Temperature-based sleep and physical activity monitoring treatment and guidance

A system using wearable devices to measure thermal gradients for personalized insomnia treatment and activity guidance addresses the lack of comprehensive, personalized approaches in current insomnia treatments, enhancing sleep quality by aligning therapy with individual circadian rhythms.

WO2026232195A1PCT designated stage Publication Date: 2026-11-12RESMED PTY LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/AU2026/050454
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-12-30
Filing Date
2026-05-07
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Current treatments for insomnia and sleep disorders lack a comprehensive, personalized approach that addresses underlying behavioral and cognitive factors, and existing monitoring technologies fail to capture nuanced thermal rhythms for effective sleep quality improvement.

Method used

A system utilizing wearable devices to measure skin temperature and core body temperature gradients, along with heat flux, to calculate Distal Proximal Gradient (DPG) slopes, providing personalized recommendations for sleep and physical activity guidance based on real-time thermal biomarkers.

Benefits of technology

Enhances sleep quality by aligning therapy with individual circadian rhythms, improving treatment outcomes through personalized, real-time adjustments and recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure AU2026050454_12112026_PF_FP_ABST
    Figure AU2026050454_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A method for physical activity monitoring and guidance, including receiving physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, while the user is engaged in a physical activity. The method further includes calculating, based on the physiological data, a Distal Proximal Gradient (DPG) slope and one or more additional thermal biomarkers associated with the user. The method further includes generating, based on the DPG slope and the additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity, and causing presentation of the recommendation in a user interface on a user device operated by the user.
Need to check novelty before this filing date? Find Prior Art

Description

MWS Docket No. 114212-0338TEMPERATURE-BASED SLEEP AND PHYSICAL ACTIVITY MONITORING TREATMENT AND GUIDANCE TECHNICAL FIELD

[0001] The present technology relates to sleep and physical activity monitoring, and more specifically, to wearable devices and data analytics for measuring and tracking physiological metrics for screening, assessment, and personalized guidance and therapeutic recommendations.BACKGROUND

[0002] Sleep disorders such as insomnia are conditions that affect the quality, timing, or duration of sleep, impacting a person’s ability to function properly while awake. Insomnia is a prevalent sleep disorder that may profoundly impact the mental and physical health of sufferers. It is estimated that 21.5% of the adult population of the United States suffers from insomnia. Characterized by difficulty falling asleep, staying asleep, or waking up too early, insomnia is implicated in sufferers experiencing feelings of exhaustion, reduced cognitive function, irritability and a general decline in quality of life. While lifestyle changes and medications may temporarily relieve some insomnia related symptoms, a highly effective long-term treatment for chronic insomnia is Cognitive Behavioral Therapy for Insomnia (CBT-I). This structured, evidence-based therapeutic approach targets the root psychological and behavioral causes of insomnia, offering patients a sustainable pathway to restful sleep without the dependency issues associated with pharmacological treatment modalities.

[0003] Insomnia may be either acute, lasting a few days to weeks due to stress or other situational factors, or chronic, persisting for three or more nights per week over a period of three months or longer. Chronic insomnia is of particular concern due to its cumulative impact on health. Studies link it to various physical conditions, including hypertension, obesity, and immune system dysfunction, as well as mental health disorders such as anxiety and depression. People suffering from chronic insomnia often experience a diminished capacity for memory, focus, and decision-making. The wide-ranging consequences of insomnia on both individual and societal levels underscore the need for effective treatment approaches.MWS Docket No. 114212-0338

[0004] Historically, treatments for insomnia have included lifestyle modifications and sleep hygiene practices, such as establishing a regular sleep schedule, reducing caffeine intake, and creating a comfortable sleep environment. For more severe cases, sedativehypnotic medications are sometimes prescribed. However, while these medications may provide short-term relief, they may carry a high risk of dependency, tolerance and potential withdrawal symptoms. Additionally, pharmacological therapies do not address underlying behavioral and cognitive factors that may contribute to insomnia.

[0005] A range of sleep disorders exist. Certain disorders can be characterized by particular respiratory events, e.g., apneas, hypopneas, hyperpneas, circadian rhythm disruptions, abnormal sleep behaviors, and involuntary movements. Sleep disorders can relate to respiratory-related disorders. For example, sleep-related respiratory disorders like obstructive sleep apnea (OSA) can cause frequent awakenings during the night, which can contribute to insomnia.

[0006] Sleep health is a critical component of overall well-being, influencing cognitive function, emotional regulation, cardiovascular health, and immune response. Despite its importance, sleep disorders affect millions globally, with conditions such as insomnia, obstructive sleep apnea, restless legs syndrome, and circadian rhythm disorders becoming increasingly prevalent. These disorders not only diminish quality of life but also contribute to chronic health issues and increased healthcare costs.

[0007] Currently, the identification and diagnosis of sleep disorders rely on a combination of clinical evaluations and specialized diagnostic tools. Common methods include polysomnography (a comprehensive overnight sleep study that monitors brain activity, oxygen levels, heart rate, and body movements), actigraphy (a wearable device that tracks sleep-wake cycles), and home sleep apnea tests for more accessible screening.Electroencephalography (EEG) is also used to measure electrical activity within the brain, and the EEG data are used to determine the wakefulness of the patient.

[0008] Treatment approaches vary depending on the specific disorder and its severity. They range from behavioral therapies, such as Cognitive Behavioral Therapy for Insomnia (CBT-I), to medical interventions including Continuous Positive Airway Pressure (CPAP) devices for sleep apnea, pharmacological treatments, and light therapy for circadian rhythm disturbance.MWS Docket No. 114212-0338

[0009] Fitness and performance are intrinsically connected to the human body’s thermal rhythms. These rhythms are set by the body’s circadian clock, which is an internal timer that governs sleep, energy, metabolism, and recovery. However, these rhythms are different and unique to each individual. Modem life often disrupts these natural rhythms, due to late-night screen time, irregular meals, travel, constant stress, and other factors. These misalignments reduce sleep quality, drain athletic performance, and affect long-term health.

[0010] In elite sports, heat patterns are measured with infrared cameras to monitor recovery and performance. However, this professional level of scientific analysis is not available to the average person.SUMMARY

[0011] Some embodiments of the present disclosure provide a method for physical activity monitoring and guidance. The method includes receiving, while the user is engaged in a physical activity, physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, the physiological data including skin temperature. The method further includes calculating, based on the physiological data, a Distal Proximal Gradient (DPG) slope, and further calculating one or more additional thermal biomarkers associated with the user, the additional thermal biomarkers including one or more of core body temperature and heat flux. The method further includes generating, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity, and causing presentation of the recommendation in a user interface on a user device operated by the user.

[0012] Some embodiments of the present disclosure provide a non-transitory, computer-readable storage medium storing instructions for physical activity monitoring and guidance, wherein the instructions, when executed by one or more processors of a computing system, cause the computing system to receive, while the user is engaged in a physical activity, physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, the physiological data including skin temperature. The instructions, when executed by the one or more processors, further cause the computing system to calculate, based on the physiological data, a Distal Proximal Gradient (DPG) slope and one or more additional thermal biomarkers associated with theMWS Docket No. 114212-0338user, the additional thermal biomarkers including one or more of core body temperature and heat flux. The instructions, when executed by the one or more processors, further cause the computing system to generate, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity, and to cause presentation of the recommendation in a user interface on a user device operated by the user.

[0013] Some embodiments of the present disclosure provide a system for physical activity monitoring and guidance, including one or more processors, a first device affixed to a proximal region of a user, a second device affixed to a distal region of a user, and one or more non-transitory, computer-readable media storing instructions that when executed by the one or more processors, cause the system to receive physiological data from the first device and from the second device while the user is engaged in a physical activity, the physiological data including skin temperature. The instructions, when executed by the one or more processors, further cause the system to calculate, based on the physiological data, a Distal Proximal Gradient (DPG) slope and one or more additional thermal biomarkers associated with the user, the additional thermal biomarkers including one or more of core body temperature and heat flux. The instructions, when executed by the one or more processors, further cause the system to generate, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity, and to cause presentation of the recommendation in a user interface on a user device operated by the user.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present technology is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which like reference numerals refer to similar elements including:

[0015] FIG. 1 illustrates a network architecture used to implement insomnia management, circadian entrainment, and / or physical activity monitoring and guidance, according to some embodiments.

[0016] FIG. 2 is a block diagram illustrating details of a system for sleep disorder detection and management, according to some embodiments.MWS Docket No. 114212-0338

[0017] FIG. 3 illustrates a closed-loop circadian therapy workflow, according to some embodiments.

[0018] FIG. 4 is an overview of a monitoring system, according to some embodiments.

[0019] FIG. 5 is an overview of a circadian therapy system, according to some embodiments.

[0020] FIG. 6 is an exemplary workflow for two monitoring devices in a monitoring system, according to some embodiments.

[0021] FIG. 7 illustrates an exemplary design of a distal device and a proximal device, according to some embodiments.

[0022] FIG. 8 is a block diagram of firmware implemented at one or more devices of a monitoring system, according to some embodiments.

[0023] FIG. 9 illustrates an example diagram of a process, according to some embodiments.

[0024] FIGS. 10A-10B show exemplary alignments in core and body temperature and their relation to sleep readiness, according to some embodiments.

[0025] FIG. 11 shows exemplary cooling and heating applied to treat sleeping disorders such as insomnia using treatment delivery, according to some embodiments.

[0026] FIG. 12 illustrates an exemplary display on a patient dashboard showing a baseline circadian clock, according to some embodiments.

[0027] FIG. 13 illustrates an exemplary display showing patients’ ability to optimize their results based on preferred sleep times, according to some embodiments.

[0028] FIGS. 14A-14C illustrate exemplary displays showing active thermoregulation treatment delivery, according to some embodiments.

[0029] FIG. 15 illustrates an exemplary display showing a light exposure recommendation, according to some embodiments.MWS Docket No. 114212-0338

[0030] FIG. 16 is a block diagram illustrating details of a system for sleep quality management, according to some embodiments.

[0031] FIG. 17 illustrates a closed-loop circadian therapy workflow, according to some embodiments.

[0032] FIG. 18 is an overview of a monitoring system, according to some embodiments.

[0033] FIG. 19 is an overview of a circadian therapy system, according to some embodiments.

[0034] FIG. 20 is an exemplary workflow for two monitoring devices in a monitoring system, according to some embodiments.

[0035] FIG. 21 illustrates an exemplary design of a distal device and a proximal device, according to some embodiments.

[0036] FIG. 22 is a block diagram of firmware implemented at one or more devices of a monitoring system, according to some embodiments.

[0037] FIG. 23 illustrates an example diagram of a process, according to some embodiments.

[0038] FIGS. 24A-24B show exemplary alignments in core and body temperature and their relation to sleep readiness, according to some embodiments.

[0039] FIG. 25 shows examples of cooling and heating applied to treat sleeping disorders such as insomnia using treatment delivery, according to some embodiments.

[0040] FIG. 26 illustrates an exemplary display on a user dashboard showing a baseline circadian clock, according to some embodiments.

[0041] FIG. 27 illustrates an exemplary display showing users’ ability to optimize their results based on preferred sleep times, according to some embodiments.

[0042] FIGS. 28A-28C illustrate exemplary displays showing active thermoregulation treatment delivery, according to some embodiments.MWS Docket No. 114212-0338

[0043] FIG. 29 illustrates an exemplary display showing a light exposure recommendation, according to some embodiments

[0044] FIG. 30 is a block diagram illustrating details of a system for physical activity monitoring and guidance, according to some embodiments.

[0045] FIG. 31A and FIG. 3 IB illustrate components of a system for physical activity monitoring and guidance, according to some embodiments.

[0046] FIGS. 32A-32B illustrate an exemplary user interface for a physiological monitoring and circadian alignment system, according to some embodiments.

[0047] FIGS. 33A-33B illustrate an exemplary user interface for assessing thermal regulation and cooling efficiency of a user, in real time and / or over summary periods, according to some embodiments.

[0048] FIGS. 34A-34D illustrate an exemplary user interface for presenting sleep metrics of a user, in real time and / or over various summary periods, according to some embodiments.

[0049] FIGS. 35A-35C illustrate an exemplary user interface for assessing physical performance metrics and bilateral muscle activity during exercise or daily activity, according to some embodiments.

[0050] FIG. 36 is a flowchart illustrating a process for physical activity monitoring and guidance performed by one or more processors of a computing system, according to some embodiments.

[0051] FIG. 37 is a block diagram illustrating an exemplary computer system with which aspects of the subject technology can be implemented.DETAILED DESCRIPTION

[0052] In the following detailed description, numerous specific details are set forth to provide a full understanding of the present disclosure. It will be apparent, however, to one ordinarily skilled in the art, that the embodiments of the present disclosure may be practiced without some of these specific details. In other instances, well-known structures and techniques have not been shown in detail so as not to obscure the disclosure.MWS Docket No. 114212-0338

[0053] All references cited anywhere in this specification, including the appendices, and Background and Detailed Description sections, are incorporated by reference as if each had been individually incorporated.

[0054] Before the present technology is described in further detail, it should be understood that the technology is not limited to the particular examples described herein, which may vary. It is also to be understood that the terminology used in this disclosure is for the purpose of describing only the particular examples discussed herein and is not intended to be limiting.

[0055] The following description is provided in relation to various examples which may share one or more common characteristics and / or features. It is to be understood that one or more features of any one example may be combinable with one or more features of another example or other examples. In addition, any single feature or combination of features in any of the examples may constitute a further example.Glossary

[0056] For the purposes of the present technology disclosure, in certain forms of the present technology, one or more of the following definitions can apply. In other forms of the present technology, alternative definitions can apply.

[0057] Patient. A person, whether or not they are suffering from a respiratory condition.

[0058] Clinical data Information encompassing developments within the health and technology space. This includes advancements in diagnostic tools, treatment protocols, and patient outcomes (e.g., from public health records), research data on new treatments, devices, drug trials, technology (e.g., medical devices), and other known medical knowledge.

[0059] User or patient data Information about or data collection (subjective and / or objective data) on an individual patient that is relevant to decisions about their current or future health or illness. This data can include a wide range of information such as medical history, treatment records, diagnostic results, health outcomes, lifestyle information, psychosocial data, and functional status. Patient data can also encompass health and demographic information, which can include age, gender, race, ethnicity, insurance information, etc.MWS Docket No. 114212-0338

[0060] Automatic Positive Airway Pressure (APAP) therapy. CPAP therapy in which the treatment pressure is automatically adjustable, e.g., from breath to breath, between minimum and maximum limits, depending on the presence or absence of indications of SDB events.

[0061] Continuous Positive Airway Pressure (CPAP) therapy. Respiratory pressure therapy in which the treatment pressure is approximately constant through a respiratory cycle of a patient. In some forms, the pressure at the entrance to the airways will be slightly higher during exhalation, and slightly lower during inhalation. In some forms, the pressure will vary between different respiratory cycles of the patient, for example, being increased in response to detection of indications of partial upper airway obstruction, and decreased in the absence of indications of partial upper airway obstruction.

[0062] Apnea-. According to some definitions, an apnea is said to have occurred when flow falls below a predetermined threshold for a duration, e.g., 10 seconds. An obstructive apnea will be said to have occurred when, despite patient effort, some obstruction of the airway does not allow air to flow. A central apnea will be said to have occurred when an apnea is detected that is due to a reduction in breathing effort, or the absence of breathing effort, despite the airway being patent. A mixed apnea occurs when a reduction or absence of breathing effort coincides with an obstructed airway.

[0063] Hypopnea-. According to some definitions, a hypopnea is taken to be a reduction in flow, but not a cessation of flow. In one form, a hypopnea can be said to have occurred when there is a reduction in flow below a threshold rate for a duration. A central hypopnea will be said to have occurred when a hypopnea is detected that is due to a reduction in breathing effort. In one form in adults, either of the following can be regarded as being hypopneas:

[0064] (i) a 30% reduction in patient breathing for at least 10 seconds plus an associated 4% desaturation; or

[0065] (ii) a reduction in patient breathing (but less than 50%) for at least 10 seconds, with an associated desaturation of at least 3% or an arousal.

[0066] Hyperpnea'. An increase in flow to a level higher than normal.MWS Docket No. 114212-0338

[0067] Distal Proximal Gradient (DPG) slope'. As used herein, the DPG slope refers to the rate of change over time of the temperature difference between a distal region (e.g., limb) and a proximal region (e.g., core) of a user’s body, as measured by sensors affixed to those regions.

[0068] Recommendation'. As used herein, a “recommendation” comprises a specific, actionable instruction, timing indication, condition indication, or adjustment provided to a user through a device based on physiological data to improve, support, or maintain physical activity. Examples include adjusting workout intensity, modifying sleep timing, changing environmental conditions, or identifying a recommended time period for exertion, rest, sleep, or focus.

[0069] Physical Activity: As used herein, a “physical activity” refers to a user state, period, or event for which guidance is provided, and may include a sleep activity, a fitness activity, a training activity, a rest or recovery activity, an eating activity, or a focus activity.Example Architecture

[0070] FIG. 1 illustrates a network architecture 100 used to implement insomnia management, circadian entrainment, and physical activity monitoring and guidance, according to some embodiments. The network architecture 100 may include one or more of client devices 110 and / or servers 130, communicatively coupled via network 150 with each other and to at least one database, e.g., database 152. In some embodiments, client devices 110 collect data, metadata, sensor data, patient and / or user data, physiological data, environmental data, video, images, and the like, for upload to the servers 130 and / or to store in the database 152. Servers 130 can include a cloud server or a group of cloud servers. In some implementations, servers 130 may not be cloud-based (i.e., platforms / applications can be implemented outside of a cloud computing environment) or can be partially cloud-based.

[0071] Client devices 110 may include, but are not limited to, computing devices (e.g., laptop computers, desktop computers, etc.), mobile devices (e.g., smartphones, tablets, etc.), wearable devices, head-mounted devices, display devices, and the like. In some embodiments, client devices 110 may include sensor pods or include sensor pod components. For example, client devices 110 may include, but are not limited to, sensor pods, a mattress topper, a ring, a smart watch, a toe-ring, an ankle band, an ankle patch, a body patch, smart garments, earrings, a headband, glasses, and the like. In addition, one or more of clientMWS Docket No. 114212-0338devices 110 may be or may include a dock for recharging and / or storing the system components. The client devices 110 may also be communicatively coupled to one or more external sensors or wearable sensors.

[0072] The client devices 110 can include user device(s), provider device(s) accessing a physical activity monitoring and guidance platform, an insomnia management and circadian entrainment platform, or the like, via a software application interface configured to display user information, data, physician-input data, etc. The client devices 110 can be computing devices with data processing and data communication capabilities that are capable of receiving inputs, data signals, or the like. In various implementations, client devices 110 can communicate over wired or wireless channels to distribute processing and / or share data. The client devices 110 can be communicatively coupled to one or more sensors or client devices. In some implementations, the client devices 110 can present data to a patient, user, medical provider, healthcare organization, or physician based on the processed data. For example, the client devices 110 can be configured to present data or information via the software application interface.

[0073] Servers 130 can host a physical activity monitoring and guidance platform, an insomnia management and circadian entrainment platform, or the like, configured to analyze data from a plurality of sources including sleep studies, medical / technological studies (e.g., new advancement or trials), and individual patient and / or user data including, for example, patient demographic, wearable sensor data, and / or biomarkers. Based on the ingested data, the platform may be configured to identify user phenotypes, guide insomnia diagnosis, dynamically generate personalized recommendations, enable provision of first-line therapy, enhance sleep quality by identifying sleep pressure (classified by changes in DPG), sleep readiness, or similar metrics through analysis of DPG measurements, and provide real-time or near real-time updates to physicians and patients, automating patient engagement and followup. For example, patient and / or user data sent through the network 150 via client device 110-1 can be received by the server 130 where it is analyzed and processed for storage and retrieval in conjunction with a database 152.

[0074] In some embodiments, one or more of the servers 130 may be a cloud server or a group of cloud servers. One or more of servers 130 may host a physical activity monitoring and guidance platform that receives sensor data from the database 152 and / or at least a subset of client devices 110 and provides actionable guidance to the user through the same or aMWS Docket No. 114212-0338different subset of the client devices 110. For example, data sent through the network 150 via client devices 110 can be received by the servers 130 where the data may be analyzed and processed for storage and retrieval in conjunction with database 152.

[0075] In some embodiments, one or more of the servers 130 may be implemented outside of a cloud computing environment, such as an on-premises environment. One or more of the servers 130 may be part of a cloud computing server, including but not limited to rackmounted computing devices and panels. Such panels may include but are not limited to processing boards, switchboards, routers, and other network devices. In some embodiments, the servers 130 may include the client devices 110 as well, such that they are peers.

[0076] Database 152 may store data and fdes associated with patients, users, and / or applications executing on the client devices 110 and / or the servers 130 including, for example, trained models, training data, medical information, research, or the like. The database 152 can logically form a single unit or can be part of a distributed computing environment encompassing multiple computing devices that are located within their corresponding server, located at the same, or located at geographically disparate physical locations. For example, contextual information can be stored in the database 152 and can comprise information such as location, sleep disorder classifications, reports, metadata associated with a patient or user (e.g., demographics), platform / messaging application data, and / or the like.

[0077] The network 150 may include a wired network (e.g., fiber optics, copper wire, telephone lines, and the like) and / or a wireless network (e.g., a satellite network, a cellular network, a radiofrequency (RF) network, Wi-Fi, Bluetooth, and the like). The network 150 may further include one or more of a local area network (LAN), a wide area network (WAN), the Internet, and the like. Further, the network 150 may include, but is not limited to, any one or more of the following network topologies, including a bus network, a star network, a ring network, a mesh network, a hybrid network, a star-bus network, tree or hierarchical network, and the like. Client devices 110, servers 130, and database 152 can be connected to each other over the network 150 through a network interface, such as by wired or wireless communication. The connections can be any kind of local, wide area, wired, or wireless network, including the network 150 or a separate public or private network.SLEEP DISORDER DETECTION AND MANAGEMENT SYSTEMMWS Docket No. 114212-0338General Overview

[0078] Some embodiments provide a closed-loop circadian therapy system and method for insomnia management that leverages advanced data aggregation techniques to generate Al-driven personalized treatment recommendations based on a holistic view of a patient. The system aims to improve treatment outcomes by continuously monitoring and adjusting therapy based on real-time data. This is done by assessing, diagnosing, monitoring, and treating sleep disorders using a combination of wearable devices, data analytics, and personalized therapeutic recommendations. Embodiments provide a data-driven system that can integrate diverse data sources and provide personalized treatment administration and other recommendations.

[0079] The closed-loop circadian therapy system for insomnia offers several technical advantages. By aggregating sensor data (for example, skin temperature data), clinical data, from various sources including, for example, Electronic Health Record (EHR), sleep raw data from sleep tests (EEG waveforms, PSG data), and physiological signals, the system provides a comprehensive and objective understanding of the patient’s sleep patterns, circadian rhythm, and sleep challenges. This aggregation of diverse datatypes (including subjective and objective data) enhances the accuracy of sleep disorder diagnosis and delivery of more precise and personalized treatments / therapies. The system leverages circadian rhythms, which influence various physiological processes, to align therapy with these rhythms to improve sleep quality.

