of the third shape (1750) are located on the first axis, while the second center of the second shape (1740) is offset relative to the first axis.

[0175] FIG. 17E The thirty-ninth GUI (1704) is depicted, in which the first shape (1730) corresponds to a positive color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a neutral color. FIG. 17E In the first shape (1730), the first center is located on the first axis, while the second center of the second shape (1740) and the third center of the third shape (1750) are offset relative to the first axis. FIG. 17E A variation is depicted in which the centers of two or more of the first, second, and third shapes are offset from each other relative to the first axis.

[0176] FIG. 17F The fortieth GUI (1705) is depicted, where the first shape (1730) corresponds to a positive color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a negative color. In some variations, the first, second, and third centers are laterally offset from each other. The first line (1735) and the second line (1745) form an angle (e.g., approximately 15 degrees, approximately 30 degrees, approximately 45 degrees, and approximately 60 degrees) between the vertical and horizontal axes of the user health graphic.

[0177] FIG. 17G The forty-first GUI (1706) is depicted, in which the first shape (1730) corresponds to a positive color, the second shape (1740) corresponds to a negative color, and the third shape (1750) corresponds to a positive color. FIG. 17G In the diagram, the first center of the first shape (1730) and the third center of the third shape (1750) are located on the first axis, while the second center of the second shape (1740) is offset relative to the first axis. The color and position of the second shape (1740) indicate to the user the difference between the corresponding ratings of the second shape (1740) and the first and third shapes (1750). The color and position of the first shape (1730) and the third shape (1750) indicate the consistency of their ratings.

[0178] FIG. 17HThe forty-second GUI (1707) is depicted, where a first shape (1730) corresponds to a positive color, a second shape (1740) corresponds to a negative color, and a third shape (1750) corresponds to a neutral color. The first center of the first shape (1730) is located on the first axis, while the second center of the second shape (1740) and the third center of the third shape (1750) are offset relative to the first axis. The color and position of each shape in the shapes indicate to the user the difference in rating between each shape in the shapes in the case that all ratings do not match.

[0179] FIG. 17I The forty-third GUI (1708) is depicted, in which a first shape (1730) corresponds to a positive color, a second shape (1740) corresponds to a negative color, and a third shape (1750) corresponds to a negative color. The first center of the first shape (1730) is located on the first axis, while the second center of the second shape (1740) and the third center of the third shape (1750) are offset relative to the first axis. The color and position of the first shape (1730) indicate to the user the difference between the corresponding ratings of the second shape (1740) and the third shape (1750) relative to the first shape (1730). The color and position of the second shape (1740) and the third shape (1750) indicate the consistency of their ratings.

[0180] FIG. 17J The forty-fourth GUI (1709) is depicted, in which a first shape (1730) corresponds to a neutral color, a second shape (1740) corresponds to a positive color, and a third shape (1750) corresponds to a positive color. The first center of the first shape (1730) is offset relative to a first axis, while the second center of the second shape (1740) and the third center of the third shape (1750) are located on the first axis. The color and position of the first shape (1730) indicate to the user the difference between the corresponding ratings of the first shape (1730) and the second and third shapes (1740 and 1750). The color and position of the second and third shapes (1740 and 1750) indicate the consistency of their ratings.

[0181] FIG. 17K The forty-fifth GUI (1710) is depicted, in which the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a neutral color. FIG. 17KIn the diagram, the second center of the second shape (1740) is located on the first axis, while the first center of the first shape (1730) and the third center of the third shape (1750) are offset relative to the first axis. The color and position of the second shape (1740) indicate to the user the difference between the corresponding ratings of the second shape (1740) and the first shape (1730) and the third shape (1750). The color and position of the first shape (1730) and the third shape (1750) indicate the consistency of their ratings (e.g., a neutral rating).

[0182] FIG. 17L The forty-sixth GUI (1711) is depicted, where the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a negative color. FIG. 17L In the first shape (1740), the second center is located on the first axis, while the first center of the first shape (1730) and the third center of the third shape (1750) are offset relative to the first axis.