[0080] Embodiments present a system designed to monitor and improve sleep quality, particularly for individuals suffering from insomnia and / or other ailments affecting a person’s circadian rhythm. The system can utilize various physiological signals including, but not limited to, skin temperature, core body temperature, heart rate variability, movement, activity, and oxygen saturation (SpO ). to track and analyze circadian rhythms and sleep patterns. Embodiments of the present disclosure provide a system for delivering treatment, the system comprising, for example, one or more wearable devices, or a patient application / interface. In some embodiments, the system can be integrated into an existing sleep disorder management platform server application executing on an insomnia management platform server. Physiological data collected at the one or more wearable devices (e.g., core body temperature, heart rate variability, light exposure) is analyzed to inform therapy administration and adjustments.MWS Docket No. 114212-0338

[0081] In addition to sleep-related activities, the system may be used to monitor and optimize other fitness activities, such as physical training, eating, and periods of cognitive focus. For example, during a training activity, the system may use DPG slope and other physiological data to recommend optimal timing for exertion, rest, or hydration. During eating activities, the system may recommend meal timing based on circadian rhythm data. For focus activities, the system may suggest periods of peak cognitive performance based on physiological markers.

[0082] According to some embodiments, the system can include at least two components used to measure physiological signals from a peripheral (distal) and central (proximal) system of a patient. The components can be attached to or worn by the patient. For peripheral measurements, the component can be positioned on locations including, but not limited to, a wrist, arm, hand, fingers, feet, or legs of the patient. For central system monitoring, suitable placement areas include, but are not limited to, a neck, chest, forehead, and abdomen of the patient. The collected data from the proximal and distal location can be used to determine a distal-proximal skin temperature gradient (DPG), which provides insights into the patient’s sleep stages and circadian clock. By monitoring these signals, the system can identify abnormalities, predict sleep quality during various stages of sleep, and provide recommendations and / or treatments based therefrom. By non-limiting example, the system can determine sleep onset and wake-up times and offer personalized recommendations to improve sleep quality.

[0083] According to some embodiments, the system can be further configured to deliver treatment, for example, based on an analysis of the collected data and / or recommendations. In some implementations, the system components can include a thermoregulation device that can warm or cool specific areas of the body to enhance sleep stages and overall sleep-wake states. The thermoregulation device can be included in the at least two components used to measure physiological signals. In some implementations, the thermoregulation device can be an additional component in the system (for example, an external sensor) configured to apply heating and cooling to a specified region of the body. According to some embodiments, the system can include sound, thermo-electric, chemical, exothermic, and other energy forms to administer treatment (for example, warm and cool the body). These methods can be implemented in the two components used to measure physiological signals or include in an additional component in the system.MWS Docket No. 114212-0338

[0084] According to some embodiments, the system incorporates a light sensor to detect light exposure, which can alter circadian rhythm, impacting sleep cycle and potentially contributing to insomnia. Light exposure is crucial for circadian tracking, as it influences how much light the body is exposed to during the day. This sensor might be a separate device or integrated within the system. In some implementations, if the system detects excessive or insufficient light exposure, it can recommend actions (for example, getting more sunlight or reducing artificial light exposure from devices like mobile phones during specific time periods, etc.). The light sensor can be an external component to the system, or integrated into one of the existing components. In some implementations, the light sensor is an additional component which can be, for example, attached to the patient (for example, attached to clothes, a collar, glasses, etc.) or placed in an environment of the patient.

[0085] The disclosed system solves a technical problem in sleep monitoring and treatment technologies by providing real-time, actionable insights based on a holistic analysis of multiple physiological signals. This enhances the accuracy of sleep predictions and the effectiveness of thermoregulation therapies. The system’s ability to deliver personalized sleep recommendations and therapies based on real-time data collected from the patient enables effective insomnia treatments and improves the patient’s overall sleep quality. The system integrates sensors (for example, temperature, heart rate, SpCh, and light exposure sensors), along with algorithms for data analysis, to provide a more comprehensive understanding of the patient’s sleep patterns and circadian rhythms. The use of DPG measurements, combined with personalized therapies and real-time data analysis, improves the technical field of sleep monitoring while offering practical benefits for individuals suffering from sleep disorders. Artificial intelligence (Al) and machine learning methods, such as artificial neural networks, deep neural networks, etc., can be implemented to analyze known medical data to generate personalized treatment plans based on the patient’s physiological and historical data. This ensures that therapy choices are informed by a wide range of relevant information, leading to more effective treatments.

[0086] Some embodiments provide a temperature-focused approach that provides deeper physiological insight as temperature gradients provide a more nuanced view of sleep transitions and circadian patterns, which are often missed by traditional actigraphy or HR-only tools. A more targeted understanding of insomnia may be attained by capturing deviations in thermal regulation patterns that can be used to identify root causes of sleepMWS Docket No. 114212-0338disturbances rather than just their symptoms. Some embodiments further provide personalized insights by combining continuous physiological monitoring with subjective input, enabling the delivery of more personalized, actionable feedback over time.

[0087] Additionally, the integration of external wearable devices to capture physiological data further refines the treatment process, providing a more holistic view of the patient’s condition. In some embodiments, a closed-loop system for monitoring treatment adherence and outcomes allows for continuous feedback and adjustment of treatment plans, ensuring that patients receive the most appropriate care throughout their treatment journey.

[0088] Embodiments are not limited to insomnia management and treatment. For example, the invention can be understood by one of ordinary skill in the art to apply to any sleep disorder.

[0089] FIG. 2 is a block diagram illustrating details of a system for sleep disorder detection and management, according to some embodiments. Specifically, FIG. 2 shows an exemplary client device 110-1 and exemplary server 130-1 used in network architecture 100, according to some embodiments. Client device 110-1 and server 130-1 are communicatively coupled over network 150 via respective communications modules 218-1 and 218-2 (hereinafter, collectively referred to as “communications modules 218”). Communications modules 218 are configured to interface with network 150 to transmit or receive information, such as user data, analysis results, user input data, and / or the like to other devices on the network 150. Communications modules 218 can be, for example, modems or Ethernet cards, and can include radio hardware and software for wireless communications (e.g., via electromagnetic radiation, such as radiofrequency (RF), near field communications (NFC), Wi-Fi, and Bluetooth radio technology).

[0090] Client device 110-1 can be coupled with an input device 214 and with an output device 216. A user can interact with client device 110-1 via the input device 214 and the output device 216. Input device 214 can include a mouse, a keyboard, a pointer, a touchscreen, a wearable input device (e.g., a haptics glove, a bracelet, a ring, an earring, a necklace, a watch, etc.), a microphone, a controller, a joystick, a virtual joystick, a camera, a touchscreen display that a user can use to interact with client device 110, or the like. In some embodiments, input device 214 can include cameras, microphones, and sensors, such as touch sensors, acoustic sensors, inertial motion units -IMUs- and other sensors configured toMWS Docket No. 114212-0338provide input data. Output device 216 can include a screen display (e.g., an LCD display screen and / or LED display screen), a touchscreen, a speaker, a projector, holographic, or augmented reality display (such as a heads-up display device or a head-mounted device), and / or the like. According to some embodiments, the client device 110-1 can be used to collect sleep assessments from the client device or an external data source, deliver personalized recommendations, and support timely communication with providers, physicians, etc., associated with patients.

[0091] Client device 110-1 can also include a processor 212-1, configured to execute instructions stored in a memory 220-1, and to cause the client device 110-1 to perform at least some operations in methods consistent with one or more embodiments and some operations are offloaded to a core processing component or server 130-1. Memory 220-1 can further include an application 222 and a display 224, configured to run in client device 110-1 and couple with input device 214 and output device 216. The application 222 can be downloaded by the user from server 130 and can be hosted by server 130. The application 222 includes specific instructions which, when executed by processor 212-1, cause operations to be performed according to methods described herein. In some embodiments, the application 222 runs on an operating system (OS) installed in client device 110-1. In some embodiments, application 222 can run out of a web browser. Data and files associated with the application 222 can be stored in database 152.

[0092] Application 222 provides a user interface that is displayed on a screen of the client device 110-1 and allows patients / users to input commands to control the operation of the application 222, view outputs from engine 232, interact with other client devices, or the like. Application 222 enables patients to track and view circadian therapy recommendations, progress, set sleep goals, view treatment plans, make adjustments to treatment plans, and follow up care. The application 222 can be implemented as a web page, a collection of web pages, or other content designed to be displayed within an internet browser.

[0093] Server 130-1 includes a memory 220-2, a processor 212-2, and communications module 218-2. Hereinafter, processors 212-1 and 212-2, and memories 220-1 and 220-2, will be collectively referred to, respectively, as “processors 212” and “memories 220.” In some implementations, the server 130-1 can be used as part of a management platform implemented via the network 150. In some embodiments, the processor is configured to control a graphical user interface (GUI) or display 224 for the user of one of client devicesMWS Docket No. 114212-0338110 accessing the server of a management platform. According to some embodiments, the management platform can synthesize patient data for rapid review and interpretation for a physician (at client device 110-1), supporting real-time communication with patients.

[0094] Processors 212 (e.g., central processing units (CPUs), graphical processing units (GPUs), holographic processing units (HPUs), etc.) are configured to execute instructions stored in memories 220. The processors 212 can be a single processing unit or multiple processing units in a device or distributed across multiple devices (e.g., distributed across two or more of client device 110-1 such as a patient device and a physician device). The processors 212 can be coupled to other hardware devices, for example, with the use of an internal or external bus, such as a PCI bus, SCSI bus, wireless connection, and / or the like. The processors 212 can communicate with a hardware controller for devices, such as input device 214 and output device 216. Processors 212 can be configured to analyze wearable sensor data, test results, medical and pharmaceutical data, patient treatment history, or the like, to generate and provide personalized treatment recommendations to physicians.

[0095] Memory 220-2 can include an engine 232 and an Al tool 234. The engine 232 can share or provide features and resources with application 222 for presentation at display 224, including Application Programming Interfaces (APIs) and other services that the application 222 can use to perform functions, such as accessing external data sources or integrating with other software. The user can access information from engine 232 through application 222, installed in a memory 220-1 of client device 110-1. Accordingly, application 222, including display 224, can be installed by server 130-1 and perform scripts and other routines provided by server 130-1 through any one of multiple tools. Server 130-1 can include an API layer, which controls applications in the client device 110- 1. An API layer can also provide tutorials to users of the client device 110-1 as to new features in the application 222.

[0096] According to some embodiments, engine 232 can include one or more sets of machine -readable instruction modules that, when executed by processors 212, are configured to perform operations according to some embodiments described herein. For example, the engine 232 can include a research module configured to track sleep disorder developments in the health and technology space. For example, the engine 232 can include a phenotype generation module configured to identify a phenotype of a patient based on patient data and sleep disorder assessment. For example, the engine 232 can be configured to facilitate provisions of first-line therapy based on input data while leveraging a generative AI / MUMWS Docket No. 114212-0338model trained at Al tool 234. As another example, engine 232 can be configured to manage end-to-end circadian therapy workflow for insomnia management including diagnosis, treatment, and patient-physician engagement and follow-ups. The aspects of the circadian therapy workflow can be provided to the users (for example, patients and physicians) via application 222.

[0097] The Al tool 234 can be configured to provide Al driven insomnia treatment recommendations tailored to each patient profile, and help physicians adopt innovative technologies (for example, obtained by engine 232). The Al tool 234 can be part of one or more machine learning models stored in the database 152. In some embodiments, at least one or more training archives or machine learning models can be stored in either one of memories 220. The database 152 includes training archives and other data files that can be used by engine 232 in the training of a machine learning model, according to the input of the user through application 222 and data extracted through the network 150.

[0098] The Al tool 234 can include algorithms trained for the specific purposes of the engine 232 and tools included therein. The algorithms can include machine learning or artificial intelligence algorithms making use of any linear or non-linear algorithm, such as a neural network algorithm, or multivariate regression algorithm. In some embodiments, the machine learning model can include an LLM, Natural Language Understanding (NLU) model, a neural network (NN), a convolutional neural network (CNN), a generative adversarial neural network (GAN), an unsupervised learning algorithm, a deep recurrent neural network (DRNN), a classic machine learning algorithm such as random forest, or any combination thereof. More generally, the machine learning model can include any machine learning model involving a training step and an optimization step. In some embodiments, the database 152 can include a training archive to modify coefficients according to a desired outcome of the machine learning model. Accordingly, in some embodiments, engine 232 is configured to access the database 152 to retrieve data and archives as inputs for the machine learning model. In some embodiments, engine 232, the tools contained therein, and at least part of database 152 can be hosted in a different server that is accessible by server 130-1 or client device 110-1.

[0099] Some implementations can be operational with numerous other computing system environments or configurations. Examples of computing systems, environments, and / or configurations that can be suitable for use with the technology include, but are not limited to,MWS Docket No. 114212-0338personal computers, server computers, handheld or laptop devices, cellular telephones, wearable electronics, gaming consoles, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and / or the like.

[0100] The techniques described herein can be implemented as method(s) that are performed by physical computing device (s); as one or more non-transitory computer-readable storage media storing instructions which, when executed by computing device(s), cause performance of the method(s); or as physical computing device(s) that are specially configured with a combination of hardware and software that causes performance of the method(s).Insomnia Management Workflow

[0101] FIG. 3 illustrates a closed-loop circadian therapy workflow 300, according to some embodiments. According to some embodiments, the closed-loop circadian therapy — facilitating patient feedback, circadian data analysis, and treatment administration — can be integrated with an insomnia management platform. This is designed to streamline sleep disorder diagnosis and management for its users, improve operational efficiency for sleep disorder workflows, and support comprehensive patient care.

[0102] The workflow 300 includes a patient application 302 used by patient 304 and physician application 308 (for example, application 222) used by physician 306. The patient 304 can be using, connected to, or associated with a monitoring system 310 used for collecting patient data for the patient 304. The patient application 302 and / or the physician application 308 may be hosted by an insomnia management platform 312 (for example, server 130). Authorized credentials can be required to gain access to the patient application 302 and physician application 308. The patient application 302 and physician application 308 can be how patients and physicians (or other clinicians), respectively, engage with the insomnia management platform 312. At least a portion of the patient data can be input by the patient 304 via patient application 302 (e.g., demographic information, treatment plan symptoms, sleep diary, medical history, etc.) and / or can be stored in a database (e.g., database 152) coupled to the insomnia management platform 312 in a patient profileMWS Docket No. 114212-0338associated with the patient 304. For example, the patient information can include the patient’s EHR.

[0103] According to some embodiments, the insomnia management platform 312 can support and present through the physician application 308 computerized alerts and reminders to care providers about critical patient information, such as evidence -based recommendations for diagnosing and treating sleep disorders, patient data reports and summaries, focused reports that summarize patient information, aiding in quick and accurate decision-making, documentation templates (e.g., for recording patient information or billing), diagnosing assistance tools, and contextually relevant reference information (e.g., medical literature and resources relevant to the patient’s condition).

[0104] According to some embodiments, the insomnia management platform 312 can be configured to determine one or more physiological patterns tied to circadian rhythms. Based on physiological patterns, treatments can be delivered to a patient. Some physiological changes during sleep cycles can be indicators for high- and low-quality sleep. By nonlimiting example, skin temperature rise at sleep on-set, distal and proximal skin temperatures closely following each other during sleep, core body temperature dropping at sleep onset and staying low throughout sleep, a drop in skin temperature an hour before waking up (indicating that the body is preparing to wake up), and heart rate slowing down at sleep on-set can be physiological indicators of high-quality sleep. By non-limiting example, a rise in skin temperature before sleep onset, a difference in proximal to distal skin temperature during sleep, heart rate slowing down on sleep on-set, core body temperature not dropping during sleep, and high variability in heart rate during sleep (indicating restlessness) can be physiological indicators of low-quality sleep.

[0105] Those skilled in the art will appreciate that patient application 302 invariably includes a range of additional features (for example, components for sleep application, sleep restriction, stimulus control, cognitive restructuring, light exposure management, relaxation techniques, goal setting, sleep coaching, sleep schedules and gamified components such as for delivering gamified cognitive brain training exercises, etc.).

[0106] According to some embodiments, the monitoring system 310 integrates data inputs from multiple sources (including external devices), enhancing treatments or therapies applied or recommended by the insomnia management platform 312. Monitoring system 310MWS Docket No. 114212-0338can include at least two wearable devices (worn by the patient 304) and comprise sensors for measuring physiological data and biological response data from the patient 304, as well as environmental data. The measured physiological, biological response and / or environmental data are relevant to the circadian rhythm tracking that the patient is undergoing in terms of both delivering particular treatments (for example, thermoregulation) and measuring their effectiveness. The patient application 302 can be used to control the wearable device, receive data from the sensors and transmit the data to the insomnia management platform 312, transmit sensory actuation commands to the wearable device, as well as serving as an application for delivering the various components of a circadian rhythm tracking program to the patient 304.

[0107] The wearable device also includes one or more sensory actuators for providing sensory actuation or feedback (such as haptic, visual, auditory or other feedback) to the patient as an aspect of the circadian rhythm tracking / therapy. By non-limiting example, actuation or feedback can be used to trigger a prompt to the patient to enter a cognitive input into the patient app relevant to the insomnia-related event to which the sensory activation relates.

[0108] In some embodiments, the insomnia management platform 312 can receive data inputs from other data sources including, but not limited to, sleep assessments, DMEs, biomarkers, wearable device(s), implants, or the like. Devices and / or DMEs can include, for example, CPAP machines, Bilevel Positive Airway Pressure (BiPAP) machines, vital sign monitors (for example, blood pressure monitors, pulse oximeters, and thermometers), EEGs, ECGs, EOGs, EMGs, spirometers, Remote Patient Monitoring (RPM) devices, or other devices used for determining sleep assessment scores, obtaining sleep results data (for example, raw data from sleep tests), or the like. The devices and / or DMEs can be used to collect data including EEG waveforms, PSG data, physiological signals from sleep studies, or other medical data understood by one of ordinary skill in the art to be relevant to sleep disorder diagnosis and / or treatment. In some implementations, the patient data can be processed in real time by the insomnia management platform 312 (e.g., at engine 232).

[0109] According to some embodiments, the insomnia management platform 312 can utilize data collected from the monitoring system 310 to track circadian rhythms, sleep patterns, identify sleep-related issues, and measure progress over time (for example, posttreatment delivery) based on physiological signals. The monitoring system 310 can recordMWS Docket No. 114212-0338initial paterns in physiological data at different sleep and wake times, total sleep duration, nightime awakenings, and other factors influencing sleep quality to establish a baseline for the patient 304. The baseline can be used to identify misalignments in the patient’s circadian clock (or desired circadian clock), such as inconsistent sleep paterns, prolonged awakenings during the night, spending too much time in bed awake, and other behaviors. The baseline can be established based on what is considered normal according to a set of characteristics (e.g., age). According to some embodiments, physiological data can be collected during the day as well as at night and further used to generate a baseline for the patient.

[0110] By non-limiting example, insomnia management platform 312 can analyze continuous physiological data for a predetermined period of time (for example, 2-4 weeks) — including, but not limited to, body temperature, heart rate, and more — alongside subjective inputs (for example, from sleep diaries, validated sleep and wellness questionnaires, etc.). The combined dataset can be used to establish a personalized baseline for each individual, allowing the insomnia management platform 312 to detect deviations and patterns that are specific to the user’s sleep behavior and physiology. According to some embodiments, the patient 304 can be guided through a questionnaire or sleep assessment through the patient application 302 during which the patient 304 can describe their desired sleep goals (for example, fall asleep faster at a desired time, sleep more deeply, wake up naturally at a preferred time, etc.), current sleep habits, or sleep issues. In some implementations, the patient’s sleep goals and physiological data collected can be used to enhance the baseline and drive recommendations and treatment delivery.

[0111] In some implementations, the insomnia management platform 312 can automate a sleep disorder indicator based on patient data to guide and make data-driven diagnoses. The sleep disorder indicator can implement an Al-based model to generate diagnostics based on patient data and, for example, other patient heath data (e.g., public health records). For example, the sleep disorder indicator can automatically indicate to a patient or physician that the patient can have a sleep disorder and what type of sleep disorder, based on, for example, the patient’s EHR, ISI, and / or sleep study data. For example, signatures within physiological data can be examined for paterns indicative of insomnia including, but not limited to, amplitude of circadian rhythm as inferred by skin temperature and core body temperature change over a day, REM fragmentation, the number of hyper arousals, and transitionsMWS Docket No. 114212-0338between different sleep stages. In this way, the sleep disorder indicator can provide insight on the type of insomnia a patient has and their core problem that needs to be addressed.

[0112] The insomnia management platform 312 can identify signatures within physiological signals including, for example, a distal proximal gradient (DPG) change between transitions to different sleep stages. DPG can be used as a biomarker for sleep readiness and sleep quality. The body does a gradient change naturally, when it is getting ready for sleep and waking up. Additionally, the gradient holds close to zero to maintain good sleep quality. As such, recording the DPG can allow for valuable insights on a patient’s circadian rhythm. Based on this, the insomnia management platform 312 can identify treatment options that can improve the quality of sleep overall and / or at specific sleep stages. According to some embodiments, the insomnia management platform 312 can leverage features such as threshold detection, signal slopes, and temporal trends to extract meaningful insights from this data. Accordingly, the insomnia management platform 312 adapts dynamically to each user’s night-to-night variations and long-term trends, enabling tailored treatment recommendations that evolve over time.

[0113] By non-limiting example, physiological patterns tied to circadian rhythms can include proximal skin temperature dropping while distal skin temperature rises approximately an hour before bedtime, increasing the skin temperature gradient. As another non-limiting example, both skin temperatures can converge at sleep onset, reducing the gradient to near zero. As another non-limiting example, skin temperature can decline about an hour before waking, signaling impending arousal. As another non-limiting example, core body temperature can naturally drop in the evening, signaling readiness for sleep, and reach its nadir between 4-6am, often followed by REM sleep.

[0114] According to some embodiments, the insomnia management platform 312 can generate personalized treatment recommendations using an Al model. The personalized treatment recommendations can be based on physiological data and relevant clinical data. In some embodiments, the insomnia management platform 312 can be configured to track clinical data, including but not limited to, developments in sleep disorders within the health and technology space, as well as other contextually relevant data points. The insomnia management platform 312 can also monitor advancements in diagnostic tools, device and treatment protocols, and patient outcomes (e.g., from public health records) related to sleep disorders. Clinical data can further include public health data, research data includingMWS Docket No. 114212-0338development of new treatments, devices, drug trials, technology (e.g., medical devices), and other known medical knowledge.

[0115] In some implementations, clinical data can be extracted by the insomnia management platform 312 from one or more external data sources (e.g., the web, medical databases, and health information exchanges). This data extraction can include automated web scraping, API integrations, and data feeds from trusted medical sources.

[0116] In some implementations, clinical data can be received by the insomnia management platform 312 from one or more sources (e.g., research institutions, healthcare providers, and patient registries). This can involve direct data submissions, secure data transfers, and / or collaborations with academic and clinical research organizations. By integrating these diverse data sources, the system aims to provide a comprehensive and up-to-date view of clinical developments, enhancing the ability to diagnose, treat, and manage sleep disorders effectively.

[0117] The Al model can use the physiological data and the clinical data to perform treatment matching and generate treatment recommendations best suited for the patient 304 based on a data-driven diagnosis. In some implementations, data from a patient’s EMR is used to establish the patient’s baseline for the treatment recommendations. For example, preexisting conditions, medication history, etc., can alter the treatment options administrable to the patient. The Al model can be continuously trained on technological and medical advancements to assist in providing new and beneficial treatment options. Training data can include details about the devices themselves, regulatory approvals, reimbursement information, insurance information, etc.

[0118] According to some embodiments, monitoring system 310 can include (for example, within the proximal and distal devices) or be communicatively coupled with (for example, external devices such as temperature-controlled mattress toppers) a treatment delivery component configured to administer treatment based on the insomnia management platform 312. In some implementations, the treatment delivery component can include a thermoregulation device configured to adjust body temperature through localized cooling or warming in accordance with treatment recommendations generated by the insomnia management platform 312. In some implementations, the treatment delivery component can include an electrical stimulation device delivering non-invasive brain stimulation, either pre-MWS Docket No. 114212-0338sleep or during sleep, to improve sleep onset and maintenance. In some implementations, the treatment delivery component can include an auditory stimulation device which uses bone conduction audio to enhance slow-wave and REM sleep, without disrupting the sleeper.

[0119] In this manner, the insomnia management platform 312 integrated with the monitoring system 310 lowers the risk of the patient experiencing negative biological responses during sleep caused by their sleep disorder. By non-limiting example, the thermoregulation device can apply heating or cooling to keep the patient in REM sleep for a longer period of time. In some embodiments, treatments like thermoregulation and electrical stimulation can be integrated into a closed-loop feedback system, where the Al continuously monitors real-time signals and autonomously triggers interventions (for example, initiating cooling during specific phases of sleep). This adaptive, insight-driven approach is designed to move beyond passive monitoring — toward active, personalized intervention to improve sleep outcomes.

[0120] According to some embodiments, monitoring system 310 can include or be communicatively coupled with a light sensor for detecting light exposure on or in an environment of patient 304. The light sensor can be used to provide light therapy through personalized guidance on timing and intensity of light exposure, promoting circadian alignment through increased daytime light and reduced evening exposure. By non-limiting example, insomnia management platform 312 can be configured to create parallel relationships to light and physiological behavior which can contribute to misalignments in the patient’s circadian rhythm. Based on data collected from monitoring system 310, the insomnia management platform 312 can generate and provide a recommendation to the client to improve sleep quality (for example, reduce light exposure at least thirty minutes before bedtime).

[0121] According to some embodiments, the insomnia management platform 312 can provide, alongside the personalized treatment recommendations, detailed reasoning and explanations to support the suggested treatment options. This can include generating and incorporating, within the physician application 308, links to relevant resources, summaries of clinical studies, and approvals (e.g., government approvals) associated with the recommended treatment options or products, etc. In some implementations, the recommendations also include insights into the efficacy, safety, and potential side effects of the treatments, ensuring that physicians have comprehensive information to make informed treatment decisions. InMWS Docket No. 114212-0338some implementations, each recommendation also includes a statistical analysis of treatment results. The analysis can be limited to outcomes from patients with the same or similar circadian clock patterns or all available patients. As a result, the insomnia management platform 312 can also serve as a source for education, helping physicians adopt innovative technologies / techniques — bridging the gap between available treatment options and healthcare professionals.

[0122] According to some embodiments, the Al model is designed to prevent unintentional and / or subconscious physician specialty biases for impacting a patient’s treatment plan. For example, a psychologist can naturally be more inclined to suggest CBTI treatments while a neurologist can more likely suggest a neuromodulation technique to treat insomnia. The personalized treatment recommendations provide recommendations for therapies or a combination of therapies that is best suited for the patient objectively based on statistics, patient data, medical studies, etc. This is advantageous to traditional diagnostics and treatment because it is not limited to a physician’s knowledge or expertise. The personalized treatment recommendations can be provided to the physician 306 via the physician application 308 to aid in making more informed decisions on treatment plans. In some implementations, the personalized treatment recommendation can include multiple therapies wherein the patient is recommended to transition into each of the multiple therapies. For example, patient 304 can be recommended to start with neuromodulation to help with falling asleep for a first part of the treatment course for a first duration of time and then transition to thermoregulation therapy to maintain sleep as a second part of the treatment course for a second duration of time. As such, the insomnia management platform 312 can make connections between different comorbidities as well as guide physicians to connect to the right treatment specific to the patient and their phenotypes.

[0123] According to some embodiments, the personalized treatment recommendations can include, but are not limited to, treatment options such as medication, DMEs, CBTI, light therapy, neuromodulation, neuro stimulation devices, circadian rhythm tracking, respiratory therapies, etc., or any combination thereof. By non-limiting example, a personalized treatment recommendation can include a treatment match transmitted to the physician application 308, an inbox associated with the physician 306, or the like, indicating that “Your patient has sleep onset issues and a history of not adhering to CBTI. We recommend trying PAP as a primary treatment.” As such, physician 306 can take the insomnia managementMWS Docket No. 114212-0338platform’s recommendation, providing insights and recommendations tailored to each patient profde, and proceed to making a decision on how to treat the patient. For example, the physician 306 can accept the personalized treatment recommendation as is and push it to the patient through the insomnia management platform 312, make modifications to the personalized treatment recommendation, or reject at least a portion of the insomnia management platform 312 and design a new treatment plan for the patient 304.

[0124] According to some embodiments, physician 306 can order or prescribe medication, DMEs, issue referrals for therapies, or the like for a patient’s sleep disorder via the physician application 308. For example, as shown in FIG. 3, the physician 306 can order personalized CBTI modules as an insomnia solution for the patient 304. The patient 304 can access the provided insomnia solutions through the patient application 302. This simplifies the process of, for example, prescribing and ordering DME for insomnia, saving time and ensuring patients access therapy solutions quickly and efficiently.

[0125] The insomnia management platform 312 is designed for multi-system integration, streamlining patient follow-ups with centralized diagnostics, therapy tracking, and care management, improving the quality of care delivery. In some embodiments, the insomnia management platform 312 can be integrated and support, for example, respiratory-related sleep disorders, such as sleep apnea, through advanced positive airway pressure (PAP) devices or the like.

[0126] In some embodiments, the insomnia management platform 312 can comprise a patient-physician messaging feature wherein the patient and / or the physician can maintain communication and conduct follow-up care. As another example, if the patient acts on any of the ordered or prescribed solutions for insomnia, corresponding data can be collected and tracked via the insomnia management platform 312. By non-limiting example, the patient 304 can purchase / pick up a prescribed medication or CPAP device, or act on a therapy solution, or the like. For example, the insomnia management platform 312 can track delivery, fulfilment, therapy adherence, therapy outcomes (e.g., systems alleviated or not alleviated), and other care management features. In some implementations, the device can be communicatively coupled to the insomnia management platform 312 such that collected data is automatically sent to the insomnia management platform 312 and viewable on the patient application 302 and / or physician application 308. In some implementations, the data is transmitted in batches or at intervals.MWS Docket No. 114212-0338

[0127] According to some embodiments, the insomnia management platform 312 enables provision of first-line therapy including, for example, administrating any products or prescriptions ordered by the physician 306 through the physician application 308 and the ability to dynamically adjust therapies based on new data (e.g., patient outcomes, clinical data, etc.). Provision of first-line therapy enables clinician-led therapies to enhance patient engagement, scale treatment capabilities, and support sustainable income through billing (e.g., Remote Therapeutic Monitoring (RTM) billing codes). Accordingly, the physician 306 can bill for the insomnia treatment through the insomnia management platform 312. This can include determining an appropriate bill based on patient data (e.g., insurance information), services rendered, and generating a bill based therefrom. Accordingly, the insomnia management platform 312 provides physicians with a comprehensive management platform for monitoring patients, following up with patients, and billing patients.

[0128] The insomnia management platform 312 operates as a closed feedback loop. According to some embodiments, this loop can utilize subjective assessments within the patient application 302 to validate and refine insights. User feedback ensures that the detected physiological patterns align with actual user experiences, facilitating continuous improvement of the insomnia management platform 312 algorithms and personalization of insights.

[0129] Privacy settings (or “access settings”) for a data element can be stored in various ways, such as in association with the data element itself, in an index on an authorization server, or through any suitable combination thereof. A privacy setting for a data element can specify how the data (or specific information associated with the data) can be accessed, stored, or otherwise used (e.g., viewed, shared, modified, copied, executed, surfaced, or identified) within a patient or physician application.

[0130] When privacy settings for a data element allow a particular entity (e.g., users, patients, etc.) to access that data, the data element can be described as being “visible” to that user or entity. For example, a user or patient can specify privacy settings for their medical history that identify a set of healthcare providers who can access their medical records, thus excluding other users from accessing that information. All access-enabled healthcare data can be subjected to Health Insurance Portability and Accountability Act (HIPAA) protocols, General Data Protection Regulation (GDPR) protocols, and the like.MWS Docket No. 114212-0338

[0131] In certain embodiments, privacy settings for a data element can specify a “blocked list” of data that cannot be altered and / or entities that should not be allowed to access certain information associated with the data element. The blocked list can include third-party entities and specify one or more entities for which the data element is not visible. Privacy settings can also be associated with specific elements of a healthcare data model. Privacy settings of a data model element, such as a node or an edge, can specify how the element, information associated with the element, or data associated with the element can be accessed using the patient application.

[0132] For example, a particular node corresponding to a specific test result can have a privacy setting specifying that the result can be accessed only by the patient and their primary care physician. Privacy settings can allow users or patients to opt in to or opt out of having their data, information, or actions stored / logged by the patient application or shared with other systems (e.g., a third-party healthcare provider, a specialty group based on a physician referral, or the like).

[0133] In certain embodiments, privacy settings can be based on one or more nodes or edges of a healthcare data model. A privacy setting can be specified for one or more edges or edge-types of the data model, or with respect to one or more nodes or node-types of the data model. The privacy settings applied to a particular edge connecting two nodes can control whether the relationship between the two entities corresponding to the nodes is visible to other users of the patient application. Similarly, the privacy settings applied to a particular node can control whether the user or concept corresponding to the node is visible to other users of the patient application.

[0134] For example, a user or patient can share a set of medical records with their healthcare provider. The records can be associated with a node connected to their profile by an edge. The user or patient can specify privacy settings that apply to a particular edge connecting to the node of the records or can specify privacy settings that apply to all edges connecting to the node. As another example, the user or patient can share a set of test results. The user or patient can specify privacy settings with respect to all test results associated with them as having a particular privacy setting (e.g., specifying that all test results are visible only to their primary care physician and / or specialists involved in their care).MWS Docket No. 114212-0338

[0135] In certain embodiments, the patient application can present a “privacy wizard” (e.g., within a webpage, a module, one or more dialog boxes, or any other suitable interface) to assist the patient in specifying one or more privacy settings. The privacy wizard can display instructions, suitable privacy-related information, current privacy settings, one or more input fields for accepting inputs from the user or patient specifying a change or confirmation of privacy settings, or any suitable combination thereof. The patient application can offer a “dashboard” functionality that displays current privacy settings to the user or patient. The dashboard functionality can be displayed at any appropriate time (e.g., following an input from the user or patient summoning the dashboard functionality, following the occurrence of a particular event or trigger action). The dashboard functionality can allow the user or patient to modify one or more of their current privacy settings at any time, in any suitable manner (e.g., redirecting the user or patient to the privacy wizard).

[0136] Privacy settings associated with a data element can specify any suitable granularity of permitted access or denial of access. For example, access or denial of access can be specified for particular users or patients (e.g., only me, my healthcare providers), users or patients within a particular degree of separation (e.g., primary care physician, specialists), user groups (e.g., my care team), user networks (e.g., employees of a particular healthcare provider), all users (“public”), no users (“private”), users of third-party systems, particular applications (e.g., third-party healthcare applications), other suitable entities, or any suitable combination thereof. Although this disclosure describes particular granularities of permitted access or denial of access, it contemplates any suitable granularities of permitted access or denial of access.Monitoring System

[0137] FIG. 4 is an overview of a monitoring system 400 (for example, monitoring system 310 of FIG. 3, and / or client device 110-1 of FIG. 2), according to some embodiments. The monitoring system 400 can be a dual location system that is actionable based on biological responses during a monitoring period. The dual location system can include a first wearable device 402 and a second wearable device 404.

[0138] The first wearable device 402 can include a proximal sensor and the second wearable device 404 can include a distal sensor. The proximal and distal physiological data captured by the first wearable device 402 and second wearable device 404 can be used forMWS Docket No. 114212-0338precise circadian clock tracking with continuous core body temperature. Based on the proximal and distal physiological data, a distal-proximal temperature gradient measurement can be computed at a platform (for example, insomnia management platform 312). According to some embodiments, the first wearable device 402 and second wearable device 404 provide two discrete temperature sensors on or near the body used to collect physiological data. Further, one or both of the distal device and proximal device can be configured to administer treatment based on an analysis of the collected physiological data.

[0139] According to some embodiments, the first wearable device 402 and second wearable device 404 are designed to be modular and adaptable. Meaning, the proximal and distal sensors included in the first wearable device 402 and second wearable device 404 are interchangeable and can be used for either proximal or distal location placement. This plug-and-play capability simplifies the setup process for patients and ensures compatibility with a wide range of platforms. The modular sensors can be used in diverse environments, from clinical settings to home-based monitoring systems. Their adaptability ensures that they can meet the specific needs of different users and applications. The first wearable device 402 and second wearable device 404 can be integrated into various systems, enhancing their versatility and usability across different applications. The sensors can be used in diverse environments (for example, clinical settings to home-based monitoring systems).

[0140] Proximal and distal skin temperature can vary, for example, 4-5 degrees, while core body temperature will vary 0.5-1 degrees in a 24-hour period. At night, dim light signals the human body to wind down. The body’s core temperature drops, and the hands and feet warm up, which helps a person relax and fall asleep. Wake up can occur after a drop in skin temperature. In the morning, the core warms up and the hands and feet cool down, signaling the body to wake. Bright light reinforces this effect, helping the person feel alert and ready for the day.

[0141] FIG. 5 is an overview of a circadian therapy system 500, according to some embodiments. As shown in FIG. 5, an application 502 (e.g., patient application 302, physician application 308, etc.) can be communicatively coupled to two devices 504, which can be placed at various locations (e.g., distal or proximal locations) on or around a patient’s body. The devices 504 can be charged using a charging station 506. The devices can be attached to the patient using connectors 508, including but not limited to, straps, adhesive bandages, or other connecting means. The devices 504 can be configured to monitor theMWS Docket No. 114212-0338patient, collect physiological data, light exposure, and the like. The devices 504 can also administer temperature treatment therapies, including but not limited to, thermoregulation.

[0142] FIG. 6 is an exemplary workflow 600 for two monitoring devices in a monitoring system, according to some embodiments. In some embodiments, the first device can correspond to a distal device 604, and the second device can correspond to a proximal device 602. The distal device 604 and proximal device 602 can include a plurality of sensors configured to record physiological data from a patient with a particular emphasis on monitoring circadian health biomarkers — sensing core body and skin temperature in two locations. According to some embodiments, the distal device 604 can include a core body temperature sensor, photoplethysmogram (PPG) sensor, skin temperature sensor, and an accelerometer and gyroscope. According to some embodiments, the proximal device 602 can include a core body temperature sensor, skin temperature sensor, and an accelerometer and gyroscope.

[0143] Although one of each of the sensors are illustrated, embodiments are not limited to this and can include one or more or any combination of the sensors. In some embodiments, the sensors can further include pulse oximeters, infrared (IR) temperature sensors, pulse sensors, or the like.

[0144] The distal device 604 and proximal device 602 can take a variety of forms including being worn like a necklace around the patient’s neck and contacting the patient’s upper chest. Either device can also be attached to the patient by way of a patch that contacts the patient’s skin at a suitable location such as the upper arm, wrist or the back of the neck. The various physiological sensors that are incorporated in the wearable device can include, but are not limited to:

[0145] A movement sensor such as an accelerometer or gyroscope for detecting movement.

[0146] A respiration sensor for measuring respiratory rate, respiratory flow, respiratory volume, inspiration and expiration.

[0147] A temperature sensor for measuring temperature, including skin and / or core body temperature.MWS Docket No. 114212-0338

[0148] A heart rate sensor (for example, an electrocardiogram) for measuring heart rate and heart rate variability.

[0149] An SpCh sensor (e.g., a pulse oximeter) for measuring the oxygen saturation level in the blood.

[0150] A galvanic skin response sensor for measuring changes in the electrical conductance of the skin which vary with moisture levels. The response is primarily influenced by sweat gland activity which is controlled by the sympathetic nervous system and often increases with emotional arousal or stress. As such, measuring galvanic skin response can provide insights into phenomena (such as hyper arousal and stress) that are implicated with insomnia symptoms. The galvanic skin response also provides a useful biofeedback signal to generate an augmented treatment strategy for the patient.

[0151] A light exposure sensor for measuring the quantity of different wavelengths of light contacting the patient. Light exposure is directly related to exposure to sunlight which is a major signal for the body’s internal clock, assisting with regulating the circadian rhythm. Sunlight exposure during the day, particularly in the morning, assists with suppressing melatonin production, signaling wakefulness and alertness. As daylight fades, melatonin levels rise, helping prepare the body for sleep. As such, measuring various lights to which the patient is exposed is useful for providing insights into the patient’s sleep-wake cycle and other circadian processes.

[0152] A sweat sensor for capturing sweat from the skin and detecting and quantifying hormone levels, principally melatonin and cortisol. Melatonin and cortisol are each useful biomarkers for monitoring and treating insomnia. In this regard, monitoring cortisol and / or melatonin levels provides insights into the time of occurrence of the patient’s sleep-wake cycle. Measuring melatonin levels can also assist in determining that the patient’s insomnia is related to a melatonin deficiency. The sweat sensor may also detect and quantify other substances such as caffeine.

[0153] A light sensor for measuring the patient’s exposure to visible light, including from artificial sources.

[0154] The physiological sensors may be used to determine sleep efficiency and sleep quality. Sleep efficiency and quality general indicate restful, uninterrupted sleep, while lowMWS Docket No. 114212-0338sleep efficiency can suggest issues with falling asleep, staying awake, or waking up too early Components of the monitoring system can also incorporate a number of behavioral sensors and actuators to continue to sleep quality determination and treatment effectiveness.

[0155] The distal device 604 and proximal device 602 can include a battery, powering each of the devices. The sensors on the distal device 604 and proximal device 602 can be controlled by a processor (for example, a microcontroller integrated with a central processing unit (CPU) along with memory and input / output peripherals on a single chip). In some embodiments, the processor can communicate with insomnia management platform 312 via a Bluetooth connection. The processor can control the sensors and transmit the physiological data to patient application 302 for processing by the insomnia management platform 312. The insomnia management platform 312 can analyze the data, perform necessary computations, and then act (provide recommendations and treatment) based on those inputs.

[0156] According to some embodiments, the insomnia management platform 312 can receive information from external data sources 606, impacting recommendations or treatment delivery. In some implementations, this can include a light sensor exposed to an environment of the patient 304 (for example, attached to or on patient 304).

[0157] The insomnia management platform 312 can include Al models / algorithms 608 used to determine circadian patterns based on physiological data, subjective data (for example, patient inputs), and patient data. Al models / algorithms 608 can incorporate machine learning models, algorithm libraries, expert systems, lookup tables and combinations thereof to analyze physiological, behavioral and other data that is uploaded to the insomnia management platform 312. For example, during sleep onset, skin temperatures typically rise because heat is drawn to proximal regions, while core body temperature drops, and heart rate slows. During sleep, skin and core body temperatures move closely together — a sign of good sleep quality. That is, core body and skin temperature can converge. Individuals with sleep maintenance insomnia can experience elevated core body temperatures at night, which can interfere with the ability to stay asleep. An hour before ideal wake up, skin temperature drops (wake-up signal), due to peripheral vasoconstriction, heat is drawn to the core, and the body is preparing for awakening. Individuals with sleep onset insomnia can experience a delayed temperature drop, making it harder to fall asleep.MWS Docket No. 114212-0338

[0158] According to some embodiments, the insomnia management platform 312 can use the Al models / algorithms 608 to generate recommendations. In some embodiments, this can include light adjust recommendations to restrict, limit, or increase light exposure (for example, when and how much light the patient needs to further boost sleep quality).

[0159] According to some embodiments, the insomnia management platform 312 can use the Al models / algorithms 608 to determine treatment and perform treatment delivery. In some implementations, treatments can be administered to patient 304 through distal device 604 and proximal device 602. For example, the insomnia management platform 312 can register when the patient is ready for sleep, via a unique sleep biomarker, and determine that sensory feedback is needed to aid sleep onset. The insomnia management platform 312 can control sensory feedback including, for example, thermoregulation to support the patient through one or more phases of sleep. Treatments can include one or more treatment options or combination thereof to provide optimal therapy personalized to the patient, for example, cognitive behavioral therapy and active thermoregulation.

[0160] FIG. 7 illustrates an exemplary design 700 of the distal device 604 and proximal device 602 described in FIG. 6, according to some embodiments. The distal device 604 and proximal device 602 can include, but are not limited to, an upper housing, PCB / battery, sensors, lower housing, and LED lens cover. According to some embodiments, the distal device 604 and proximal device 602 can further include (not depicted) Bluetooth (for example, BLE transmitter / receiver), storage (for example, SPI Flash storage), temperature sensors (for example, for providing thermoregulation), and the like.

[0161] The example of FIG. 7 shows a core temperature sensor plate, but embodiments are not limited to this configuration and can include one or more of any combination of sensors. In the non-limiting example of FIG. 7, the appearance of distal device 604 and proximal device 602 differ, the proximal device 602 having a round cylindrical shape and the distal device 604 having a cuboid shape. In other embodiments, the sensors are the same in size / shape and can be interchangeable with each other.

[0162] According to some embodiments, proximal device 602 can be attached to the patient, for example, using an adhesive bandage (illustrated in FIG. 7), chain, cord, band, strap, frame (for example, eyeglass frame), and the like. According to some embodiments,MWS Docket No. 114212-0338distal device 604 can be attached to the patient, for example, using a strap (illustrated in FIG.7), chain, cord, band, or the like.

[0163] FIG. 8 is a block diagram of firmware 800 implemented at one or more devices of a monitoring system, according to some embodiments. According to some embodiments, the firmware 800 can include an acquisition recording module 802. The acquisition recording module 802 can start by acquiring data from sensors or inputs and recording it into memory. According to some embodiments, devices of the monitoring system can be switched on or off manually or via a mobile app.

[0164] Idle 804 can be configured to cause the system to enter an idle state, waiting for further instructions or events. If no signal is detected (e.g., the device is not in contact with the skin), the device remains in an idle state to conserve battery.

[0165] Idle memory full 806 can be configured to determine when memory becomes full during acquisition and cause the system unpair 810 where the system can unpair from a connected device, such as a sensor or a data collector, to stop data acquisition. Data acquisition can continue when the idle memory is empty 808. Reading 812 can read the recorded data from memory for processing or transmission. Pause reading 820 can pause the reading process if required, for example, to prioritize other tasks.

[0166] Lead detection 814 can be configured to determine when signals should be recording 816. The device continuously measures voltages around leads to detect if sensors are in contact with skin. Once a signal is detected, indicating the device is on the patient’s body, the lead detection 814 triggers the device to start recording data from all sensors (for example, temperature, heart rate, oxygen blood level). The recording trigger signal can be based on a single sensor (for example, sensitive to skin contact).

[0167] Memory testing 818 can be configured to perform memory testing to ensure data integrity and check for errors. Erasing 822 can erase the recorded data from memory to free up space for new data acquisition after the data has been read.Circadian Monitoring Process FlowMWS Docket No. 114212-0338

[0168] FIG. 9 illustrates an example diagram of a process 900, according to some embodiments. Process 900 can be implemented by a system utilizing a multi-sensor setup involving two primary monitoring devices.

[0169] At step 902, process 900 can include collecting patient data and clinical data associated with the patient. This can include subjective inputs through questionnaires to identify patient needs, goals (e.g., desired bedtime window), and patient history, including comorbidities. By non-limiting example, patients can fdl out a questionnaire detailing their sleep patterns, lifestyle, medical history, and specific sleep-related issues. In some embodiments, this can include collecting essential information from patients prior to the patient receiving medical services. Patient intake information can include, but is not limited to, demographic information, medical history, authorizations for data collection, treatment, billing, or the like. In some implementations, an insomnia management platform can create a patient profile based at least on the patient intake. The patient can enable access to EMR.