[0183] FIG. 17M The forty-seventh GUI (1712) is depicted, in which the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a positive color. FIG. 17M In the diagram, the third center (1750) of the third shape is located on the first axis, while the first center (1730) of the first shape and the second center (1740) of the second shape are offset relative to the first axis. The color and position of the third shape (1750) indicate to the user the difference between the corresponding ratings of the third shape (1750) and the first and second shapes (1740). The color and position of the first shape (1730) and the second shape (1740) indicate the consistency of their ratings (e.g., a neutral rating).

[0184] FIG. 17N The forty-eighth GUI (1713) is depicted, in which the first shape (1730), the second shape (1740), and the third shape (1750) correspond to a neutral color. When each shape has a neutral color, these shapes can be aligned at an angle (e.g., approximately 15 degrees, approximately 30 degrees, approximately 45 degrees, approximately 60 degrees, approximately 75 degrees) relative to the vertical axis of the GUI to indicate a neutral user health status. For example, a neutral user health status can have a positive angle (…). FIG. 17N ), while a negative user health status can have a negative angle ( FIG. 17AA In some variations, the first axis can be an angled axis between the vertical axis and the horizontal axis of the user health graph.

[0185] FIG. 17O The forty-ninth GUI (1714) is depicted, in which the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a negative color.

[0186] FIG. 17P The fiftieth GUI (1715) is depicted, where the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a negative color, and the third shape (1750) corresponds to a positive color. FIG. 17P In the first shape (1750), the third center is located on the first axis, while the first center of the first shape (1730) and the third center of the third shape (1750) are offset relative to the first axis.

[0187] FIG. 17Q The fifty-first GUI (1716) is depicted, in which the first shape (1730) corresponds to a neutral color, the second shape (1740) corresponds to a negative color, and the third shape (1750) corresponds to a neutral color.

[0188] FIG. 17R The fifty-second GUI (1717) is depicted, in which a first shape (1730) corresponds to a neutral color, a second shape (1740) corresponds to a negative color, and a third shape (1750) corresponds to a negative color. The color and position of the first shape (1730) indicate to the user the difference between the corresponding ratings of the first shape (1730) and the second and third shapes (1740). The color and position of the second and third shapes (1750) indicate the consistency of their ratings (e.g., negative ratings).

[0189] FIG. 17S The fifty-third GUI (1718) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a positive color. FIG. 17S In the diagram, the second center of the second shape (1740) and the third center of the third shape (1750) are located on the first axis, while the first center of the first shape (1730) is offset relative to the first axis. The color and position of the first shape (1730) indicate to the user the difference between the corresponding ratings of the first shape (1730) and the second and third shapes (1750). The color and position of the second shape (1740) and the third shape (1750) indicate the consistency of their ratings (e.g., positive ratings).

[0190] FIG. 17TThe fifty-fourth GUI (1719) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a neutral color. FIG. 17T In the first shape (1740), the second center is located on the first axis, while the first center of the first shape (1730) and the third center of the third shape (1750) are offset relative to the first axis and are on opposite sides of the axis.

[0191] FIG. 17U The fifty-fifth GUI (1720) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a positive color, and the third shape (1750) corresponds to a negative color. FIG. 17U In the first shape (1740), the second center is located on the first axis, while the first center (1730) of the first shape and the third center (1750) of the third shape are offset relative to the first axis and are on the same side of the axis.

[0192] FIG. 17V The fifty-sixth GUI (1721) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a neutral color, and the third shape (1750) corresponds to a positive color. In some variations, the first axis may be an angled axis between the vertical axis and the horizontal axis of the user health graph (e.g., with a negative slope).

[0193] FIG. 17W The fifty-seventh GUI (1722) is depicted, in which a first shape (1730) corresponds to a negative color, a second shape (1740) corresponds to a neutral color, and a third shape (1750) corresponds to a neutral color. The color and position of the first shape (1730) indicate to the user the difference between the corresponding ratings of the first shape (1730) and the second and third shapes (1740). The color and position of the second and third shapes (1750) indicate the consistency of their ratings (e.g., a neutral rating).