[0170] In some embodiments, a patient can optionally undergo sleep studies at a sleep center or the like. Acquired data can include lab data acquisition from performance of a sleep study or other tests. In some implementations, the patient can upload data (for example, records) to a cloud server of the insomnia management platform.

[0171] At step 904, process 900 can include generating a baseline specific to the patient based on the initial patient data and clinical information. Using the collected data, a baseline of the patient’s physiological and sleep-related metrics is established. This baseline serves as a reference point for monitoring and treatment. The baseline can include initial core body temperature, heart rate variability, movement, activity levels, and oxygen saturation (SpO ) information.

[0172] At step 906, process 900 can include receiving physiological data from a monitoring system including at least a distal device and a proximal device. These devices are equipped with sensors to measure physiological signals including, but not limited to, core body temperature, heart rate, movement, activity, and SpO . According to some embodiments, process 900 can include continuous monitoring of sensor data from both distal and proximal devices for a given time period.MWS Docket No. 114212-0338

[0173] According to some embodiments, the distal device can be placed on peripheral body parts (e.g., arms, legs), while the proximal device is placed near the central body (e.g., chest, neck).

[0174] According to some embodiments, the distal device and proximal device can include lead detection to ensure sensors are in contact with the skin before recording data, optimizing battery usage and data accuracy.

[0175] At step 908, process 900 can include generating Distal Proximal Gradient (DPG) based on the physiological data. DPG can be used as a biomarker to identify different sleep stages and circadian rhythm alignment. The distal device and proximal device capture temperature across different locations to analyze the temperature gradient between distal and proximal skin regions. This gradient is a physiological marker of circadian rhythm and sleep readiness, providing insights into sleep biology and mechanisms underlying insomnia.

[0176] At step 910, process 900 can include analyzing the DPG to detect trends and patterns in the patient’s sleep readiness and quality. In some embodiments, a sleep-onset DPG and a sleep-wake DPG can be used to determine when a patient is ready to sleep, wake up, enter REM, etc. This can be leveraged to influence sleep onset, sleep maintenance, and sleep-wake stages and to identify biomarking time windows for sleep. For example, a patient can be ready to sleep (that is, reach an optimal time to go to sleep) when skin and core body temperature begin to align, as observed during quality sleep.

[0177] At step 912, process 900 can include generating individualized treatment plans. A treatment plan can be based on the DPG analysis and the patient’s sleep goals to maximize sleep potential. The treatment plan can also include recommendations for light exposure, medication adjustments, behavioral changes to support circadian rhythm alignment, and other relevant interventions.

[0178] In some embodiments, a light sensor is included to monitor light exposure, which is crucial for circadian rhythm tracking. This sensor can be integrated into one of the primary devices or used as a separate component. Accordingly, the recommendation can be made based on data received from the light sensor.

[0179] At step 914, process 900 can include administering at least one treatment based on the treatment plans, achieving therapeutic results that improve sleep quality and help theMWS Docket No. 114212-0338patient reach their sleep goals. According to some embodiments, treatments can include thermoregulation to adjust skin temperature, for example, warming or cooling specific body areas to enhance sleep stages. According to some embodiments, treatments can be adjusted based on real-time data. For example, thermoregulation interventions can be modified based on ongoing sensor readings from the monitoring system.

[0180] This method / process provides a comprehensive approach to monitoring and improving sleep quality by leveraging multi-sensor data and personalized treatment plans. It aims to address insomnia and enhance overall sleep health through targeted interventions and continuous monitoring.

[0181] FIGS. 10A-10B show exemplary alignments 1000 in core and body temperature and their relation to sleep readiness, according to some embodiments. Different temperature variances can be observed and individual to patients.

[0182] FIG. 11 shows examples 1100 of cooling and heating applied to treat sleeping disorders such as insomnia using treatment delivery (for example, thermoregulation), according to some embodiments. The treatment delivery can be administered to help align core and body temperature and improve overall sleep quality.Platform User Interfaces

[0183] FIG. 12 illustrates an exemplary display 1200 on a patient dashboard showing a baseline circadian clock, according to some embodiments. Display 1200 can be used by the patient to understand their baseline body clock. For example, display 1202 shows when the body is most active. Display 1204 shows when the body starts winding down naturally. Display 1206 shows when the body is ready for bed.

[0184] FIG. 13 illustrates an exemplary display 1300 showing patients’ ability to optimize their results based on preferred sleep times, according to some embodiments. Patients can also adjust their fall-asleep times (as shown in display 1302) and wake-up times (as shown in display 1304) based on a target desired bedtime window or actual sleep schedules using the patient dashboard.

[0185] FIGS. 14A-14C illustrate exemplary displays 1400 showing active thermoregulation treatment delivery, according to some embodiments. The displays 1400 canMWS Docket No. 114212-0338include body visuals wherein a patient (or physician) can monitor treatment outcomes or effectiveness. The visuals can indicate device placement, overall temperature changes, thermoregulation treatment settings, etc.

[0186] Displays 1402, 1404, and 1406 show thermoregulation treatment applied for faster sleep onset, cooling the core body temperature while warming the extremities, such as the hands. Displays 1408, 1410, and 1412 show thermoregulation treatment applied during sleep for deeper sleep, cooling the core body temperature while warming the extremities. Displays 1414, 1416, and 1418 show thermoregulation treatment applied to aid natural wakening, warming the core body temperature while cooling the extremities to support natural wakening.

[0187] FIG. 15 illustrates an exemplary display 1500 showing a light exposure recommendation generated by the insomnia management platform 312 and provided through the patient dashboard, according to some embodiments.DISTAL PROXIMAL TEMPERATURE BASED SLEEP QUALITY MANAGEMENTGeneral Overview

[0188] The disclosure provides a closed-loop circadian therapy system and method for insomnia management and circadian entrainment that leverages advanced data aggregation techniques to generate Al-driven personalized treatment recommendations based on a holistic view of a user. The system aims to improve treatment outcomes by continuously monitoring and adjusting therapy based on real-time data. This is done by assessing, diagnosing, monitoring, and treating sleep disorders using a combination of wearable devices, data analytics, and personalized therapeutic recommendations. Embodiments provide a data-driven system that can integrate diverse data sources and provide personalized treatment administration and other recommendations.

[0189] The closed-loop circadian therapy system for insomnia circadian entrainment offers several technical advantages. By aggregating sensor data (for example, skin temperature data), clinical data, from various sources including, for example, Electronic Health Record (EHR), sleep raw data from sleep tests (EEG waveforms, PSG data), and physiological signals, the system provides a comprehensive and objective understanding ofMWS Docket No. 114212-0338the user’s sleep patterns, circadian rhythm, and sleep challenges. This aggregation of diverse data types (including subjective and objective data) enhances the accuracy of identifying circadian rhythm misalignments and enables delivery of precise, personalized treatments and therapies based on those insights. The system leverages circadian rhythms, which influence various physiological processes, to align therapy with these rhythms to improve sleep quality.

[0190] Embodiments present a system designed to monitor and improve sleep quality, particularly for individuals suffering from insomnia and / or other ailments affecting a person’s circadian rhythm. The system can utilize various physiological signals including, but not limited to, skin temperature, core body temperature, heart rate variability, movement, activity, and oxygen saturation (SpO ). to track and analyze circadian rhythms and sleep patterns. In some embodiments, the system may further include biosensors such as sweat sensors, galvanic skin response sensors, and EDA sensors to monitor emotional arousal and stress levels, respiration sensors for measuring respiratory rate, respiratory flow, respiratory volume, inspiration and expiration, or the like. These signals can provide additional context for sleep disturbances, particularly in cases where stress or anxiety contributes to insomnia.

[0191] Embodiments of the present disclosure provide a system for delivering treatment, the system comprising, for example, one or more wearable devices, or a user application / interface. In some embodiments, the system can be integrated into an existing sleep disorder management platform server application executing on an insomnia management and circadian entrainment platform server. Physiological data collected at the one or more wearable devices is analyzed to inform therapy administration and adjustments. Physiological data can include one or any combination of, for example, distal proximal temperature gradient, core body temperature, skin temperature, heart rate / heart rate variability, respiratory rate / effort, light exposure, SpO . heat flux, electrodermal activity (EDA), galvanic skin response (GSR), other activity / movement, etc.

[0192] According to some embodiments, the system can include at least two components used to measure physiological signals from a peripheral (distal) and central (proximal) system of a user. The components can be attached to or worn by the user (for example, sensor pods). The components can comprise, for example, sensor pods, a mattress topper, ring, smart watch, toe-ring, ankle band, ankle patch, body patch, smart garments, earrings, headband, glasses, or the like. For peripheral measurements, the component can be positioned on locations including, but not limited to, a wrist, arm, hand, fingers, feet, or legs of the user. ForMWS Docket No. 114212-0338central system monitoring, suitable placement areas include, but are not limited to, a neck, chest, forehead, and abdomen of the user. The collected data from the proximal and distal location can be used to determine a distal-proximal skin temperature gradient (DPG).According to some embodiments, DPG can be used as a physiological marker to assess sleep pressure, sleep quality, body’s readiness to wake up, sleep drive, sleep stages, and / or hyperarousal. By analyzing the slope of the DPG over time, embodiments of the present disclosure can determine whether an individual is experiencing optimal sleep conditions or diminished sleep quality, enabling more precise and timely interventions. In some embodiments, DPG and heat flux are used as a measure of sleep quality. By monitoring these signals, the system can identify abnormalities, predict sleep quality during various stages of sleep, and provide recommendations and / or treatments based therefrom.

[0193] According to some embodiments, the system can be further configured to deliver treatment, for example, based on an analysis of the collected data and / or recommendations. In some implementations, the system components can include a thermoregulation device that can warm or cool specific areas of the body to enhance sleep stages and overall sleep-wake states. The thermoregulation device can be included in the at least two components used to measure physiological signals. In some implementations, the thermoregulation device can be an additional component in the system (for example, an external sensor) configured to apply heating and cooling to a specified region of the body. According to some embodiments, the system can include sound, thermo-electric, chemical, exothermic, and other energy forms to administer treatment (for example, warm and cool the body). These methods can be implemented in the two components used to measure physiological signals or include in an additional component in the system.

[0194] According to some embodiments, the system incorporates a light sensor to detect light exposure, which can alter circadian rhythm, impacting sleep cycle and potentially contributing to insomnia. Light exposure is crucial for circadian tracking and determining circadian alignment and sleep quality, as it influences how much light the body is exposed to during the day. This sensor might be a separate device or integrated within the system. In some implementations, if the system detects excessive or insufficient light exposure, it can recommend actions (for example, getting more sunlight or reducing artificial light exposure from devices like mobile phones during specific time periods, etc.). The light sensor can be an external component to the system or integrated into one of the existing components. InMWS Docket No. 114212-0338some implementations, the light sensor is an additional component which can be, for example, attached to the user (for example, attached to clothes, a collar, glasses, etc.) or placed in an environment of the user.

[0195] In some embodiments, other environmental inputs such as sound, humidity, ambient temperature, and air quality can be incorporated to improve the accuracy of circadian alignment and sleep quality assessment. These factors can influence sleep onset, maintenance, and arousal thresholds. For example, elevated noise levels or poor air quality may contribute to sleep fragmentation or hyperarousal.

[0196] The disclosed system solves a technical problem in sleep monitoring and treatment technologies by providing real-time, actionable insights based on a holistic analysis of multiple physiological signals. This enhances the accuracy of sleep predictions and the effectiveness of thermoregulation therapies. The system’s ability to deliver personalized sleep recommendations and therapies based on real-time data collected from the user enables effective insomnia treatments and improves the user’s overall sleep quality. The system integrates sensors (for example, temperature, heart rate, SpO . and light exposure sensors), along with algorithms for data analysis, to provide a more comprehensive understanding of the user’s sleep patterns and circadian rhythms. The use of DPG measurements, combined with personalized therapies and real-time data analysis, improves the technical field of sleep monitoring while offering practical benefits for individuals suffering from sleep disorders. Artificial intelligence (Al) and machine learning methods, such as artificial neural networks, deep neural networks, etc., can be implemented to analyze known medical data and inputs from the user, including but not limited to mood, energy, sleep, activity, nutrition, social interactions, environmental context, self-regulation strategies, and medication use to generate personalized treatment plans based on the user’s physiological and historical data. This ensures that therapy choices are informed by a wide range of relevant information, leading to more effective treatments.

[0197] Some embodiments provide a circadian temperature-focused approach that provides deeper physiological insight as temperature gradients provide a more nuanced view of sleep transitions and circadian patterns, which are often missed by traditional actigraphy or HR-only tools. This also provides a more targeted understanding of insomnia by capturing deviations in thermal regulation patterns that can be used to identify root causes of sleep disturbances rather than just their symptoms. The circadian system further providesMWS Docket No. 114212-0338personalized insights by combining continuous physiological monitoring with subjective input, enabling the delivery of more personalized, actionable feedback over time.

[0198] Additionally, the integration of external wearable devices to capture physiological data further refines the treatment process, providing a more holistic view of the user’s condition. The closed-loop system for monitoring treatment adherence and outcomes allows for continuous feedback and adjustment of treatment plans, ensuring that users receive the most appropriate care throughout their treatment journey.

[0199] Embodiments are not limited to insomnia management, circadian entrainment, and treatment. For example, the invention can be understood by one of ordinary skill in the art to apply to any sleep disorder.Example Architecture

[0200] FIG. 16 is a block diagram illustrating details of a system 1600 for sleep quality management, according to some embodiments. Specifically, FIG. 16 shows details of a client device 110-2 and server 130-2 used in a network architecture as disclosed herein (for example, network architecture 100), according to some embodiments. The client device 110-2 and server 130-2 are similar to the embodiments of the client device 110-1 and server 130-1 discussed above with respect to FIG. 2, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0201] Client device 110-2 and server 130-2 are communicatively coupled over network 150 via respective communications modules 1618-1 and 1618-2 (hereinafter, collectively referred to as “communications modules 1618”). Communications modules 1618 are configured to interface with network 150 to transmit or receive information, such as user data, analysis results, user input data, and / or the like to other devices on the network 150. Communications modules 1618 can be, for example, modems or Ethernet cards, and can include radio hardware and software for wireless communications (for example, via electromagnetic radiation, such as radiofrequency -RF-, near field communications -NFC-, Wi-Fi, and Bluetooth radio technology).MWS Docket No. 114212-0338

[0202] Client device 110-2 can be coupled with an input device 1614 and with an output device 1616. A user can interact with client device 110-2 via the input device 1614 and the output device 1616. Input device 1614 can include a mouse, a keyboard, a pointer, a touchscreen, a wearable input device (for example, a haptics glove, a bracelet, a ring, an earring, a necklace, a watch, etc.), a microphone, a controller, a joystick, a virtual joystick, a camera, a touchscreen display that a user can use to interact with client device 110-2, or the like. In some embodiments, input device 1614 can include cameras, microphones, and sensors, such as touch sensors, acoustic sensors, inertial motion units -IMUs- and other sensors configured to provide input data. Output device 1616 can include a screen display (for example, an LCD display screen and / or LED display screen), a touchscreen, a speaker, a projector, holographic, or augmented reality display (such as a heads-up display device or a head-mounted device), and / or the like. According to some embodiments, the client device 110-2 can be used to collect sleep assessments from the client device or an external data source and deliver personalized recommendations with users.

[0203] Client device 110-2 can also include a processor 1612-1, configured to execute instructions stored in a memory 1620-1, and to cause client device 110-2 to perform at least some operations in methods consistent with one or more embodiments and some operations are offloaded to a core processing component or server 130-2. Memory 1620-1 can further include an application 1622 and a display 1624, configured to run in client device 110-2 and couple with input device 1614 and output device 1616. The application 1622 can be downloaded by the user from server 130-2 and / or can be hosted by server 130-2. The application 1622 includes specific instructions which, when executed by processor 1612-1, cause operations to be performed according to methods described herein. In some embodiments, the application 1622 runs on an operating system (OS) installed in client device 110-2. In some embodiments, application 1622 can run out of a web browser. Data and files associated with the application 1622 can be stored in database 152.

[0204] Application 1622 provides a user interface that is displayed on a screen of the client device 110-2 and allows users to input commands to control the operation of the application 1622, view outputs from engine 1632, interact with other client devices, or the like. Application 1622 enables users to track and view circadian therapy recommendations, progress, set sleep goals, view treatment plans, make adjustments to treatment plans, andMWS Docket No. 114212-0338follow up care. The application 1622 can be implemented as a web page, a collection of web pages, or other content designed to be displayed within an internet browser.

[0205] Server 130-2 includes a memory 1620-2, a processor 1612-2, and communications module 1618-2. Hereinafter, processors 1612-1 and 1612-2, and memories 1620-1 and 1620-2, will be collectively referred to, respectively, as “processors 1612” and “memories 1620.” In some implementations, the server 130-2 can be used as part of a management platform implemented via the network 150. In some embodiments, the processor is configured to control a graphical user interface (GUI) or display 1624 for the user of client device 110-2 accessing the server of a management platform. According to some embodiments, the management platform can synthesize user data for rapid review and interpretation (at client device 110-2), supporting real-time communication with users.

[0206] Processors 1612 (for example, central processing units (CPUs), graphical processing units (GPUs), holographic processing units (HPUs), etc.) are configured to execute instructions stored in memories 1620. The processors 1612 can be a single processing unit or multiple processing units in a device or distributed across multiple devices (for example, distributed across two or more of client device 110-2 such as a user mobile device and a user wearable device). The processors 1612 can be coupled to other hardware devices, for example, with the use of an internal or external bus, such as a PCI bus, SCSI bus, wireless connection, and / or the like. The processors 1612 can communicate with a hardware controller for devices, such as input device 1614 and output device 1616. Processors 1612 can be configured to analyze wearable sensor data, test results, medical and pharmaceutical data, user treatment history, or the like, to generate and provide personalized treatment recommendations.

[0207] Memories 1620 can include both read-only and writable memory. For example, a memory can include one or more of random access memory (RAM), various caches, CPU registers, read-only memory (ROM), and writable non-volatile memory, such as flash memory, hard drives, floppy disks, CDs, DVDs, magnetic storage devices, tape drives, and so forth. The memories 1620 can include program memory that stores programs and software. The memories 1620 can also include data memory that can include information to be provided to the program memory or any element of the network.MWS Docket No. 114212-0338

[0208] Memory 1620-2 can include an engine 1632 and an Al tool 1634. The engine 1632 can share or provide features and resources with application 1622 for presentation at display 1624, including Application Programming Interfaces (APIs) and other services that the application 1622 can use to perform functions, such as accessing external data sources or integrating with other software. The user can access information from engine 1632 through application 1622, installed in memory 1620-1 of client device 110-2. Accordingly, application 1622, including display 1624, can be installed by server 130-2 and perform scripts and other routines provided by server 130-2 through any one of multiple tools. Server 130-2 can include an API layer, which controls applications in the client device 110-2. An API layer can also provide tutorials to users of the client device 110-2 as to new features in the application 1622.

[0209] According to some embodiments, engine 1632 can include one or more sets of machine -readable instruction modules that, when executed by processors 1612, are configured to perform operations according to some embodiments described herein. For example, the engine 1632 can include a research module configured to track sleep disorder developments in the health and technology space. For example, the engine 1632 can include a phenotype generation module configured to identify a phenotype of a user based on user data and sleep disorder assessment. For example, the engine 1632 can be configured to facilitate provisions of first-line therapy based on input data while leveraging a generative AI / ML model trained at Al tool 1634. As another example, engine 1632 can be configured to manage end-to-end circadian therapy workflow for insomnia management. The aspects of the circadian therapy workflow can be provided to the users (for example, user 1704 in FIG. 17) via application 1622.

[0210] The Al tool 1634 can be configured to provide Al driven sleep disorder treatment recommendations tailored to each user profile. In some embodiments, the Al tool 1634 can be configured to phenotype users based on their symptoms, medical history, physiological / user data, or the like. Phenotypes may be used to classify insomnia users and provide recommendations that are phenotypically more relevant to the user. The Al tool 1634 can be part of one or more machine learning models stored in the database 152. In some embodiments, at least one or more training archives or machine learning models can be stored in memories 1620. The database 152 includes training archives and other data files thatMWS Docket No. 114212-0338can be used by engine 1632 in the training of a machine learning model, according to the input of the user through application 1622 and data extracted through the network 150.

[0211] The Al tool 1634 can include algorithms trained for the specific purposes of the engine 1632 and tools included therein. The algorithms can include machine learning or artificial intelligence algorithms making use of any linear or non-linear algorithm, such as a neural network algorithm, or multivariate regression algorithm. In some embodiments, the machine learning model can include an LLM, Natural Language Understanding (NLU) model, a neural network (NN), a convolutional neural network (CNN), a generative adversarial neural network (GAN), an unsupervised learning algorithm, a deep recurrent neural network (DRNN), a classic machine learning algorithm such as random forest, or any combination thereof. More generally, the machine learning model can include any machine learning model involving a training step and an optimization step. In some embodiments, the database 152 can include a training archive to modify coefficients according to a desired outcome of the machine learning model. Accordingly, in some embodiments, engine 1632 is configured to access the database 152 to retrieve data and archives as inputs for the machine learning model. In some embodiments, engine 1632, the tools contained therein, and at least part of database 152 can be hosted in a different server that is accessible by server 130-2 or client device 110-2.

[0212] Some implementations can be operational with numerous other computing system environments or configurations. Examples of computing systems, environments, and / or configurations that can be suitable for use with the technology include, but are not limited to, personal computers, server computers, handheld or laptop devices, cellular telephones, wearable electronics, gaming consoles, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and / or the like.Insomnia Management and Circadian Entrainment Workflow

[0001] FIG. 17 illustrates a closed-loop circadian therapy workflow 1700, according to some embodiments. The workflow 1700 is similar in some respects to the embodiment of the workflow 300 discussed above with respect to FIG. 3, and like reference numerals have been used to refer to the same or similar components. TheMWS Docket No. 114212-0338following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0213] The workflow 1700 can include a user application 1702 (for example, application 1622) used by user 1704, wearing wearable sensors 1706, and may also include external devices 1708. The user application 1702 may be hosted insomnia management and circadian entrainment platform 1710 (for example, server 130-2), and authorized credentials can be required to gain access to the user application 1702. The user application 1702 can be how users engage with platform 1710. For example, platform 1710 includes sleep coaching that user 1704 can participate and take advantage of via the user application 1702. The user 1704 can be using, connected to, or associated with the wearable sensors 1706 used for collecting user data from the user 1704 for processing by platform 1710. At least a portion of the user data can be input by the user 1704 via the user application 1702 (for example, demographic information, treatment plan symptoms, sleep diary, medical history, etc.) and / or can be stored in a database (for example, database 152) coupled to platform 1710 in a user profde associated with the user 1704. For example, the user information can include the user’s EHR.

[0214] According to some embodiments, the closed-loop circadian therapy — facilitating user feedback, circadian data analysis, and treatment administration — can be integrated with platform 1710. This is designed to streamline user onboarding and management of sleep-related challenges, improve operational efficiency in treatment workflows, and support the delivery of comprehensive, personalized user care.

[0215] According to some embodiments, platform 1710 can support and present data through computerized alerts and reminders about critical user information, such as evidencebased recommendations for treating sleep disorders, user data reports and summaries, focused reports that summarize user information, documentation templates (for example, for recording user information or billing), assistance tools, and contextually relevant reference information (for example, medical literature and resources relevant to the user’s condition).

[0216] Those skilled in the art will appreciate that user application 1702 invariably includes a range of additional features (for example, components for sleep application, sleep restriction, stimulus control, cognitive restructuring, light exposure management, relaxationMWS Docket No. 114212-0338techniques, goal setting, sleep coaching, sleep schedules and gamified components such as for delivering gamified cognitive brain training exercises, etc.).

[0217] According to some embodiments, the wearable sensors 1706 can integrate data inputs from multiple sources (including external devices), enhancing treatments or therapies applied or recommended by platform 1710. Wearable sensors 1706 can include at least two wearable devices (worn by the user 1704) and comprise sensors for measuring physiological data including, but not limited to, body temperature, heart rate, SpO . movement, and heat flux, of the user 1704, as well as environmental data (for example, light exposure, sound, humidity, ambient temperature, and air quality). The measured physiological, biological response and / or environmental data are relevant to the circadian rhythm tracking that the user is undergoing in terms of both delivering particular treatments (for example, thermoregulation) and measuring their effectiveness.

[0218] In some embodiments, wearable sensors 1706 comprises dual sensor pods that may be attached to the user in a proximal and distal location. The dual sensor pods are configured to monitor DPG and modulate DPG for personalized, restorative sleep. In some embodiments, wearable sensors 1706 comprises other form factors including, but not limited to, a mattress topper, ring, smart watch, toe-ring, ankle band, ankle patch, smart garments, earrings, headband, glasses, etc. These devices may vary in size and placement, allowing for flexible deployment across different body locations to accommodate user preferences and optimize data collection.

[0219] The user application 1702 can be used to control the wearable device, receive data from the sensors and transmit the data to platform 1710, transmit sensory actuation commands to the wearable device, as well as serving as an application for delivering the various components of a circadian rhythm tracking program to the user 1704. The user application 1702 can be used to understand, predict, and adjust a desired optimal bedtime. Recommendations or treatment options provided by platform 1710 can then be tailored to align the user’s current sleep patterns with their desired sleep settings.

[0220] In some implementations, the wearable device also includes one or more sensory actuators for providing sensory actuation or feedback (such as haptic, visual, auditory or other feedback) to the user as an aspect of the circadian rhythm tracking / therapy. By nonlimiting example, actuation or feedback can be used to trigger a prompt to the user to enter aMWS Docket No. 114212-0338cognitive input into the user app relevant to the insomnia-related event to which the sensory activation relates.

[0221] In some embodiments, platform 1710 can receive data inputs from other data sources including, but not limited to, sleep assessments, DMEs, biomarkers, wearable device(s), implants, or the like. Devices and / or DMEs can include, for example, CPAP machines, Bilevel Positive Airway Pressure (BiPAP) machines, vital sign monitors (for example, blood pressure monitors, pulse oximeters, and thermometers), EEGs, ECGs, EOGs, EMGs, spirometers, Remote Patient Monitoring (RPM) devices, or other devices used for determining sleep assessment scores, obtaining sleep results data (for example, raw data from sleep tests), or the like. The devices and / or DMEs can be used to collect data including EEG waveforms, PSG data, physiological signals from sleep studies, or other medical data understood by one of ordinary skill in the art to be relevant to sleep disorder diagnosis and / or treatment. In some implementations, the user data can be processed in real time by platform 1710 (for example, engine 1632).

[0222] According to some embodiments, platform 1710 can utilize data collected from the wearable sensors 1706 to track circadian rhythms, sleep patterns, identify sleep-related issues, and measure progress over time (for example, post-treatment delivery) based on physiological signals. The wearable sensors 1706 can record initial patterns in physiological data at different sleep and wake times, total sleep duration, nighttime awakenings, and other factors influencing sleep quality to establish a baseline for the user 1704. The baseline can be used to identify misalignments in the user’s circadian clock (or desired circadian clock), such as inconsistent sleep patterns, prolonged awakenings during the night, spending too much time in bed awake, and other behaviors. The baseline can be established based on what is considered normal according to a set of characteristics (for example, age). According to some embodiments, physiological data can be collected during the day as well as at night and further used to generate a baseline for the user.

[0223] By non-limiting example, platform 1710 can analyze continuous physiological data for a predetermined period of time (for example, 2-4 weeks) — including, but not limited to, body temperature, heart rate, movement, heat flux, and more — alongside subjective inputs (for example, from sleep diaries, validated sleep and wellness questionnaires, etc.). The combined dataset can be used to establish a personalized baseline for each individual, allowing platform 1710 to detect deviations and patterns that are specific to the user’s sleepMWS Docket No. 114212-0338behavior and physiology. According to some embodiments, the user 1704 can be guided through a questionnaire or sleep assessment through the user application 1702 during which the user 1704 can describe their desired sleep goals (for example, fall asleep faster at a desired time, sleep more deeply, wake up naturally at a preferred time, etc.), current sleep habits, or sleep issues. In some implementations, the user’s sleep goals and physiological data collected can be used to enhance the baseline and drive recommendations and treatment delivery.

[0224] Platform 1710 is configured to support personalized onboarding and treatment of circadian rhythm misalignments using sleep signatures. For example, patterns within physiological data may be analyzed to identify signatures associated with sleep issues, including, but not limited to, the amplitude of circadian rhythms as inferred from skin and core body temperature fluctuations over a 24-hour period, REM fragmentation, frequency of hyperarousals, transitions between sleep stages, or the like. These insights enable the platform to tailor interventions and behavioral guidance to the user’s specific sleep challenges, helping to address the underlying causes and optimize treatment timing and effectiveness.

[0225] In some implementations, platform 1710 may be configured to support personalized onboarding and treatment of circadian rhythm misalignments using sleep signatures. For example, patterns within physiological data may be analyzed to identify features associated with insomnia, including — but not limited to — the amplitude of circadian rhythms as inferred from skin and core body temperature fluctuations over a 24-hour period, REM fragmentation, frequency of hyperarousals, and transitions between sleep stages. These insights enable the platform to tailor interventions and behavioral guidance to the user’s specific sleep challenges, helping to address the underlying causes and optimize treatment timing and effectiveness.

[0226] Platform 1710 can identify signatures within physiological signals including, for example, a DPG change between transitions to different sleep stages. DPG can be used as a biomarker for sleep readiness and sleep quality. The body does a gradient change naturally, when it is getting ready for sleep and waking up. Additionally, the gradient holds close to zero to maintain good sleep quality. As such, recording the DPG can allow for valuable insights on a user’s circadian rhythm. Based on this, platform 1710 can identify treatment options that can improve the quality of sleep overall and / or at specific sleep stages.MWS Docket No. 114212-0338According to some embodiments, platform 1710 can leverage features such as threshold detection, signal slopes (for example, DPG trend slopes), and temporal trends to extract meaningful insights from this data. Accordingly, platform 1710 adapts dynamically to each user’s night-to-night variations and long-term trends, enabling tailored treatment recommendations that evolve over time — effectively coaching the user to better quality sleep.

[0227] By non-limiting example, physiological patterns tied to circadian rhythms can include proximal skin temperature dropping while distal skin temperature rises approximately an hour before bedtime, increasing the skin temperature gradient. As another non-limiting example, both skin temperatures can converge at sleep onset, reducing the gradient to near zero. As another non-limiting example, skin temperature can decline about an hour before waking, signaling impending arousal. As another non-limiting example, core body temperature can naturally drop in the evening, signaling readiness for sleep, and reach its nadir between 4-6am, often followed by REM sleep.

[0228] According to some embodiments, platform 1710 can generate personalized treatment recommendations using an Al model. The personalized treatment recommendations can be based on physiological data and relevant clinical data. In some embodiments, the platform 1710 can be configured to track clinical data, including but not limited to, developments in sleep disorders within the health and technology space, as well as other contextually relevant data points. The platform 1710 can also monitor advancements in diagnostic tools, device and treatment protocols, and user outcomes (for example, from public health records) related to sleep disorders. Clinical data can further include public health data, research data including development of new treatments, devices, drug trials, technology (for example, medical devices), and other known medical knowledge.

[0229] In some implementations, clinical data can be extracted by the platform 1710 from one or more external data sources (for example, the web, medical databases, and health information exchanges). This data extraction can include automated web scraping, API integrations, and data feeds from trusted medical sources.

[0230] In some implementations, clinical data can be received by platform 1710 from one or more sources (for example, research institutions, healthcare providers, and user registries). This can involve direct data submissions, secure data transfers, and / or collaborations with academic and clinical research organizations. By integrating these diverseMWS Docket No. 114212-0338data sources, the system aims to provide a comprehensive and up-to-date view of clinical developments, enhancing the ability to manage and / or treat sleep disorders effectively.

[0231] The Al model can use physiological data and clinical data to phenotype the user. The Al model can use physiological data and clinical data to perform treatment matching and generate treatment recommendations best suited for the user 1704 based on data-driven insights. In some implementations, a phenotype is assigned to a user and used to guide treatment recommendations. In some implementations, data from a user’s EMR is used to establish the user’s baseline for the treatment recommendations. This is important because preexisting conditions, medication history, etc., can alter treatment options administrable to the user. The Al model can be continuously trained on technological and medical advancements to assist in providing new and beneficial treatment options. Training data can include details about the devices themselves, regulatory approvals, reimbursement information, insurance information, etc.

[0232] According to some embodiments, wearable sensors 1706 can include (for example, within the proximal and distal devices) or be communicatively coupled with, for example, external device(s) 1708. The external device(s) 1708 can be a treatment delivery component configured to administer treatment based on the platform 1710 (for example, a temperature-controlled mattress topper). In some implementations, the treatment delivery component can include a thermoregulation device configured to adjust body temperature through localized cooling or warming in accordance with treatment recommendations generated by the platform 1710. In some implementations, the treatment delivery component can include an electrical stimulation device delivering non-invasive brain stimulation, either pre-sleep or during sleep, to improve sleep onset and maintenance. In some implementations, the treatment delivery component can include an auditory stimulation device which uses bone conduction audio to enhance slow-wave and REM sleep, without disrupting the sleeper.

[0233] In this manner, the platform 1710 integrated with the wearable sensors 1706 lowers the risk of the user experiencing negative biological responses during sleep caused by their sleep disorder. By non-limiting example, the thermoregulation device can apply heating or cooling to keep the user in REM sleep for a longer period of time. In some embodiments, treatments like thermoregulation and electrical stimulation can be integrated into a closed-loop feedback system, where the Al continuously monitors real-time signals and autonomously triggers interventions (for example, initiating cooling during specific phases ofMWS Docket No. 114212-0338sleep). This adaptive, insight-driven approach is designed to move beyond passive monitoring — toward active, personalized intervention to improve sleep outcomes.

[0234] According to some embodiments, wearable sensors 1706 can include or be communicatively coupled with a light sensor for detecting light exposure on or in an environment of user 1704. The light sensor can be used to provide light therapy through personalized guidance on timing and intensity of light exposure, promoting circadian alignment through increased daytime light and reduced evening exposure. By non-limiting example, platform 1710 can be configured to create parallel relationships to light and physiological behavior which can contribute to misalignments in the user’s circadian rhythm. Based on data collected from wearable sensors 1706, the platform 1710 can generate and provide a recommendation to the client to improve sleep quality (for example, reduce light exposure at least thirty minutes before bedtime). In some implementations, wearable sensors 1706 include biosensors including, but not limited to, sweat sensors, GSR sensors, and EDA sensors to monitor emotional arousal and stress levels.

[0235] According to some embodiments, the platform 1710 can provide, alongside the personalized treatment recommendations, detailed reasoning and explanations to support the suggested treatment options. This can include generating and incorporating links to relevant resources, summaries of clinical studies, and approvals (for example, government approvals) associated with the recommended treatment options or products, etc. In some implementations, the recommendations also include insights into the efficacy, safety, and potential side effects of the treatments. In some implementations, each recommendation also includes a statistical analysis of treatment results. The analysis can be limited to outcomes from users with the same or similar circadian clock patterns or all available users.

[0236] In some implementations, the personalized treatment recommendation can include multiple therapies wherein the user is recommended to transition into each of the multiple therapies. For example, user 1704 can be recommended to start with neuromodulation to help with falling asleep for a first part of the treatment course for a first duration of time and then transition to thermoregulation therapy to maintain sleep as a second part of the treatment course for a second duration of time. As such, the platform 1710 can make connections between different comorbidities to guide users to connect to the right treatment specific to their phenotypes and needs.MWS Docket No. 114212-0338

[0237] According to some embodiments, the personalized treatment recommendations can include, but are not limited to, treatment options such as light therapy and circadian rhythm tracking-based thermoregulation. The treatment recommendations may be in addition to or in combination with other therapies including, but not limited to, medication, DMEs, CBTI, respiratory therapies, neuromodulation / neuro stimulation devices, etc., or any combination thereof. By non-limiting example, a personalized treatment recommendation can include a treatment match transmitted to the user application 1702, an inbox associated with the user 1704, or the like, indicating that “You have sleep onset issues and a history of not adhering to CBTI. We recommend trying PAP as a primary treatment.” As such, user 1704 can take the platform’s recommendation, providing insights and recommendations tailored to each user profde, and make a decision on how to proceed.

[0238] In some embodiments, platform 1710 can be configured to deliver direct light therapy through spectral manipulation to influence circadian alignment and sleep onset. This capability can be integrated with ambient lighting systems in the user’s environment, enabling dynamic adjustments to light exposure based on real-time physiological data and treatment recommendations. Such integration supports personalized light therapy delivery aligned with the user’s biological rhythms and sleep goals.

[0239] The platform 1710 is designed for multi-system integration, streamlining user follow-ups with centralized sleep quality tracking, therapy administration, and care management, improving the quality-of-care delivery. In some embodiments, the platform 1710 can be integrated with a broader therapy ecosystem and support treatment options beyond what may be administered by the monitoring devices including, for example, treatments for respiratory-related sleep disorders, such as upper airway resistance syndrome (UARS) or sleep apnea, through advanced positive airway pressure (PAP) devices or the like.

[0240] According to some embodiments, the platform 1710 enables provision of first-line therapy including, for example, administrating any products or prescriptions and the ability to dynamically adjust therapies based on new data (for example, user outcomes, clinical data, etc.). Provision of first-line therapy enables clinician-led therapies to enhance user engagement, scale treatment capabilities, and support sustainable income through billing (for example, Remote Therapeutic Monitoring (RTM) billing codes). Accordingly, platform 1710 can include a provider, insurance, and / or a billing feature. This can include determiningMWS Docket No. 114212-0338an appropriate bill based on user data (for example, insurance information), services rendered, and generating a bill based therefrom.

[0241] The platform 1710 operates as a closed feedback loop. According to some embodiments, this loop can utilize subjective assessments within the user application 1702 to validate and refine insights. User feedback ensures that the detected physiological patterns align with actual user experiences, facilitating continuous improvement of the platform 1710 algorithms and personalization of insights.Monitoring System

[0242] FIG. 18 is an overview of a monitoring system 1800 (for example, wearable sensors 1706 and external device(s) 1708 of FIG. 17, and / or client device 110-2 of FIG. 16), according to some embodiments. The monitoring system 1800 is similar in some respects to the embodiment of the monitoring system 400 discussed above with respect to FIG. 4, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0243] The monitoring system 1800 can be a dual location system that is actionable based on physiological responses during a monitoring period to enhance sleep quality by leveraging the body’s natural cues for personalized intervention. The dual location system can include a first wearable device 1802 and a second wearable device 1804. In some implementations, the first wearable device 1802 and second wearable device 1804 can comprise dual sensor pods configured for attachment to the user (for example, via an adhesive patch, a strap, a clip, integration into a garment, etc.).

[0244] The first wearable device 1802 can include a proximal sensor and the second wearable device 1804 can include a distal sensor. The proximal and distal physiological data captured by the first wearable device 1802 and second wearable device 1804 can be used for precise circadian clock tracking with continuous core body temperature. According to some embodiments, the first wearable device 1802 and second wearable device 1804 provide two discrete temperature sensors on or near the body to collect physiological data. Based on the proximal and distal physiological data, a distal-proximal temperature gradient can be computed at a platform (for example, platform 1710) to assess sleep quality trends over time.MWS Docket No. 114212-0338

[0245] According to some embodiments, one or both of the devices can also be configured to administer treatment based on analysis of the collected physiological data. In some embodiments, the monitoring system 1800 can include an external device configured to administer treatment. Treatments administered by the monitoring system can include, but are not limited to, timing interventions (for example, light exposure, bedtime shifts, thermoregulation therapy, etc.) guided by DPG slope trends, behavior-linked modulation, or the like.

[0246] According to some embodiments, the first wearable device 1802 and second wearable device 1804 are designed to be modular and adaptable. Meaning, the proximal and distal sensors included in the first wearable device 1802 and second wearable device 1804 are interchangeable and can be used for either proximal or distal location placement. This plug-and-play capability simplifies the setup process for users and ensures compatibility with a wide range of platforms. The modular sensors can be used in diverse environments, from clinical settings to home-based monitoring systems. Their adaptability ensures that they can meet the specific needs of different users and applications. The first wearable device 1802 and second wearable device 1804 can be integrated into various systems to provide sleep coaching, real-time behavioral feedback, and sleep timing optimization recommendations based on DPG slope analysis — enhancing their versatility and usability across different applications. The sensors can be used in diverse environments (for example, clinical settings to home-based monitoring systems).

[0247] Proximal and distal skin temperature can vary, for example, 4-5 degrees, while core body temperature typically varies 0.5-1 degrees over a 24-hour period. At night, dim light signals the body to wind down, with core temperature dropping and extremities warming up to help facilitate sleep onset. Wake up can follow a drop in skin temperature, with core temperature rising and extremities cooling. Bright light reinforces this transition, helping you feel alert and ready for the day. These temperature dynamics are reflected in the DPG slope, which some embodiments can use to trigger real-time sleep guidance through, for example, light exposure and thermoregulation, aligned with an individual’s desired readiness-to-sleep window.

[0248] Illustrations of the temperature changes throughout the day (for example, FIG. 18) may be provided to the user at a user interface of platform 1710. By non-limiting example, during the day, when the proximal skin temperature is higher, the illustrationMWS Docket No. 114212-0338highlights the torso and upper limbs in warm red tones, indicating elevated proximal temperatures, while the extremities (such as hands and feet) are shaded in cooler blue hues, reflecting lower distal temperatures. A sun icon may be used to reinforce the daytime context. Additionally, during the night, the visual may shift to showing the extremities depicted in red to signify increased distal skin temperature, while the torso and upper limbs appear in blue, denoting a drop in proximal temperature. A moon icon may be used to reinforce the nighttime context. These color-coded visuals provide an intuitive understanding of circadian thermal regulation patterns of the user.

[0249] According to some embodiments, the platform can determine one or more physiological patterns tied to circadian rhythms and deliver treatments accordingly. Sleep quality can be assessed using DPG slope trends, which reflect the alignment of physiological signals with expected sleep phases. By non-limiting example, indicators of high-quality sleep include skin temperature rise at sleep onset, close alignment of distal and proximal temperatures during sleep, core temperature dropping and remaining low, and heart rate slowing at onset. By non-limiting example, low-quality sleep may be indicated by pre-onset skin temperature rise, persistent temperature differences, lack of core temperature drop, and high heart rate variability. These patterns inform a real-time feedback loop that supports behavioral modifications, sleep coaching, and timing optimization via a modulation engine tailored to the user’s circadian readiness.

[0250] FIG. 19 is an overview of a circadian therapy system 1900, According to some embodiments. The system 1900 is similar in some respects to the embodiment of the system 500 discussed above with respect to FIG. 5, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0251] As shown in FIG. 19, the application 1902 can be communicatively coupled to dual sensor pods 1904, which can be placed at distal and proximal locations on or around a user’s body. The dual sensor pods 1904 can be charged using a charging station 1906. The devices can be attached to the user using connectors 1908, including but not limited to, straps, adhesive bandages, or other connecting means. The dual sensor pods 1904 can be configured to monitor the user, collect physiological data, light exposure, and the like. The dual sensorMWS Docket No. 114212-0338pods 1904 can also administer temperature treatment therapies, including but not limited to, thermoregulation.

[0252] FIG. 20 is an exemplary workflow 2000 for two monitoring devices in a monitoring system, according to some embodiments. The workflow 2000 is similar in some respects to the embodiment of the workflow 600 discussed above with respect to FIG. 6, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0253] In some embodiments, the first device can correspond to a distal device, and the second device can correspond to a proximal device. The distal device 2004 and proximal device 2002 can include a plurality of sensors configured to monitor physiological data from a user with a particular emphasis on monitoring circadian health biomarkers such as DPG — sensing core body and skin temperature in two locations. According to some embodiments, the distal device 2004 can include a core body temperature sensor, photoplethysmogram (PPG) sensor, skin temperature sensor, and an accelerometer and gyroscope. According to some embodiments, the proximal device 2002 can include a core body temperature sensor, skin temperature sensor, and an accelerometer and gyroscope.

[0254] Although one of each of the sensors are illustrated, embodiments are not limited to this and can include one or more or any combination of the sensors. In some embodiments, the sensors can further include pulse oximeters, infrared (IR) temperature sensors, pulse sensors, or the like.

[0255] The distal device 2004 and proximal device 2002 can take a variety of forms including being worn like a necklace around the user’s neck and contacting the user’s upper chest. The wearable device can also be attached to the user by way of a patch that contacts the user’s skin at a suitable location such as the upper arm, wrist or the back of the neck. The various physiological sensors that are incorporated in the wearable device can include, but are not limited to, a movement sensor, respiration sensor, temperature sensor, heart rate sensor, SpO2sensor, galvanic skin response sensor, light exposure sensor, and / or sweat sensor, etc.

[0256] Physiological sensors may be used to assess sleep efficiency and sleep quality. High sleep efficiency and quality generally indicate restful, uninterrupted sleep, while lowMWS Docket No. 114212-0338sleep efficiency can suggest difficulty falling asleep, frequent awakenings, or waking up too early. DPG is a robust physiological marker for circadian sleep drive and sleep quality, serving as a strong predictor of sleep propensity, a reliable indicator of optimal sleep timing, and enables both phenotyping and thermoregulatory profiling.

[0257] In some embodiments, distal device 2004 and proximal device 2002 can comprise dual sensor pods that enable real-time monitoring of sleep quality via DPG, supporting a feedback loop that delivers behavioral modification suggestions, personalized sleep coaching, and / or automated therapy administration tailored to the individual user. These wearable devices can detect physiological signals such as hyperarousal and breathing irregularities, leveraging DPG to distinguish cases where sleep pressure is adequate, but sleep quality remains poor, indicating conditions beyond pure insomnia. Additional sensor inputs, including heat flux, movement, heart rate, and PPG, can be used to furthercharacterize physiological hyperarousal and respiratory disturbances during sleep, enabling more targeted and responsive interventions.

[0258] In some embodiments, DPG and heat flux measurements are used to assess daytime performance, particularly in athletes. DPG and heat flux monitoring can be leveraged in athletic contexts to provide real-time insights into performance, recovery, and injury prevention. Variations in heat dissipation, thermal regulation, and distal-proximal temperature gradients offer valuable indicators of physical exertion, recovery status, and overall metabolic efficiency. By analyzing these patterns during waking hours, platform 1710 can support improved sleep quality, performance optimization, and fatigue management strategies. Thermoregulatory strategies guided by DPG, such as targeted cooling or warming of specific body regions, can be employed during training to maintain optimal core temperature and prevent overheating, thereby enhancing endurance and reducing the risk of heat-related fatigue. During recovery periods, controlled thermal interventions informed by both heat flux and DPG can accelerate muscle repair, reduce inflammation, and promote restorative sleep by aligning with the athlete’s circadian rhythm. These strategies can be personalized based on real-time heat flux and temperature data and integrated with wearable technologies to deliver adaptive thermal support aligned with the athlete’s circadian rhythm and performance goals. These strategies are further enhanced by wearable technologies that deliver adaptive thermal support and integrate with features such as muscle-specific powerMWS Docket No. 114212-0338output monitoring, individual chronobiology profiling, and voice-enabled Al performance advisors.