[0194] FIG. 17X The fifty-eighth GUI (1723) is depicted, in which a first shape (1730) corresponds to a negative color, a second shape (1740) corresponds to a neutral color, and a third shape (1750) corresponds to a negative color. The color and position of the second shape (1740) indicate to the user the difference between the corresponding ratings of the second shape (1740) and the first shape (1730) and the third shape (1750). The color and position of the first shape (1730) and the third shape (1750) indicate the consistency of their ratings (e.g., negative ratings).

[0195] FIG. 17Y The fifty-ninth GUI (1724) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a negative color, and the third shape (1750) corresponds to a positive color. FIG. 17Y In the first shape (1750), the third center is located on the first axis, while the first center of the first shape (1730) and the second center of the second shape (1740) are offset relative to the first axis.

[0196] FIG. 17Z The sixtieth GUI (1725) is depicted, in which the first shape (1730) corresponds to a negative color, the second shape (1740) corresponds to a negative color, and the third shape (1750) corresponds to a neutral color.

[0197] FIG. 17AA The sixty-first GUI (1726) is depicted, in which a first shape (1730) corresponds to a negative color, a second shape (1740) corresponds to a negative color, and a third shape (1750) corresponds to a negative color. In some variations, the first axis may be an angled axis (e.g., having a negative slope) between the vertical axis and the horizontal axis of the user health graph.

[0198] For purposes of explanation, specific terminology has been used in the foregoing description to provide a comprehensive understanding of the invention. However, it will be apparent to those skilled in the art that specific details are not required to practice the invention. Therefore, for purposes of illustration and description, the foregoing description of specific embodiments of the invention is presented. They are not intended to be exhaustive or to limit the invention to the precise forms disclosed; obviously, many modifications and variations are possible in light of the foregoing teachings. The embodiments were chosen and described to explain the principles of the invention and its practical application, thus enabling others skilled in the art to utilize the invention and various embodiments with various modifications to suit a particular intended use. The following claims and their equivalents are intended to define the scope of the invention.

Claims

1. A method for graphically representing user health, comprising: The system receives user data, including sleep scores, multiple physical health parameters, and mental health scores, from the computing device, and receives sleep measurement data from the measurement device. A sleep quality score is generated based on the sleep score and the sleep measurement data; a physical health quality score is generated based on the multiple physical health parameters; and a mental health quality score is generated based on the mental health score. Generating a user health graph on the graphical user interface of the computing device, wherein the generation includes: A first shape is generated based on the sleep quality score, a second shape is generated based on the physical health quality score, and a third shape is generated based on the mental health quality score. as well as The positions of the first shape, the second shape, and the third shape relative to the first axis of the user health graph are arranged based on the sleep quality score, the physical health quality score, and the mental health quality score.

2. The method of claim 1, further comprising periodically generating the sleep quality score, the physical health quality score, and the mental health quality score.

3. The method of claim 1, wherein the sleep measurement data includes one or more of the following: sleep duration, sleep efficiency, sleep latency, number of awakenings, wakefulness time, and sleep quality.

4. The method of claim 1, wherein the sleep quality score is based on a weighted sum of the sleep score and the sleep measurement data.

5. The method of claim 4, wherein the weighting is based on time.

6. The method of claim 1, wherein the plurality of physical health parameters includes two or more of the following: physical health score, number of physical discomforts, maximum number of physical discomforts, and average severity of physical discomforts.

7. The method of claim 1, wherein the physical health quality score is based on a weighted sum of the plurality of physical health parameters.

8. The method of claim 7, wherein the weighting is based on time.

9. The method of claim 1, wherein each of the plurality of physical health parameters corresponds to a predetermined scale.

10. The method of claim 9, wherein the predetermined scale is a Likert scale.

11. The method of claim 1, wherein generating the user health graph comprises alphanumeric representations of the sleep quality score, the physical health quality score, and the mental health quality score.

12. The method of claim 1, wherein the user data and the sleep measurement data are each received at one or more predetermined intervals.

13. The method of claim 12, wherein the predetermined interval is at least once a day.

14. The method of claim 1, wherein the first axis is the vertical axis of the user health graph.

15. The method of claim 1, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are located on the first axis.

16. The method of claim 1, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein two of the first center, the second center, and the third center are located on the first axis, and the third of the first center, the second center, and the third center is offset relative to the first axis.