[0259] In some embodiments, components of the monitoring system can also incorporate a number of behavioral sensors and actuators to support sleep quality determination and treatment effectiveness.

[0260] Distal device 2004 and proximal device 2002 can include a battery, powering each of the devices. The sensors on distal device 2004 and proximal device 2002 can be controlled by a processor (for example, a microcontroller integrated with a central processing unit (CPU) along with memory and input / output peripherals on a single chip). The processor can communicate with platform 1710 via a Bluetooth connection. The processor can control the sensors and transmit the physiological data to user application 1702 for processing by platform 1710. Platform 1710 can analyze the data, perform necessary computations, and then act (provide recommendations and treatment) based on those inputs.

[0261] According to some embodiments, platform 1710 can receive information from external data sources 2006, impacting recommendations or treatment delivery. In some implementations, this can include a light sensor exposed to an environment of the user 1704 (for example, attached to or near user 1704). According to some embodiments, Al models / algorithms 2008 may output a range of physiological and behavioral insights, including sleep pressure, sleep quality, sleep drive, sleep stages, hyperarousal, sleep propensity, the body’s readiness to wake, and the optimal sleep window (encompassing both sleep onset and wake-up time). Additionally, the models may generate recommendations for optimizing melatonin intake, light exposure, and thermoregulatory aids. Al models / algorithms 2008 can be configured to: (i) quantify sleep pressure, (ii) objectively measure sleep quality, and (iii) identify the optimal timing for sleep aids to be most effective. These capabilities enable platform 1710 to deliver personalized, data-driven interventions aligned with the user’s circadian profile.

[0262] Al models / algorithms 2008 are used to determine circadian patterns based on physiological data, subjective data (for example, user inputs), and user data. Al models / algorithms 2008 can incorporate machine learning models, algorithm libraries, expert systems, lookup tables and combinations thereof to analyze physiological, behavioral and other data that is uploaded to platform 1710. The circadian patterns in, for example, sleepMWS Docket No. 114212-0338pressure, sleep readiness, sleep quality, sleep drive, hyperarousal, and sleep stage transitions, can be derived from physiological signals (for example, DPG and heat flux data). For example, during sleep onset, skin temperatures typically rise because heat is drawn to proximal regions, while core body temperature drops, and heart rate slows. As another example, during sleep, skin and core body temperatures move closely together — a sign of good sleep quality. That is, core body and skin temperature can converge. Individuals with sleep maintenance insomnia can experience elevated core body temperatures at night, which can interfere with the ability to stay asleep. As another example, an hour before ideal wake up, skin temperature drops (wake-up signal), due to peripheral vasoconstriction, heat is drawn to the core and the body is preparing for awakening. Individuals with sleep onset insomnia can experience a delayed temperature drop, making it harder to fall asleep. By understanding a user’s circadian patterns, platform 1710 is able to deliver adaptive, data-driven interventions aligned with the user’s biological rhythms.

[0263] In some embodiments, Al models / algorithms 2008 can be extended to include diagnostic insights into comorbid conditions such as mental health disorders (for example, anxiety, depression), metabolic disorders (for example, diabetes risk), and behavioral patterns. These extensions enable a more comprehensive understanding of the user’s health profde, allowing the platform to identify underlying contributors to sleep disturbances and tailor interventions accordingly. Behavioral insights derived from longitudinal data can further inform therapy adherence, lifestyle recommendations, and stress-related sleep disruptions.

[0264] According to some embodiments, Al models / algorithms 2008 can be configured to perform sleep phenotyping based on continuous monitoring of DPG, heat flux, and / or other physiological signals. According to some embodiments, platform 1710 may diagnose a user with a sleep-related condition based on their identified phenotypic profile, enabling targeted treatment recommendations and alignment with appropriate care pathways. For example, if the Al determines that a user is experiencing poor sleep quality, based on indicators such as low sleep pressure or fragmented sleep, platform 1710 may initiate further analysis to support an insomnia diagnosis, or other sleep disorders including, but not limited to, RLS, sleep apnea, etc. According to some embodiments, platform 1710 can use the Al models / algorithms 2008 to generate recommendations, including behavioral modification suggestions, based on the user’s circadian patterns. In some embodiments, theMWS Docket No. 114212-0338recommendations can include light adjustment recommendations to restrict, limit, or increase light exposure (for example, when and how much light the user needs to further boost sleep quality). Using phenotyping and circadian pattern identification capabilities, platform 1710 can detect early signs of sleep-related dysfunctions, including multisystemic and non-specific symptoms (for example, night awakenings accompanied by increased heart rate, sweating, etc.; chronic sleep deprivation; anxiety; and fatigue).

[0265] In some implementations, platform 1710 may also surface associated physical symptoms such as pain, gastrointestinal disturbances, rosacea, and cognitive issues like brain fog. By recognizing these patterns early, platform 1710 can guide users toward appropriate interventions and escalate care when necessary (for example, to a broader therapy ecosystem or clinician-led system). In some implementations, platform 1710 can deliver direct light therapy through spectral manipulation integrated with ambient lighting systems in the user’s environment, including red and blue light wavelengths, to influence circadian alignment and sleep onset.

[0266] According to some embodiments, platform 1710 can use the Al models / algorithms 2008 to determine treatment and perform treatment delivery. In some embodiments, based on recommendations generated by Al models / algorithms 2008, distal device 2004 and proximal device 2002 may be configured to deliver personalized interventions. For example, platform 1710 can register when the user is ready for sleep, via a unique sleep biomarker, and determine that sensory feedback is needed to aid sleep onset. Platform 1710 can control sensory feedback including, for example, thermoregulation to support the user through one or more phases of sleep. Treatments can include one or more treatment options or combinations thereof to provide optimal therapy personalized to the user, for example, cognitive behavioral therapy and active thermoregulation.

[0267] In some embodiments, Al models / algorithms 2008 may support reproductive health features, including fertility and ovulation tracking, pregnancy detection, and conception risk estimation. These capabilities can be derived from circadian patterns and physiological signals such as temperature fluctuations, heart rate variability, and hormonal cycle patterns. Integrating reproductive health insights allows the platform to provide more comprehensive care recommendations and align sleep interventions with hormonal changes that may influence circadian rhythms and sleep quality.MWS Docket No. 114212-0338

[0268] FIG. 21 illustrates an exemplary design 2100 of the distal device 2004 and proximal device 2002 described in FIG. 20, according to some embodiments. The distal device 2004 and proximal device 2002 are similar in some respects to the embodiments of the distal device 604 and proximal device 602 discussed above with respect to FIGS. 6 and 7, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0269] The distal device 2004 and proximal device 2002 can include, but are not limited to, an upper housing, PCB / battery, sensors, lower housing, and LED lens cover. According to some embodiments, the distal device 2004 and proximal device 2002 can further include (not depicted) Bluetooth (for example, BLE transmitter / receiver), storage (for example, SPI Flash storage), temperature sensors (for example, for providing thermoregulation), and the like.

[0270] The example of FIG. 21 shows a core temperature sensor plate, but embodiments are not limited to this configuration and can include one or more of any combination of sensors. In the non-limiting example of FIG. 21, the appearance of distal device 2004 and proximal device 2002 differ, the proximal device 2002 having a round cylindrical shape and the distal device 2004 having a cuboid shape. In other embodiments, the sensors are the same in size / shape, and can be interchangeable with each other.

[0271] According to some embodiments, proximal device 2002 can be attached to the patient, for example, using an adhesive bandage (illustrated in FIG. 21), chain, cord, band, strap, frame (for example, eyeglass frame), and the like. According to some embodiments, distal device 2004 can be attached to the patient, for example, using a strap (illustrated in FIG. 21), chain, cord, band, or the like.

[0272] FIG. 22 is a block diagram of firmware 2200 implemented at one or more devices of a monitoring system, according to some embodiments. The firmware 2200 is similar in some respects to the embodiment of the firmware 800 discussed above with respect to FIG. 8, and like reference numerals have been used to refer to the same or similar components. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.MWS Docket No. 114212-0338

[0273] According to some embodiments, the firmware 2200 can include an acquisition recording module 2202. The acquisition recording module 2202 can start by acquiring data from sensors or inputs and recording it into memory. According to some embodiments, devices of the monitoring system can be switched on or off manually or via a mobile app.

[0274] Idle 2204 can be configured to cause the system to enter an idle state, waiting for further instructions or events. If no signal is detected (for example, the device is not in contact with the skin), the device remains in an idle state to conserve battery.

[0275] Idle memory full 2206 can be configured to determine when memory becomes full during acquisition and cause the system unpair 2210 where the system can impair from a connected device, such as a sensor or a data collector, to stop data acquisition. Data acquisition can continue when the idle memory is empty 2208. Reading 2212 can read the recorded data from memory for processing or transmission. Pause reading 2220 can pause the reading process if required, for example, to prioritize other tasks.

[0276] Lead detection 2214 can be configured to determine when signals should be recording 2216. The device continuously measures voltages around leads to detect if sensors are in contact with skin. Once a signal is detected, indicating the device is on the user’s body, the lead detection 2214 triggers the device to start recording data from all sensors (for example, temperature, movement, heart rate, oxygen blood level). The recording trigger signal can be based on a single sensor (for example, sensitive to skin contact).

[0277] Memory testing 2218 can be configured to perform memory testing to ensure data integrity and check for errors. Erasing 2222 can erase the recorded data from memory to free up space for new data acquisition after the data has been read.Circadian Monitoring Process Flow

[0278] FIG. 23 illustrates an example diagram of a process 2300, according to some embodiments. The process 2300 is similar in some respects to the embodiment of the process 900 discussed above with respect to FIG. 900, and like reference numerals have been used to refer to the same or similar operations. The following discussion focuses on the differences between these embodiments. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.MWS Docket No. 114212-0338Process 2300 can be implemented by a system utilizing a multi-sensor setup involving two primary monitoring devices.

[0279] At step 2302, process 2300 can include collecting user data and clinical data associated with the user. This can include subjective inputs through questionnaires to identify user needs, goals (for example, desired bedtime window), and user history, including comorbidities. By non-limiting example, users can fill out a questionnaire detailing their sleep patterns, lifestyle, medical history, and specific sleep-related issues. In some embodiments, this can include collecting essential information from users prior to the user receiving medical services. User intake information can include, but is not limited to, demographic information, medical history, authorizations for data collection, treatment, billing, or the like. In some implementations, an insomnia management platform can create a user profile based at least on the user intake. The user can enable access to EMR.

[0280] In some embodiments, a user can optionally undergo sleep studies at a sleep center or the like. Acquired data can include lab data acquisition from performance of a sleep study or other tests. In some implementations, the user can upload data (for example, records) to a cloud server of the insomnia management platform.

[0281] At step 2304, process 2300 can include generating a personalized baseline of the user’s physiological and sleep-related metrics using the collected data. The baseline can include initial core body temperature, heart rate variability, movement, activity levels, and SpO information. This baseline serves as a reference point for monitoring and treatment.

[0282] At step 2306, process 2300 can include receiving physiological data from a monitoring system. According to some embodiments, the monitoring system can include two or more sensors including at least a distal device and a proximal device such as dual sensor pods. In some implementations, the monitoring system comprises one or more other form factors including, but not limited to, a mattress topper, ring, smart watch, band, patch, smart garments, earrings, headband, glasses, or the like. These devices are equipped with sensors to measure physiological signals including, but not limited to, skin temperature, core body temperature, heart rate, movement, activity, light exposure, heat flux, respiratory rate, EDA, GSR, and SpCh. According to some embodiments, process 2300 can include continuous monitoring of sensor data from both distal and proximal devices for a given time period.MWS Docket No. 114212-0338

[0283] According to some embodiments, the distal device can be placed on peripheral body parts (for example, arms, legs), while the proximal device is placed near the central body (for example, chest, neck).

[0284] According to some embodiments, the distal device and proximal device can include lead detection to ensure sensors are in contact with the skin before recording data, optimizing battery usage and data accuracy.

[0285] At step 2308, process 2300 can include generating a Distal Proximal Gradient (DPG) slope based on the physiological data. DPG can be used as a biomarker to identify different sleep stages and circadian rhythm alignment. The distal device and proximal device capture temperature across different locations to analyze the temperature gradient between distal and proximal skin regions. This gradient is a physiological marker of circadian rhythm and sleep readiness, providing insights into sleep biology and mechanisms underlying insomnia.

[0286] According to some embodiments, process 2300 can further include phenotyping the user based on the physiological data. The user’s phenotype can be used to generate a sleep disorder diagnosis (for example, RLS, insomnia, sleep apnea, etc.).

[0287] At step 2310, process 2300 can include analyzing the DPG to determine sleep quality. In some embodiments, process 2300 is further configured to determine sleep pressure, the body’s readiness to wake up, sleep drive, sleep stages, hyperarousal, optimal sleep window (which includes sleep onset and wake up time), sleep propensity, optimized melatonin intake, optimized light exposure, and / or optimized thermoregulatory aids. Process 2300 can be further configured to detect trends and patterns in the user’s sleep readiness and quality. In some embodiments, patterns such as sleep-onset DPG and a sleep-wake DPG can be used to determine when a user is ready to sleep, wake up, enter REM, etc. This can be leveraged to influence sleep onset, sleep maintenance, and sleep-wake stages and to identify biomarking time windows for sleep. For example, a user can be ready to sleep (that is, reach an optimal time to go to sleep) when skin and core body temperature begin to align, as observed during quality sleep.

[0288] At step 2312, process 2300 can include generating individualized treatment plans based at least on the sleep quality. A treatment plan can be based on the DPG analysis and the user’s sleep goals to maximize sleep potential. The treatment plan can also includeMWS Docket No. 114212-0338recommendations for light exposure, behavioral changes to support circadian rhythm alignment, thermoregulatory profding, and / or other relevant interventions.

[0289] In some embodiments, a light sensor is included to monitor light exposure, which is crucial for circadian rhythm tracking. This sensor can be integrated into one of the primary devices or used as a separate component. Accordingly, the recommendation can be made based on data received from the light sensor.

[0290] At step 2314, process 2300 can include administering at least one treatment based on the treatment plans, achieving therapeutic results that improve sleep quality and help the user reach their sleep goals. According to some embodiments, treatments can include thermoregulation to adjust skin temperature, for example, warming or cooling specific body areas to enhance sleep stages. According to some embodiments, treatments can be adjusted based on real-time data. For example, thermoregulation interventions can be modified based on ongoing sensor readings from the monitoring system. According to some embodiments, treatments can include adjustments to light exposure. Process 2300 can further include adjusting light exposure in an environment of the user in accordance with at least one of the treatment recommendations (for example, to initiate sleep onset, sleep offset, or the like).

[0291] This method / process provides a comprehensive approach to monitoring and improving sleep quality by leveraging multi-sensor data and personalized treatment plans. It aims to address insomnia and enhance overall sleep health through targeted interventions and continuous monitoring.

[0292] FIGS. 24A-24B show exemplary alignments 2400 in core and body temperature and their relation to sleep readiness, according to some embodiments. Different temperature variances can be observed and individual to users. The alignments 2400 are similar in some respects to the embodiments of the alignments 1000 discussed above with respect to FIGS.10A and 10B, and like reference numerals have been used to refer to the same or similar components. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0293] As shown in FIG. 24A, proximal and distal temperature data may become more aligned as a person’s body prepares for sleep. A complete or near-complete overlap in these data sets may indicate that the body is physiologically ready for sleep. During the evening hours, FIG. 24A shows a time-series graph display including two fluctuating temperatureMWS Docket No. 114212-0338curves. For example, an orange-shaded region may be used to indicate core body temperature and a purple-shaded region may be used to represent skin temperature. The x-axis is segmented into three key time points — A (5 PM), B (bedtime preparation), and C (9 PM, sleep-ready) — marked by vertical lines. As the core body temperature and the skin temperature get closer to each other, it can indicate that the person is approaching optimal temperatures for sleep.

[0294] To the right of the graph, three sets of overlapping circles labeled A, B, and C further illustrate the convergence of core and skin temperatures. At point A, the orange and purple circles show minimal overlap, suggesting a physiological state not yet conducive to sleep. By point B, the overlap increases, signaling the body’s transition toward sleep readiness. At point C, the circles nearly converge, visually indicating optimal thermal conditions for sleep initiation. These graphical and symbolic elements work together to convey the gradual alignment of core and skin temperatures as a biomarker for sleep readiness.

[0295] Similarly, FIG. 24B illustrates that during the day, the proximal and distal temperature data tend to diverge beyond a threshold value. During sleep, the overlap may remain within a threshold range and begin to separate again as the body prepares to wake. These transitions may be visually represented to the user in a user interface through color gradients and variations that correspond to different sleep stages and physiological states. For example, during the day (as shown at 5 pm), the interface may display orange or light orange tones to indicate wakefulness. As the body begins to wind down in the evening (for example, 9 pm), the color may gradually shift to shades of blue, reflecting the cooling of distal regions and alignment of temperature data associated with sleep onset. In some implementations, sleep stages such as REM, deep, and light sleep may be illustrated using distinct colors (for example, purple for REM, dark blue for deep sleep, and lighter blue for light sleep) based on the DPG data. These visual cues enhance user understanding of their sleep patterns and transitions throughout the day and night.

[0296] FIG. 25 shows examples 2500 of cooling and heating applied to treat sleeping disorders such as insomnia using treatment delivery (for example, thermoregulation), According to some embodiments. The examples 2500 are similar in some respects to the embodiments of the examples 1100 discussed above with respect to FIG. 11, and like reference numerals have been used to refer to the same or similar components. Any of theMWS Docket No. 114212-0338various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0297] The treatment delivery can be administered to help align core and body temperature and improve overall sleep quality. FIG. 25 illustrates exemplary desired temperature distributions across the body through key sleep stages to help with circadian alignment to improve sleep quality. For example, thermoregulation may be applied during sleep onset to begin cooling upper extremities (which are shaded in blue to indicate cooling regions), and warm lower extremities (which are shaded in red to denote warming areas). Thermoregulation can continue during sleep, stabilizing the upper and lower body temperatures. Further, thermoregulation can be used to trigger wake signals by warming the upper extremities and cooling the lower extremities.Platform User Interfaces

[0298] FIG. 26 illustrates an exemplary display 2600 on a user dashboard showing a baseline circadian clock, according to some embodiments. The display 2600 is similar in some respects to the embodiment of the display 1200 discussed above with respect to FIG.12, and like reference numerals have been used to refer to the same or similar components. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0299] Each screen corresponds to a distinct time window and is color-coded to reflect the body’s physiological state. Display 2600 can be used by the user to understand their individual circadian rhythm through a visual translation of DPG data, enabling intuitive feedback on sleep readiness and timing.

[0300] For example, display 2602 can show periods of peak alertness or activity, shaded in a vibrant orange to represent the daytime phase when the body is most alert and engaged. In this time window, the core and skin temperatures are furthest apart. As another example, display 2604 can show when the body begins to wind down naturally showing the transition to a purple background, indicating the early nighttime period when the body begins to relax and prepare for rest. In this time window, the core and skin temperatures are beginning to align. As another example, display 2606 shows when the body is ready for bed and adopts a deep blue background, signifying the optimal window for sleep initiation. In this time window, the core and skin temperatures have the most overlap. These visualizations representMWS Docket No. 114212-0338DPG as a measure of sleep quality, sleep onset, or sleep pressure and can be used to monitor improvements overtime via the user dashboard. Each display 2600 can also include a set of icons along the bottom, representing application features such as user profde, notifications, and settings, reinforcing the continuity of the user experience across circadian phases.

[0301] FIG. 27 illustrates an exemplary display 2700 showing users’ ability to optimize their results based on preferred sleep times, according to some embodiments. The display 2700 is are similar in some respects to the embodiment of the display 1300 discussed above with respect to FIG. 13, and like reference numerals have been used to refer to the same or similar components. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0302] Users can also adjust their fall-asleep times (as shown in display 2702) and wakeup times (as shown in display 2704) based on a target desired bedtime window or actual sleep schedules using the user dashboard.

[0303] FIGS. 28A-28C illustrate exemplary displays 2800 showing active thermoregulation treatment delivery, according to some embodiments. The displays 2800 are similar in some respects to the embodiments of the displays 1400 discussed above with respect to FIGS. 14A-14C, and like reference numerals have been used to refer to the same or similar components. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.

[0304] The displays 2800 can include body visuals wherein a user can monitor sleep quality via a DPG slope, offering a visual representation of treatment outcomes and / or effectiveness. The visuals can indicate device placement, overall temperature changes, thermoregulation treatment settings, etc.

[0305] Displays 2802, 2804, and 2806 show thermoregulation treatment applied for faster sleep onset during the nighttime (indicated by the blue and deep blue background), cooling the core body temperature while warming the extremities, such as the hands. Display 2802 presents a circular diagram composed of two overlapping circles — one red indicating where warming will be applied, labeled 33.8°C as the current temperature, and one blue indicating where cooling will be applied, labeled 37.4°C as the current temperature — representing the contrast between core and peripheral temperatures, respectively, during thermo-activation at sleep onset (for example, around 10 PM). A button labeled “VIEWMWS Docket No. 114212-0338THERMO ACTIVITY” invites further interaction. Display 2804 transitions to a full-body silhouette with color-coded temperature zones: red highlights warmer regions (37.4°C), while blue indicates cooler zones (33.8°C). Icons of a flame and snowflake visually reinforce the warming and cooling processes occurring across the body via dual -thermoregulation devices. Display 2806 shows a refined thermal distribution: the core temperature is reduced to 37°C, while the extremities are warmed to 34°C as a result of cooling the core and warming of hands to support faster sleep onset.

[0306] Displays 2808, 2810, and 2812 show thermoregulation treatment applied during sleep for deeper sleep during the nighttime (indicated by the blue and deep blue background), cooling the core body temperature while warming the extremities. The information shown on displays 2808, 2810, and 2812 may indicate late-night thermal engagement (for example, around 1AM).

[0307] Displays 2814, 2816, and 2818 show thermoregulation treatment applied to aid natural wakening during the daytime (indicated by the orange background), warming the core body temperature while cooling the extremities to support natural wakening. Display 2814 presents a circular diagram composed of two overlapping circles — one blue indicating cooling the distal regions and one red indicating warming the proximal regions, during thermo-activation at sleep offset (for example, around 6AM). Display 2816 transitions to color-coded temperature zones: red highlights warmer regions (37°C), while blue indicates cooler zones (34°C). Icons of a flame and snowflake visually reinforce the warming and cooling processes occurring across the body via dual-thermoregulation devices. Display 2818 shows a refined thermal distribution: the proximal temperature is increased to 37.4°C, while the distal temperature is cooled to 33.8°C as a result of cooling the hands and warming the core to support natural sleep waking.

[0308] FIG. 29 illustrates an exemplary display 2900 showing a light exposure recommendation generated by the platform and provided through the user dashboard, according to some embodiments. The display 2900 is similar in some respects to the embodiment of display 1500 discussed above with respect to FIG. 15, and like reference numerals have been used to refer to the same or similar components. Any of the various features discussed with any one of the embodiments discussed herein may also apply to and be used with any other embodiments.MWS Docket No. 114212-0338

[0309] The light exposure recommendation may include a depiction of a large yellow sun icon, visually reinforcing the focus on light as a key circadian input. Beneath it, four icons represent related physiological and behavioral metrics, including cardiovascular indicators and time-based cues. The central portion of the screen features a segmented gauge chart tracking light exposure from 4 AM to 12 PM. The gauge indicates that 27% of the ideal light exposure by 10 AM is recommended, providing users with a visual benchmark for optimizing circadian alignment. The segmented design helps convey progress across the morning hours.PHYSICAL ACTIVITY MONITORING AND GUIDANCE

[0310] Some embodiments provide a platform for physical activity monitoring of a user. More specifically, some embodiments provide systems and methods for screening and assessment of the user’s fitness, by monitoring and tracking physiological metrics (including but not limited to thermal biomarkers) using combinations of wearable devices and data analytics, as well as using these metrics to provide personalized fitness-related recommendations. Some embodiments train artificial intelligence (Al) models using physiological data and use these trained Al models to provide data analytics and personalized fitness-related recommendations to the user.

[0311] Embodiments, as disclosed herein, provide a solution to the above-mentioned problems rooted in computer technology, namely, providing solutions for optimizing fitness performance and sleep.

[0312] A technical challenge addressed by some embodiments is generating user guidance from concurrently collected measurements at different body regions rather than from a single-location temperature signal or from generic activity tracking alone. Some embodiments address that challenge by using physiological data from devices affixed at proximal and distal body regions to derive a Distal Proximal Gradient (DPG) slope and, in some implementations, additional thermal biomarkers such as core body temperature and heat flux, and by generating guidance based on those derived values. This allows the computing system to determine time periods or conditions for sleep, training, rest, eating, or focus based on dual-location thermal behavior of the user.

[0313] Some embodiments may utilize measurements and determinations of various physiological metrics, including, but not limited to, skin temperature, core body temperature,MWS Docket No. 114212-0338movement, activity, oxygen saturation (SpCh), distal-proximal temperature gradient (DPG), heart rate and / or heart rate variability, respiratory rate and / or effort, light exposure, heat flux, electrodermal activity (EDA), galvanic skin response (GSR), other activity and / or movement, and the like. In some embodiments, physiological metrics are analyzed to provide guidance to a user for optimization of fitness activities and sleep.

[0314] FIG. 30 is a block diagram illustrating details of a system 3000 for physical activity monitoring and guidance, according to some embodiments. Specifically, the example of FIG. 30 illustrates an exemplary client device 110-3 (of the client devices 110) and an exemplary server 130-3 (of the servers 130) in the network architecture 100 of FIG. 1.

[0315] Client device 110-3 and server 130-3 are communicatively coupled over network 150 via respective communications modules 3002-1 and 3002-2 (hereinafter, collectively referred to as “communications modules 3002”). Communications modules 3002 are configured to interface with network 150 to send and receive information, such as requests, data, messages, commands, and the like, from and to other devices on the network 150. Communications modules 3002 can be, for example, modems or Ethernet cards, and / or may include radio hardware and software for wireless communications (e.g., via electromagnetic radiation, such as radiofrequency (RF), near field communications (NFC), Wi-Fi, and Bluetooth radio technology).

[0316] The client device 110-3 and server 130-3 also include processors 3005-1 and 3005-2, and memories 3020-1 and 3020-2, respectively. Processors 3005-1 and 3005-2 and memories 3020-1 and 3020-2 will be collectively referred to, hereinafter, as “processors 3005,” and “memories 3020,” respectively. Processors 3005 may be configured to execute instructions stored in memories 3020, to cause client device 110-3 and / or server 130-3 to perform methods and operations consistent with embodiments of the present disclosure.

[0317] The client device 110-3 and the server 130-3 may each be coupled to at least one input device 3030-1 and input device 3030-2, respectively (hereinafter, collectively referred to as “input devices 3030”). The input devices 3030 can include a mouse, a controller, a keyboard, a pointer, a stylus, a touchscreen, a microphone, voice recognition software, a joystick, a virtual joystick, a touch-screen display, awearable device (for example, a haptics glove, a bracelet, a ring, an earring, a pin, a necklace, a watch, etc.), and the like. In some embodiments, the input devices 3030 may include cameras, microphones, sensors, and theMWS Docket No. 114212-0338like. In some embodiments, the sensors may include touch sensors, acoustic sensors, inertial motion units (IMUs) and the like. In some embodiments, the input devices 3030 may include biometric input devices, such as fingerprint scanners, eye trackers, and the like.

[0318] The client device 110-3 and the server 130-3 may also be coupled to at least one output device 3032-1 and output device 3032-2, respectively (hereinafter, collectively referred to as “output devices 3032”). The output devices 3032 may include a screen, a display (e.g., a touchscreen display that also functions as an input device), a speaker, an alarm, a haptic feedback device, and the like. A user may interact with client device 110-3 and / or server 130-3 via the input devices 3030 and the output devices 3032.

[0319] Memory 3020-1 may further include an application 3042, configured to execute on client device 110-3 and couple with input device 3030-1 and output device 3032-1. The application 3042 may be downloaded by the user from server 130-3, and / or may be hosted by server 130-3. The application 3042 may include specific instructions which, when executed by processor 3005-1, cause operations to be performed consistent with embodiments of the present disclosure. In some embodiments, the application 3042 runs on an operating system (OS) installed in client device 110-3. In some embodiments, application 3042 may run within a web browser. In some embodiments, the processor 3005-1 is configured to control a graphical user interface (GUI) (e.g., spanning at least a portion of input devices 3030 and output devices 3032) for the user of client device 110-3 to access the server 130-3. Data and files associated with the application 3042 may be stored in and / or retrieved from one or more databases (e.g., database 152).

[0320] A technical challenge addressed by some embodiments is generating user guidance from concurrently collected physiological measurements at different body regions rather than from a single-location temperature signal or from generic activity tracking alone. Some embodiments address that challenge by using physiological data from devices affixed at proximal and distal body regions to derive a Distal Proximal Gradient (DPG) slope and, in some implementations, additional thermal biomarkers such as core body temperature and heat flux, and by generating guidance identifying recommended times, conditions, or actions for sleep and fitness activities based on those derived values.

[0321] In some embodiments, application 3042 provides a user interface that is displayed on a screen of client device 110-3 and allows users to input commands to control theMWS Docket No. 114212-0338operation of the application 3042, view outputs from application engine 3043 (described below), interact with other client devices 110, or the like. Application 3042 may enable users to track and view their physiological metrics measured using sensors or determined from measurements, and view guidance on fitness performance and sleep optimization. The application 3042 may be implemented as a web page, a collection of web pages, or other content designed to be displayed within an internet browser.

[0322] In some embodiments, memory 3020-2 includes an application engine 3043. The application engine 3043 may be configured to perform methods and operations consistent with embodiments of the present disclosure. The application engine 3043 may share or provide features and resources with the client device 110-3, including data, libraries, and / or applications retrieved with application engine 3043 (e.g., application 3042). The user may access the application engine 3043 through the application 3042. The application 3042 may be installed in client device 110-3 by the application engine 3043 and / or may execute scripts, routines, programs, applications, and the like provided by the application engine 3043.

[0323] Memory 3020-2 can include an application engine 3043 and trained model 3045. The application engine 3043 can share or provide features, resources, data, and information with application 3042 for presentation to the user. The user can access information from application engine 3043 through application 3042, installed in a memory 3020-1 of client device 110-3. Accordingly, application 3042 can be installed by server 130-3 and perform scripts and other routines provided by server 130-3 through any one of multiple tools. Server 130-3 can include an API layer 3050, which may control and / or configure the application 3042 in the client device 110-3.

[0324] According to some embodiments, application engine 3043 can include one or more sets of machine-readable instruction modules that, when executed by processors 3005, are configured to perform operations according to some embodiments described herein. For example, the application engine 3043 may be configured to receive physiological data of the user from client device 110-3 (or any combination of client devices 110) and process the data using trained model 3045, to provide guidance to the user regarding fitness performance and sleep optimization. The guidance may be provided to the user via output device 3032-1 of client device 110-3 and / or a user interface of application 3042.MWS Docket No. 114212-0338

[0325] The trained model 3045 can be configured to provide Al-driven fitness performance and sleep optimization recommendations tailored to each user profile. The trained model 3045 may be part of one or more machine learning models stored in database 152 and / or executing in memory 3020-2. In some embodiments, at least one or more training archives or machine learning models can be stored in either one or both of memories 3020. The database 152 may include training archives and other data files that can be used by application engine 3043 in the training of trained model 3045.

[0326] The trained model 3045 may include algorithms trained for the specific purposes of the application engine 3043. The algorithms may include machine learning or artificial intelligence algorithms making use of any linear or non-linear algorithm, such as a neural network algorithm, or multivariate regression algorithm. In some embodiments, the trained model 3045 can include an LLM, Natural Language Understanding (NLU) model, a neural network (NN), a convolutional neural network (CNN), a generative adversarial neural network (GAN), an unsupervised learning algorithm, a deep recurrent neural network (DRNN), a classic machine learning algorithm such as random forest, or any combination thereof. More generally, the machine learning model may include any machine learning model involving a training step and an optimization step. In some embodiments, the database 152 can include a training archive to modify coefficients according to a desired outcome of the trained model 3045. Accordingly, in some embodiments, application engine 3043 is configured to access the database 152 and / or data collected by one or more client devices 110 to retrieve data and archives as inputs for the machine learning model. In some embodiments, application engine 3043, the tools contained therein, and at least part of database 152 can be hosted in a different server that is accessible by server 130-3 or client device 110-3.

[0327] In some embodiments, the application engine 3043 forms an input feature set for the trained model 3045 from data received from the first device and the second device and, in some implementations, from one or more additional data sources. The input feature set may include one or more current or historical values associated with proximal skin temperature, distal skin temperature, Distal Proximal Gradient (DPG), DPG slope, core body temperature, heat flux, movement, activity, heart rate, respiratory rate, oxygen saturation, light exposure, electrodermal activity, galvanic skin response, user-entered goals, travel-related data, or any combination thereof. The input feature set may represent a current time window, a sequence of time windows, or both.MWS Docket No. 114212-0338

[0328] In some embodiments, database 152 stores a training archive including historical input feature sets and associated outcome data. The associated outcome data may include one or more labels, scores, or categories corresponding to sleep quality, sleep readiness, circadian phase alignment, heat-flow status, recommendation category, adherence outcome, activity timing outcome, or combinations thereof. The trained model 3045 may be trained using the training archive to map input feature sets to one or more output values, scores, or classifications used by the application engine 3043 to generate guidance for the user.

[0329] In some embodiments, during operation, the application engine 3043 applies the trained model 3045 to an input feature set to obtain one or more model outputs. The model outputs may include one or more scores, classifications, ranked options, Boolean indicators, or time-window indicators corresponding to sleep pressure, sleep readiness, sleep quality, heat-flow status, circadian phase alignment, a recommended time period for an activity, a predicted benefit of exertion, rest, cooling, hydration, refueling, or focus at a given time, or any combination thereof. The application engine 3043 may generate a recommendation based on the one or more model outputs alone or in combination with one or more rule-based operations.

[0330] In some embodiments, later measurements and / or user feedback may be used to validate a prior recommendation and update the training archive. For example, later-measured physiological data, subsequent sleep metrics, activity outcomes, or user inputs indicating adherence to or deviation from a recommendation may be stored as follow-on data associated with an earlier input feature set. The trained model 3045 may be periodically retrained or updated using the follow-on data so that subsequent recommendations are more closely aligned with the user’s longitudinal physiological patterns.

[0331] In some embodiments, the trained model 3045 outputs machine-readable data rather than a human-like decision. By way of example, the trained model 3045 may output a score, category, ranking, or Boolean indicator, and the application engine 3043 may generate a recommendation, alert, display element, or timing indication based on that output.Accordingly, the trained model 3045 can be used as one component of a processing pipeline that receives sensor data, computes one or more derived values, generates one or more model outputs, and causes user-facing guidance to be presented through the user device.MWS Docket No. 114212-0338

[0332] FIG. 31A and FIG. 3 IB illustrate components of a system 3100 for physical activity monitoring and guidance, according to some embodiments. In this example, the system 3100 includes a proximal sensor pod 3105 and a distal sensor pod 3110, each to measure one or more skin temperature, core body temperature, ambient temperature, electrodermal activity, movement, heart rate, SpO . or any combination thereof. The system 3100 also includes a charging dock 3115 that charges the proximal sensor pod 3105 and the distal sensor pod 3110, as well as measures light levels and ambient temperature. Each sensor pod may have charging contacts 3117a, 3117b on one surface to facilitate charging from the charging dock 3115. The proximal sensor pod 3105 and the distal sensor pod 3110 may each be configured with flexible patches 3120a, 3120b on one surface to enable them to directly attach to the user’s skin or clothing. The flexible patches 3120a, 3120b may be sweat-proof and / or waterproof with adhesive patches for long wear time (e.g., 14 days). In addition, system 3100 may include an application (e.g., application 3042) executing on a user device 3122 (e.g., client device 110-3) that provides a user interface (not shown) for configuring components of system 3100 and providing guidance to the user based on data collected by proximal sensor pod 3105, distal sensor pod 3110, charging dock 3115, or any combination thereof.

[0333] Though the components of system 3100 are shown in FIG. 31A and FIG. 3 IB as pods worn directly attached to the skin, system 3100 may alternatively or additionally include other types of components, devices (e.g., client devices 110), and / or wearable devices, including but not limited to a mattress topper, a ring, a smart watch, a toe-ring, an ankle band, an ankle patch, a body patch, smart garments, earrings, a headband, glasses, and the like. In addition, system 3100 may include remote servers (e.g., servers 130) in wireless communication with components of system 3100 (e.g., user device 3122, proximal sensor pod 3105, distal sensor pod 3110, and charging dock 3115), to receive data and measurements from components of system 3100, process and analyze that data to generate actionable guidance for the user, and provide the generated guidance to the user via the user interface on user device 3122.

[0334] In some embodiments, as shown in FIG. 31A and FIG. 3 IB, the proximal sensor pod 3105 and the distal sensor pod 3110 may be used to measure physiological signals from a central (proximal) system 3125 and a peripheral (distal) system 3130, respectively, of a user. For peripheral measurements, a distal component (e.g., distal sensor pod 3110) may beMWS Docket No. 114212-0338positioned on locations including, but not limited to, a wrist, arm, hand, fingers, feet, and / or legs of the user. For central system monitoring, suitable placement areas for a proximal component (e.g., proximal sensor pod 3105) may include, but are not limited to, a neck, chest, forehead, and / or abdomen of the user. As an example, the collected data from the proximal and distal locations may be used to determine distal-proximal skin temperature gradient (DPG). According to some embodiments, DPG may be used as a physiological marker to assess fitness and performance. In some embodiments, at least a third device (e.g., charging dock 3115) may be used to collect environmental data, including but not limited to ambient temperature and light level. The charging dock 3115 may include one or more environmental sensors, including an ambient temperature sensor, a light sensor, or both. Some embodiments may receive environmental data from the charging dock and may generate a recommendation at least partially based on the environmental data. In some implementations, the environmental data may be used to generate sleep-environment guidance, including lighting guidance or temperature guidance.

[0335] Some embodiments may measure thermal biomarkers based on measurements from the user’s core (head and torso) and limbs (arms and legs), using proximal and distal wearable devices worn at these locations, respectively. Heat patterns unique to each user may be used to determine when the user should rest, recover, and perform at peak during athletic activity, as well as assess sleep quality. Heat patterns may vary between regions, as a user’s core may generally stay relatively steady but rise under strain, whereas the limbs may act as radiators, warming to release heat or cooling to conserve it. Measurement of thermal biomarkers may capture heat shifts and changes in heat patterns from workout intensity, recovery state, and readiness for rest or sleep.

[0336] Various exemplary embodiments related to different use cases are now described. In these examples, core and limb thermal data may be collected from sensors in proximal and distal wearable devices, to calculate at least DPG and heat flux. In addition, activity may be measured or estimated using sensor data, including but not limited to heart rate, respiratory rate, motion from IMUs, or any combination thereof. In some embodiments, activity data may also be measured or validated using a light sensor in a third device (e.g., a charging dock).

[0337] Some embodiments may use measurements of physiological metrics to determine when the user is ready for peak performance, in terms of strength, power, endurance, and / orMWS Docket No. 114212-0338focus. Knowledge of these time windows may provide a “body clock” that helps the user train more effectively and recover more quickly. This may enable the user to train and recover in tune with their body. An exemplary body clock embodiment is shown in FIG. 32A and FIG. 32B, which will be described in more detail below.

[0338] Inputs may include, but are not limited to, distal-proximal temperature gradient (DPG), heat flux, and activity. Activity may serve as a proxy for light exposure, with the assumption that when a user is sleeping, the environment may be dark; this may be confirmed via a light sensor in the charging dock.

[0339] Outputs may include, but are not limited to, an R2correlation number that may indicate rhythm strength. A value close to 1 may reflect a strong circadian rhythm, while a value close to 0 may suggest that the rhythm is not clear and may indicate sleep disorders.

[0340] Outputs may further include a cosinor graph to visually represent the user’s circadian rhythm by plotting physiological data over a 24-hour period to show the natural highs and lows of the body’s readiness or activity levels. Time stamps from the cosinor curve (hh:mm) may refer to specific points in time, recorded in hours and minutes, that correspond to key phases of the user’s circadian rhythm as visualized by the cosinor graph. These time stamps may indicate when physiological peaks and troughs occur, such as periods of highest alertness, optimal physical performance, or readiness for sleep. Additional time points from the cosinor curve may include, but are not limited to:

[0341] Dim Light Melatonin Onset (DLMO): the time at which melatonin production begins to rise in response to decreasing light levels. This output may be used as a marker for the start of the biological night and may help determine the optimal timing for sleep onset.

[0342] Peak rest: the highest point on the cosinor curve, which may represent the nadir of core body temperature (CBT). This point, plus some offset number of hours, may align with peak levels of cortisol, strength, and / or endurance. Identifying peak rest windows may help the user optimize recovery and schedule periods of intense physical activity for times when the body is most prepared.

[0343] Core body temperature minimum: the period during which the user’s core body temperature reaches its minimum, which may coincide with the deepest stage of sleep.MWS Docket No. 114212-0338Tracking this output may provide insights into sleep quality and recovery, as well as help identify the most restorative phases of the sleep cycle.

[0344] Other time points may also be shown or displayed, including but not limited to peak endurance, peak strength, and the like.

[0345] Some embodiments may present personalized peak windows as time ranges, such as “Your focus peak: 10: 15 am-11:45 am.” These ranges may be calculated based on physiological metrics and circadian rhythm analysis. For example, a focus or alertness window (e.g., 9:30 am-11 :30 am) may be displayed as “Mind sharpest — best time for deep work,” while a coordination window (e.g., 2:30 pm-4:30 pm) may be shown as “Ideal time for skills or technique work.” Strength or power windows (e.g., 4:00 pm-6:00 pm) may be indicated as “Muscles primed — best window for heavy lifts or sprints,” and endurance windows (e.g., 5:00 pm-7:00 pm) may be presented as “Energy systems steady — best time for longer training.” Refueling windows (e.g., 6:30 pm-8:00 pm) may be displayed as “Body ready to refuel — meals now restore energy faster,” and sleep and recovery windows may be shown as “Body signaling rest — best chance for deep, restorative sleep.” These windows may help users optimize their daily activities and training schedules by aligning with their natural physiological peaks.

[0346] Some embodiments may provide a rhythm strength indicator that is easy for the user to interpret at a glance. Rhythm strength may be categorized as strong (e.g., 0.7-1.0), moderate (e.g., 0.4-0.69), or weak (e.g., 0-0.39). For a strong rhythm, the interface may display "Your body clock is strong and consistent — sleep, energy, and performance align well.” For a moderate rhythm, the message may be “Moderate rhythm — more regular sleep, meal, and light timings can strengthen your body clock.” For a weak rhythm, the interface may indicate "Your rhythm is weak — irregular sleep, meals, or light may be disrupting recovery, focus, and energy.” This categorization and corresponding suggestion may help users quickly understand the alignment of their circadian rhythm and identify areas for improvement as well as relevant optimal action to take.

[0347] Some embodiments may include a cosinor graph in the user interface, presented as a wave diagram showing “highs and lows” across the day, with the user’s current time marked. The graph may be labeled as "Your 24-hour body clock,” with the y-axis representing qualitative readiness (such as “higher readiness” or “lower readiness”) and the x-MWS Docket No. 114212-0338axis representing time. Key peak windows, such as focus, strength, and sleep, may be tagged with icons for quick reference. Tooltip text associated with these icons may explain, “This curve shows your daily rhythm — when your body naturally peaks and when it’s primed for rest.” This visualization may help users intuitively understand their daily physiological cycles and make informed decisions about activity timing.

[0348] The user interface for some embodiments may be designed to lead with the benefit, such as displaying “Mind sharpest now — focus on deep work.” Numerical values, like rhythm strength, may be hidden by default and shown only as qualitative indicators, for example, “Strong,” with the option to view detailed metrics in an expanded view for advanced users. Traffic-light coding (red, green, yellow) and / or icons may be used throughout the interface to enable instant recognition of status or recommendations.Additionally, micro-actions may be provided under each physiological window or status, such as “Tackle your hardest task” during peak focus, “Wind down now for deeper rest” during the sleep window, and “Stick to consistent bed / wake times” when rhythm strength is weak.

[0349] FIGS. 32A-32B illustrate an exemplary user interface 3200 for a physiological monitoring and circadian alignment system, according to some embodiments. The user interface 3200 includes a body clock interface 3205, which is a circular, clock-based visualization representing a 24-hour circadian cycle of a user. Distinct time windows, represented as colored arcs, icons, and the like, corresponding to different functional states are displayed around the circumference, including periods associated with cognitive focus, coordination, strength, endurance, refueling, and sleep or rest / recovery. The body clock interface 3205 further presents numerical indicators 3207 or graphical indicators (e.g., a cosinor graph 3208) of circadian rhythm strength, peak alertness timing, and phase alignment. In some embodiments, selectable controls 3210 allow initiation of a time-shift or circadian adjustment mode.

[0350] The exemplary user interface 3200 also includes a time-zone transition interface 3215, illustrating the gradual shifting of the user’s body clock in response to travel across time zones. The time-zone transition interface 3215 displays a sequence of daily schedules before, during, and after travel, with visual indicators (e.g., indicators 3217) representing recommended timing of sleep, light exposure, activity, and rest relative to both the origin andMWS Docket No. 114212-0338destination time zones. A vertical timeline view 3220 illustrates progressive circadian phase adjustments over multiple days until alignment with the destination time zone is achieved.

[0351] Together, the above-described interfaces provide a visualization to the user of their circadian state and provide guidance for adapting physiological rhythms to changes in environmental time cues, including but not limited to long-distance travel.

[0352] Some embodiments track the user’s heat flow during physical activity, to determine when the user should make more exertion (“push”), adjust pacing, and proactively use hydration or cooling before performance drops. This advanced heat flow tracking enables the user to track how efficiently they cool down after workouts, for example. An exemplary heat flow / cooling efficiency embodiment is shown in FIG. 33A and FIG. 33B which will be described in more detail below.

[0353] Inputs may include, but are not limited to, heat flux, heart rate, distal-proximal temperature gradient (DPG), ambient temperature, electrodermal activity (EDA), activity level, or any combination thereof. These physiological and environmental metrics may be collected during exercise and post-exercise periods to assess the body’s ability to release heat and maintain optimal performance.

[0354] Outputs may include heat flow and cooling efficiency, which may be expressed as a percentage or categorized (e.g., as high, medium, or low). The results may be further organized into a number of cooling capacity zones, e.g., Zones 1 through 4.