17. The method of claim 1, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein one of the first center, the second center, and the third center is located on the first axis, and the other two of the first center, the second center, and the third center are offset relative to the first axis and are on opposite sides of the first axis.

18. The method of claim 1, wherein the first axis is an axis that forms an angle between the vertical axis of the user health graph and the horizontal axis of the user health graph.

19. The method of claim 1, wherein the center-to-center distance between the first shape and the second shape is based on the difference between the sleep score, the physical health score, and the mental health score.

20. The method of claim 1, wherein the centers of two or more of the first shape, the second shape, and the third shape are spaced apart from each other along the first axis.

21. The method of claim 1, wherein the centers of two or more of the first shape, the second shape, and the third shape are offset from each other relative to the first axis.

22. The method of claim 1, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are laterally offset from each other.

23. The method of claim 22, wherein the first shape, the second shape, and the third shape partially overlap along the first axis.

24. The method of claim 22, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are spaced apart along the first axis by equal center-to-center distances.

25. The method of claim 1, wherein generating the user health graph includes generating a plurality of lines, wherein each of the plurality of lines overlaps with two of the first shape, the second shape, and the third shape.

26. The method of claim 25, wherein the plurality of lines comprises a first line between the center of the first shape and the center of the second shape and a second line between the center of the second shape and the center of the third shape.

27. The method of claim 1, wherein each of the first shape, the second shape, and the third shape comprises a two-dimensional geometry.

28. The method of claim 1, wherein each of the first color, the second color, and the third color includes a color gradient.

29. The method of claim 1, wherein each of the first color, the second color, and the third color includes an opacity gradient.

30. The method of claim 1, wherein the background of the graphical user interface includes a color gradient.

31. The method of claim 1, further comprising periodically updating the user health graph.

32. The method of claim 31, further comprising generating an animation, the animation including the updated user health graph and one or more previous user health graphs.

33. The method of claim 1, further comprising using the computing device to output a notification for inputting the user data, wherein the notification is output at predetermined intervals.

34. The method of claim 1, further comprising modifying computing device settings based on the user health graph.

35. The method of claim 1, further comprising referring a sleep service to the user based on the user health graph.

36. The method of claim 1, further comprising: Based on the user data and the sleep measurement data, predict the risk of one or more sleep disorders; as well as Refer sleep services to users based on the predicted risk of one or more of the aforementioned sleep disorders.

37. The method of claim 36, wherein the sleep measurement data includes one or more sleep parameters.

38. The method of claim 37, wherein the one or more sleep parameters include one or more of the following: sleep start time, sleep end time, sleep duration, sleep stage, sleep onset time, number of awakenings, duration of wakefulness, snoring status, snoring duration, exercise duration, exercise end time, quantity of alcoholic beverages consumed, time of last alcoholic beverage consumption, quantity of caffeinated beverages consumed, time of last caffeinated beverage consumption, daytime sleepiness status, severity of daytime sleepiness, average sleep oxygen saturation, average sleep heart rate variability, minimum sleep heart rate, maximum sleep heart rate, average sleep heart rate, a group of medications taken, and user demographic data.

39. The method of claim 38, wherein the one or more sleep parameters further include user wake-up time records and user bedtime records.

40. The method of claim 38, wherein the user demographic data includes one or more of medical history and examination results.

41. The method of claim 6, wherein the sleep score, the physical health score, and the mental health score each correspond to a predetermined scale.

42. The method of claim 41, wherein the predetermined scale is a Likert scale.

43. The method of claim 41, wherein the sleep score includes sleep quality status, the physical health score includes physical status, and the mental health score includes emotional status.

44. The method of claim 43, wherein the sleep quality state includes a reason for waking up.

45. The method of claim 43, wherein the physical state includes the type of physical discomfort, the location of physical discomfort, and the intensity of physical discomfort.

46. ​​The method of claim 43, wherein the emotional state includes waking-time emotion and bedtime emotion.

47. The method of claim 45, further comprising generating sleep data based on the user data and the sleep measurement data.

48. The method of claim 47, wherein generating sleep data includes coordinating the user data and the sleep measurement data.

49. The method of claim 47, further comprising generating one or more sleep trends by analyzing the sleep data.

50. The method of claim 49, wherein the risk of one or more sleep disorders is based on the one or more sleep trends.

51. The method of claim 36, further comprising generating a graphical user interface, the graphical user interface including one or more of the sleep trends and the sleep disorder risk.

52. The method of claim 36, further comprising modifying computing device settings based on one or more of the sleep trend and the risk of sleep disorder.

53. The method of claim 36, wherein sleep service referrals are based on one or more of the sleep trends and the risk of sleep disorders.

54. The method of claim 36, wherein the user data and the sleep measurement data are received at predetermined intervals.

55. The method of claim 54, wherein the predetermined interval is at least once a day.

56. The method of claim 54, wherein the predetermined interval is the wake-up time and the bedtime.

57. The method of claim 36, wherein the sleep disorder includes one or more of the following: obstructive sleep apnea, central sleep apnea, hypoventilation, orthopnea, nocturnal atrial fibrillation, nocturnal hypertension, nocturnal discomfort, nocturnal exacerbation of chronic obstructive pulmonary disease, heart failure, asthma, sleep quality, and waking discomfort.

58. A method for graphically representing user health, comprising: The computing device outputs notifications for users to input sleep scores, physical health scores, and mental health scores; Generating a user health graph on the graphical user interface of the computing device, wherein the generation includes: A first shape including a first color is generated based on the sleep score; a second shape including a second color is generated based on the physical health score; and a third shape including a third color is generated based on the mental health score. as well as The positions of the first shape, the second shape, and the third shape relative to the first axis of the user health graph are arranged based on the sleep score, the physical health score, and the mental health score.

59. The method of claim 58, wherein the first axis is the vertical axis of the user health graph.

60. The method of claim 58, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are located on the first axis.

61. The method of claim 58, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein two of the first center, the second center, and the third center are located on the first axis, and the third of the first center, the second center, and the third center is offset relative to the first axis.

62. The method of claim 58, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein one of the first center, the second center, and the third center is located on the first axis, and the other two of the first center, the second center, and the third center are offset relative to the first axis and are on opposite sides of the first axis.

63. The method of claim 58, wherein the first axis is an axis that forms an angle between the vertical axis of the user health graph and the horizontal axis of the user health graph.

64. The method of claim 58, wherein the center-to-center distance between the first shape and the second shape is based on the difference between the sleep score, the physical health score, and the mental health score.

65. The method of claim 58, wherein the centers of two or more of the first shape, the second shape, and the third shape are spaced apart from each other along the first axis.

66. The method of claim 58, wherein the centers of two or more of the first shape, the second shape, and the third shape are offset from each other relative to the first axis.

67. The method of claim 58, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are laterally offset from each other.

68. The method of claim 67, wherein the first shape, the second shape, and the third shape partially overlap along the first axis.

69. The method of claim 67, wherein the first shape includes a first center, the second shape includes a second center, and the third shape includes a third center, wherein the first center, the second center, and the third center are spaced apart along the first axis by equal center-to-center distances.

70. The method of claim 58, wherein generating the user health graph includes generating a plurality of lines, wherein each of the plurality of lines overlaps with two of the first shape, the second shape, and the third shape.

71. The method of claim 70, wherein the plurality of lines comprises a first line between the center of the first shape and the center of the second shape and a second line between the center of the second shape and the center of the third shape.

72. The method of claim 58, wherein the sleep score, the physical health score, and the mental health score each correspond to a predetermined scale.

73. The method of claim 72, wherein the predetermined scale is a Likert scale.

74. The method of claim 58, wherein each of the first shape, the second shape, and the third shape comprises a two-dimensional geometry.

75. The method of claim 58, wherein each of the first color, the second color, and the third color includes a color gradient.

76. The method of claim 58, wherein each of the first color, the second color, and the third color includes an opacity gradient.

77. The method of claim 58, wherein the background of the graphical user interface includes a color gradient.

78. The method of claim 58, further comprising periodically updating the user health graph.

79. The method of claim 78, further comprising generating an animation, the animation including the updated user health graph and one or more previous user health graphs.

80. The method of claim 58, wherein the notification is output at predetermined intervals.

81. The method of claim 58, further comprising modifying computing device settings based on the user health graph.

82. The method of claim 58, further comprising referring a sleep service to the user based on the user health graph.

83. A method for predicting sleep disorders, comprising: Receive user data, including sleep scores, physical health scores, and mental health scores, from the computing device, and receive sleep measurement data from the measurement device; Based on the user data and the sleep measurement data, predict the risk of one or more sleep disorders; as well as Refer sleep services to users based on the predicted risk of one or more of the aforementioned sleep disorders.

84. The method of claim 83, further comprising using the computing device to output a notification for inputting the user data.

85. The method of claim 83, wherein the sleep measurement data includes one or more sleep parameters.

86. The method of claim 85, wherein the one or more sleep parameters include one or more of the following: sleep start time, sleep end time, sleep duration, sleep stage, sleep onset time, number of awakenings, duration of wakefulness, snoring status, snoring duration, exercise duration, exercise end time, quantity of alcoholic beverages consumed, time of last alcoholic beverage consumption, quantity of caffeinated beverages consumed, time of last caffeinated beverage consumption, daytime sleepiness status, severity of daytime sleepiness, average sleep oxygen saturation, average sleep heart rate variability, minimum sleep heart rate, maximum sleep heart rate, average sleep heart rate, a group of medications taken, and user demographic data.

87. The method of claim 86, wherein the one or more sleep parameters further include user wake-up time records and user bedtime records.

88. The method of claim 86, wherein the user demographic data includes one or more of medical history and examination results.

89. The method of claim 83, wherein the sleep score, the physical health score, and the mental health score each correspond to a predetermined scale.

90. The method of claim 89, wherein the predetermined scale is a Likert scale.

91. The method of claim 83, wherein the sleep score includes sleep quality status, the physical health score includes physical status, and the mental health score includes emotional status.

92. The method of claim 91, wherein the sleep quality state includes a reason for waking up.

93. The method of claim 91, wherein the physical state includes the type of physical discomfort, the location of physical discomfort, and the intensity of physical discomfort.

94. The method of claim 91, wherein the emotional state includes waking-time emotion and bedtime emotion.

95. The method of claim 83, further comprising generating sleep data based on the user data and the sleep measurement data.

96. The method of claim 95, wherein generating sleep data includes coordinating the user data and the sleep measurement data.

97. The method of claim 95, further comprising generating one or more sleep trends by analyzing the sleep data.

98. The method of claim 97, wherein the risk of one or more sleep disorders is based on the one or more sleep trends.

99. The method of claim 83, further comprising generating a graphical user interface, the graphical user interface including one or more of the sleep trends and the sleep disorder risk.

100. The method of claim 83, further comprising modifying computing device settings based on one or more of the sleep trend and the risk of sleep disorder.

101. The method of claim 83, wherein sleep service referrals are based on one or more of the sleep trends and the risk of sleep disorders.

102. The method of claim 83, wherein the user data and the sleep measurement data are received at predetermined intervals.

103. The method of claim 83, wherein the predetermined interval is at least once a day.

104. The method of claim 83, wherein the predetermined interval is at wake-up time and bedtime.

105. The method of claim 83, wherein the sleep disorder includes one or more of the following: obstructive sleep apnea, central sleep apnea, hypoventilation, orthopnea, nocturnal atrial fibrillation, nocturnal hypertension, nocturnal discomfort, nocturnal exacerbation of chronic obstructive pulmonary disease, heart failure, asthma, sleep quality, and waking discomfort.

106. A method for predicting user health, comprising: The system receives user data, including sleep scores, multiple physical health parameters, and mental health scores, from the computing device, and receives sleep measurement data from the measurement device. as well as A sleep quality score is generated based on the sleep score and the sleep measurement data; a physical health quality score is generated based on the multiple physical health parameters; and a mental health quality score is generated based on the mental health score.

107. The method of claim 106, further comprising referring a sleep service to a user based on one or more of the sleep quality score, the physical health quality score, and the mental health quality score.

Images