[0355] The user interface for these embodiments may present cooling capacity in a clear and actionable manner. Zone 1 may indicate high cooling capacity, with a message “Cooling capacity high — body releasing heat easily, ready to perform and recover.” Zone 2 may reflect moderate capacity, with a message “Cooling capacity steady — body managing heat but working harder.” Zone 3 may signal low capacity, with a message “Cooling capacity low — heat building up, recovery or performance may drop,” and may prompt actions such as slowing down, hydrating, or cooling the user’s environment (“Body working harder to cool -pace yourself, stay hydrated).” Zone 4 may represent capacity maximum, with a message “Cooling capacity maxed — body struggling to shed heat, risk of overheating,” and may recommend stopping exertion, cooling down, and resting.MWS Docket No. 114212-0338

[0356] In addition, the user interface may use color coding and / or visual icons. Color coding may be traffic-light coding, e.g., green to proceed, yellow to slow down, and red to stop. A dashboard tile may be used to provide a concise summary or one-liner message, such as “Cooling high - you’re in the clear” for Zone 1, “Cooling steady - holding fine” for Zone 2, “Cooling low - ease up” for Zone 3, and “Cooling maxed - slow down” for Zone 4. An expanded view may offer longer explanations and recommended actions tailored to the user’s current cooling capacity.

[0357] FIGS. 33A-33B illustrate an exemplary user interface 3300 for assessing thermal regulation and cooling efficiency of a user, in real time and / or over summary periods, according to some embodiments. The user interface 3300 includes a cooling efficiency interface 3305, that may be configured as a real-time monitoring mode 3305a or a daily summary mode 3305b, selectable by the user by a mode toggle control 3306. When the cooling efficiency interface 3305 is configured for the real-time monitoring mode 3305a, the cooling efficiency interface 3305 may display a central indicator 3307 representing a realtime assessment of a cooling efficiency state of the user, in this example categorized into qualitative levels such as high (left), moderate (middle), or low (right). The cooling efficiency interface 3305 may include contextual guidance corresponding to the detected state. Below the central indicator 3307, a time-series histogram 3309 or equivalent bar chart illustrates real-time changes in cooling efficiency and / or related thermal metrics over a recent time window.

[0358] The cooling efficiency interface 3305 further presents multiple physiological and environmental parameters 3311 associated with heat dissipation and thermoregulation, including but not limited to one or more of heat flux or heat flow measurements, heart rate or cardiac -derived metrics, electrodermal activity (EDA), peripheral or core body temperature, ambient temperature, and activity classification (e.g., workout or non-workout state).

[0359] When the cooling efficiency interface 3305 is configured for the daily summary mode 3305b, the cooling efficiency interface 3305 may aggregate cooling efficiency states and related metrics across different activities or time periods within a day and may present comparative visualizations indicating relative durations or intensities of high, moderate, and low cooling efficiency states. The cooling efficiency interface 3305 may visualize heat flow dynamics, integrate multiple physiological signals, and provide interpretable feedbackMWS Docket No. 114212-0338regarding the user’s thermal regulation and cooling performance during physical activity and daily life.

[0360] Some embodiments provide tracking of advanced sleep metrics by measuring thermal patterns and sleep heat flow throughout the sleep period, to assess how well the sleep and rest supports recovery, muscle repair, and next-day performance. An exemplary sleep quality embodiment is shown in FIGS. 34A-34D, which are described in more detail below.

[0361] Inputs may include, but are not limited to, activity level, distal-proximal temperature gradient (DPG), heat flux, heart rate, light exposure (optionally, measured from a dock), or any combination thereof.

[0362] Outputs may include, but are not limited to, sleep onset and offset times recorded as clock time (hh:mm), sleep duration measured in minutes or hours, sleep bank or debt calculated in hours on a rolling basis, and sleep regularity categorized as good (within ±30 minutes), moderate (within ±1 hour), or low (within ±1.5 hours). Additional outputs may include the number and duration of wake after sleep onset (WASO) events, and heat flow, expressed as a percentage or qualitatively categorized (e.g., optimal / sub-optimal).

[0363] The user interface for these embodiments may visualize sleep time and duration, including start time, end time, and the number of wakes during sleep. Sleep bank or debt may be displayed on a dashboard, for example, as “Sleep debt: Ih 30m” or “Sleep banked: ±45m,” with thresholds for balanced (within ±30 min), mild debt (0.5-1.5 h), and high debt (>1.5 h), and action phrasing such as “Catch up tonight with an earlier bedtime.” Sleep regularity may be presented to the user on the dashboard or as messages, with sample messages like “Consistent bed and wake times — strong body clock support” for good regularity, “Some variation in bed and wake times — rhythm still steady” for moderate regularity, and “Irregular bed and wake times — this weakens your circadian rhythm and makes it harder for your body clock to stay aligned” for low regularity. Heat flow may be communicated to the user via the interface using messages such as “Good heat flow — supportive of deep sleep” when optimal, or “Heat flow sub-optimal — may make sleep less restful,” with suggested actions such as “Try a cooler room or lighter bedding” when sub-optimal.

[0364] In addition to providing sleep quality, some embodiments may also provide environmental monitoring. An exemplary environmental sleep tracking embodiment is discussed below.MWS Docket No. 114212-0338

[0365] Inputs may include, but are not limited to, the level of light in the bedroom, (e.g., measured in melanopic lux), the ambient temperature (e.g., measured in degrees Fahrenheit or Celsius), or any combination thereof.

[0366] Outputs may include, but are not limited to, a categorization of the level of darkness and temperature upon which actionable feedback on the sleep environment can be provided to the user.

[0367] The user interface may present light levels to the users via informative messages on a dashboard, such as: “Room is dark, ideal for sleep — stay as is” for dark (ideal) conditions; “Some light detected, which may delay sleep — dim the lights further” for dim (borderline) conditions; and “Light is too bright and can suppress sleep hormones — switch off lamps or close curtains” for bright (disruptive to sleep) conditions. Temperature feedback may be provided as well, using messages such as “Room is colder than ideal and may delay sleep onset — add a blanket or adjust thermostat” for cold conditions (e.g., below 17° C); “Room is in the optimal sleep range — no changes needed” for cool and ideal conditions (e.g., 18-21° C); “Room is warmer than ideal and may cause restlessness — cool the room or use lighter bedding” for warm conditions (e.g., 22-25° C); and “Room is too hot and may fragment sleep — lower thermostat or use a fan” for hot conditions (e.g., above 25° C). The interface may use a simple traffic-light system, with green indicating ideal conditions, amber indicating borderline conditions, and red indicating disruptive conditions. Overtime, the system may personalize recommendations by adapting ranges if data shows the user sleeps well in warmer, cooler, or brighter conditions.

[0368] FIGS. 34A-34D illustrate an exemplary user interface 3400 for presenting sleep metrics of a user, in real time and / or over various summary periods, according to some embodiments. The user interface 3400 may integrate multimodal physiological and environmental data to characterize sleep quality, sleep stability, heat flow during sleep, sleep position, blood oxygen during sleep, bedroom light levels, and bedroom temperature, and may provide detailed feedback regarding sleep behavior and sleep-related physiological regulation.

[0369] In some embodiments, the user interface 3400 includes a total sleep time visualization 3405, a temperature visualization 3407, a light level visualization 3409, a blood oxygen visualization 3411, a sleep-consistency visualization 3413, a heat-flow visualizationMWS Docket No. 114212-03383415, a sleep-bank or sleep-debt visualization 3417, and a sleep-position visualization 3419. Summary weekly views 3430 and monthly views 3440 may include aggregated versions of one or more of these metrics and associated summary text (e.g., qualitative assessments 3450).

[0370] The user interface 3400 may be configured to present advanced sleep-related metrics derived from one or more sensors during a sleep period. In this example, the user interface 3400 presents summaries of total sleep time, sleep timing, and sleep consistency across one or more nights. Circular visualizations (e.g., temperature visualization 3407), barbased visualization (e.g., light level visualization 3409), or time-series visualizations (e.g., blood oxygen visualization 3411) may be used to represent various sleep metrics, variability, and deviations from baseline or target values.

[0371] The user interface 3400 may display multiple physiological and behavioral sleep metrics, including one or more of: sleep continuity and fragmentation indicators (e.g., sleepconsistency visualization 3413), spatial or regional heat flow or thermal distribution during sleep (e.g., heat-flow visualization 3415), heart rate or cardiac-derived sleep metrics, sleep posture or body position distributions overtime (e.g., sleep-position visualization 3419), blood oxygen saturation (SpOz) measurements and trends (e.g., blood oxygen visualization 3411), ambient and user-experienced light exposure during sleep periods (e.g., light level visualization 3409), and skin, peripheral, or core body temperature measurements and variability (e.g., temperature visualization 3407).

[0372] The user interface 3400 may present longitudinal views showing nightly variability and trends across multiple days (e.g., weekly view 3430, monthly view 3440), and / or detailed views for a single sleep session. Qualitative assessments 3450 (e.g., good, moderate, or high deviation) may be displayed alongside quantitative metrics to assist interpretation.

[0373] Some embodiments provide performance tracking by converting the user’s body heat signature into peak power, average power, and energy use, providing a quantitative assessment of training load and efficiency. In addition, some embodiments may enable tracking of muscle bilateral balance, when wearable devices are both placed at left and right distal locations (e.g., on the left and right biceps). Bilateral muscle output may be tracked accordingly, to determine how the muscles are working, determine limits, and detectMWS Docket No. 114212-0338imbalances, so that the user may correct asymmetries, refine technique, and train more effectively. An exemplary performance tracking and muscle balance embodiment is shown in FIGS. 35A-35C, which are described in more detail below.

[0374] As used herein, a “bilateral muscle balance metric” refers to a quantitative measure of the difference in power output or activity level between a left-side muscle and a right-side muscle, as determined by sensors affixed to each muscle. This metric may be calculated as the absolute or relative difference in measured power or activity between the two sides.

[0375] Inputs may include, but are not limited to, heat flux, height, weight, heart rate, muscle group size (assuming standard size), or any combination thereof. For total power and average power calculations, heat flux, height, weight, and heart rate may be used as inputs. For local or muscle-specific power, heat flux, height, weight, and muscle group size may be used as inputs. The calculation of calories burned may be based on heat flux, heart rate, height, and weight. It may be assumed that some fraction (e.g., 80%) of power is lost as heat.

[0376] Outputs may include, but are not limited to, metabolic power output for muscle building and calories burned. Units for these outputs may include watts (W), watts per kilogram (W / kg) for total and average power, watts (W) for muscle-specific power, and kilocalories (kcal) for calories burned.

[0377] The user interface may display total power and / or peak power in watts and watts per kilogram, average power in watts and watts per kilogram, power for the left muscle in watts, power for the right muscle in watts, and calories burned in kilocalories. These options may provide users with clear, actionable feedback on their performance and muscle balance.

[0378] FIGS. 35A-35C illustrate an exemplary user interface 3500 for assessing physical performance metrics and bilateral muscle activity during exercise or daily activity, according to some embodiments. The user interface 3500 integrates multiple physiological signals to quantify performance, track energy expenditure, and assess bilateral muscle balance during physical activity.

[0379] User interface 3500 includes a performance tracking interface 3502 to present real-time views 3505 of metabolic and physiological performance metrics. The user interface 3500 displays an estimate of metabolic power output 3507 over a defined time period, alongMWS Docket No. 114212-0338with one or more trend graphs 3509 illustrating temporal changes in power output, heart rate, and blood oxygen saturation (SpCh). Additional summary metrics 3511 may include average and maximum power, average and maximum heart rate, minimum SpCh. and accumulated or average caloric expenditure.

[0380] The performance tracking interface 3502 may further present summary views 3513 that include real-time time-series visualizations showing the evolution of performance-related parameters during an activity session, such as strength training, and cumulative graphs representing total calories burned over time and power output.

[0381] In some embodiments, the user interface 3500 includes a bilateral muscle balance interface 3520. The bilateral muscle balance interface 3520 presents comparative metrics representing power output or activity levels associated with left-side and right-side muscle groups. Bilateral comparisons may be displayed as instantaneous values 3522, time-series plots 3524, or summary statistics indicating asymmetries or imbalances in generated power output 3526 or temperature 3528 between opposing muscle groups.

[0382] The user interface 3500 may support selectable modes, including a real-time monitoring mode and an activity summary mode, allowing the user to switch between live data visualization and post-activity analysis.

[0383] The original applicant acknowledges that the selection and development of technologies in the dynamic field of artificial intelligence are determined based on their utility and relevance for both the applicant and its users. Consequently, it is possible that the systems and methods detailed in this document may not have been, or may not be in the future, employed or developed by the original applicant in the realm of artificial intelligence. Additionally, any implementation or utilization of these systems and methods by the original applicant adheres to its privacy policies, which are designed to uphold and prioritize user privacy in the context of artificial intelligence, aiming to meet or exceed relevant government and legal requirements.

[0384] In cases where the implementation or use of these systems and methods involves the processing of user personal information within the artificial intelligence, such processing occurs in accordance with the privacy policies, under a valid legal mechanism, and respecting user privacy settings or preferences. The original applicant also expresses its intention for these systems and methods, if adopted by other entities in the field of artificial intelligence, toMWS Docket No. 114212-0338comply with privacy policies and practices aligned with the objective of respecting user privacy within the artificial intelligence domain.

[0385] FIG. 36 is a flowchart illustrating a process 3600 for physical activity monitoring and guidance performed by one or more processors of a computing system. In some embodiments, one or more operations in process 3600 are performed by one or more processors (e.g., processors 3005, etc.) executing instructions stored in one or more memory devices (e.g., memories 3020, etc.) of a system (e.g., system 3100, etc.) as disclosed herein. For example, one or more operations of process 3600 may be performed by various software modules, including but not limited to application 3042, application engine 3043, trained model 3045, or some combination thereof. Moreover, in some embodiments, a process consistent with this disclosure may include at least operations in process 3600 performed in a different order, simultaneously, quasi-simultaneously, or overlapping in time.

[0386] At 3610, the process 3600 receives physiological data from a first device affixed to a first region of a user and from a second device affixed to a second region of a user, while the user is engaged in a physical activity. In some embodiments, the first region is a proximal region of the user’s body, and the second region is a distal region of the user’s body. In some embodiments, the proximal region is a core region of the user’s body, and the distal region is a limb region of the user’s body.

[0387] In other embodiments directed to bilateral performance monitoring, rather than proximal / distal placement, the first device may be affixed to a left-side muscle, and the second device may be affixed to a right-side muscle corresponding to the left-side muscle. The process may calculate a bilateral muscle balance metric representing a difference, ratio, or other comparison of power output or activity levels associated with the left-side muscle and the right-side muscle and may generate a recommendation based on the bilateral muscle balance metric.

[0388] In some embodiments, the physiological data includes skin temperature. The physiological data may include one or more of movement, activity, oxygen saturation (SpCh), heart rate, respiratory rate, light exposure, electrodermal activity (EDA), and galvanic skin response (GSR). In some embodiments, the process 3600 further receives activity data from at least one of the first device and the second device. Activity data may include, but is not limited to, heart rate, respiratory rate, and user motion.MWS Docket No. 114212-0338

[0389] At 3620, the process 3600 calculates a Distal Proximal Gradient (DPG) slope based on the received physiological data. In some embodiments, the process 3600 further calculates additional thermal biomarkers associated with the user, the additional thermal biomarkers including, but not limited to, core body temperature and / or heat flux.

[0390] At 3630, the process 3600 generates a recommendation for the user based on at least the DPG slope. Generating the recommendation may be further based on additional thermal biomarkers calculated by the process 3600. In some embodiments, the recommendation identifies at least one recommended time period, condition, action, or adjustment associated with a physical activity of the user. In addition, generating the recommendation may, for example, be further based on activity data.

[0391] In some embodiments, the physical activity is a sleep activity, and the recommendation identifies one or more of a sleep-debt condition, a sleep-regularity condition, a heat-flow condition during sleep, a bedroom temperature condition, or a bedroom lighting condition.

[0392] In some embodiments, the physical activity is a fitness activity, and the recommendation identifies at least one time period during a day to perform the fitness activity, wherein the fitness activity comprises one of a training activity, or a rest or recovery activity.

[0393] In some embodiments, the fitness activity is a training activity, and the recommendation includes real-time, quantitative measurements of power and energy during the training activity. The recommendation may further include determining in real time one or more optimum times for additional exertion during the training activity, resting during the training activity, cooling during the training activity, and / or hydrating during the training activity.

[0394] In some embodiments, the physical activity is an eating activity, and the recommendation includes determining an optimum time period to perform the eating activity.

[0395] In some embodiments, the physical activity is a focus activity, and the recommendation includes determining an optimum time period to perform the focus activity.MWS Docket No. 114212-0338

[0396] In some embodiments, the recommendation includes a circadian phase alignment indication or a body-clock time window associated with one or more of cognitive focus, coordination, strength, endurance, refueling, sleep, or rest or recovery.

[0397] In some embodiments, the recommendation includes a heat-flow condition or a cooling-efficiency state associated with the fitness activity.

[0398] In some embodiments, the recommendation further includes caloric expenditure associated with the training activity.

[0399] At 3640, the process 3600 causes presentation of the recommendation in a user interface on a user device operated by the user.Hardware Overview

[0400] FIG. 37 is a block diagram illustrating an exemplary computer system 3700 (equivalently referred to as a computing system) with which aspects of the subject technology can be implemented. In certain aspects, the computer system 3700 may be implemented using hardware or a combination of software and hardware, either in a dedicated server, integrated into another entity, or distributed across multiple entities. As a non-limiting example, the computer system 3700 may be one or more of the servers 130 and / or the client devices 110.

[0401] Computer system 3700 includes a bus 3708 or other communication mechanism for communicating information, and at least one of processor 3702 coupled with bus 3708 for processing information. By way of example, the computer system 3700 may be implemented with one or more processors 3702. Processor 3702 may be a general-purpose microprocessor, a microcontroller, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a state machine, gated logic, discrete hardware components, or any other suitable entity that can perform calculations or other manipulations of information.

[0402] Computer system 3700 can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them stored in an included memory 3704, such as a Random Access Memory (RAM), a flash memory, a Read-Only Memory (ROM), a ProgrammableMWS Docket No. 114212-0338Read-Only Memory (PROM), an Erasable PROM (EPROM), registers, a hard disk, a removable disk, a CD-ROM, a DVD, or any other suitable storage device, coupled to bus 3708 for storing information and instructions to be executed by processor 3702. The processor 3702 and the memory 3704 can be supplemented by, or incorporated in, special purpose logic circuitry.

[0403] The instructions may be stored in the memory 3704 and implemented in one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer-readable medium for execution by, or to control the operation of, the computer system 3700, and according to any method well-known to those of skill in the art, including, but not limited to, computer languages such as data-oriented languages (e.g., SQL, dBase), system languages (e.g., C, Objective-C, C++, Assembly), architectural languages (e.g., Java, .NET), and application languages (e.g., PHP, Ruby, Perl, Python). Instructions may also be implemented in other computer languages including, but not limited to, array languages, aspect-oriented languages, assembly languages, authoring languages, command line interface languages, compiled languages, concurrent languages, curly-bracket languages, dataflow languages, data-structured languages, declarative languages, esoteric languages, extension languages, fourth-generation languages, functional languages, interactive mode languages, interpreted languages, iterative languages, list-based languages, little languages, logic-based languages, machine languages, macro languages, metaprogramming languages, multiparadigm languages, numerical analysis, non-English-based languages, object-oriented class-based languages, object-oriented prototype-based languages, off-side rule languages, procedural languages, reflective languages, rule-based languages, scripting languages, stack-based languages, synchronous languages, syntax handling languages, visual languages, Wirth languages, and xml -based languages. Memory 3704 may also be used for storing temporary variable or other intermediate information during execution of instructions to be executed by processor 3702.

[0404] A computer program as discussed herein does not necessarily correspond to a fde in a fde system. A program can be stored in a portion of a fde that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single fde dedicated to the program in question, or in multiple coordinated fdes (e.g., fdes that store one or more modules, subprograms, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site orMWS Docket No. 114212-0338distributed across multiple sites and interconnected by a communication network. The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output.

[0405] Computer system 3700 further includes a data storage 3706 such as a magnetic disk or optical disk, coupled to bus 3708 for storing information and instructions. Computer system 3700 may be coupled via input / output module 3710 to various devices. The input / output module 3710 can be any input / output module. Exemplary input / output modules 3710 include data ports such as USB ports. The input / output module 3710 is configured to connect to a communications module 3712. Exemplary communications modules 3712 include networking interface cards, such as Ethernet cards and modems. In certain aspects, the input / output module 3710 is configured to connect to a plurality of devices, such as an input device 3714 and / or an output device 3716. Exemplary input devices 3714 include a keyboard and a pointing device, e.g., a mouse or a trackball, by which a user can provide input to the computer system 3700. Other kinds of input devices 3714 can be used to provide for interaction with a user as well, such as a tactile input device, visual input device, audio input device, or brain-computer interface device. For example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback, and input from the user can be received in any form, including acoustic, speech, tactile, or brain wave input. Exemplary output devices 3716 include display devices such as an LCD (liquid crystal display) monitor, for displaying information to the user.

[0406] Embodiments of the present disclosure, including but not limited to the system 3100, may be at least partially implemented using a computer system 3700 in response to one or more of processor 3702 executing one or more sequences of one or more instructions contained in memory 3704. Such instructions may be read into memory 3704 from another machine -readable medium, such as data storage 3706. Execution of the sequences of instructions contained in the memory 3704 causes processor 3702 to perform the process steps described herein. One or more processors in a multi-processing arrangement may also be employed to execute the sequences of instructions contained in memory 3704. In alternative aspects, hard-wired circuitry may be used in place of or in combination with software instructions to implement various aspects of the present disclosure. Thus, aspects ofMWS Docket No. 114212-0338the present disclosure are not limited to any specific combination of hardware circuitry and software.

[0407] Various aspects of the subject matter described in this specification can be implemented in a computing system that includes a back end component, e.g., such as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the subject matter described in this specification, or any combination of one or more such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. The communication network can include, for example, any one or more of a LAN, a WAN, the Internet, and the like. Further, the communication network can include, but is not limited to, for example, any one or more of the following network topologies, including a bus network, a star network, a ring network, a mesh network, a star-bus network, tree or hierarchical network, or the like. The communications modules can be, for example, modems or Ethernet cards.

[0408] Computer system 3700 can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. Computer system 3700 can be, for example, and without limitation, a desktop computer, laptop computer, or tablet computer. Computer system 3700 can also be embedded in another device, for example, and without limitation, a mobile telephone, a PDA, a mobile audio player, a Global Positioning System (GPS) receiver, a video game console, and / or a television settop box.

[0409] As used herein, the terms “machine-readable storage medium,” “computer-readable storage medium,” and “computer-readable medium” refer to any non-transitory, tangible storage medium that stores instructions or data for access by processor 3702.Examples of such non-transitory, tangible storage media include magnetic or optical disks, such as data storage 3706, as well as ROM, PROM, EPROM, EEPROM, flash memory, and other non-transitory, tangible storage media from which a computer can read instructions or data. In some examples, instructions stored on such a medium may be read into memory 3704 for execution by processor 3702. These terms expressly exclude transitory propagatingMWS Docket No. 114212-0338signals, carrier waves, and other non-tangible transmission media, including signals communicated via bus 3708 or other communication pathways.

[0410] As the computer system 3700 reads application data and provides an application, information may be read from the application data and stored in a memory device, such as the memory 3704. Additionally, data from the memory 3704 servers accessed via a network, the bus 3708, or the data storage 3706 may be read and loaded into the memory 3704. Although data is described as being found in the memory 3704, it will be understood that data does not have to be stored in the memory 3704 and may be stored in other memory accessible to the processor 3702 or distributed among several media, such as the data storage 3706.

[0411] Many of the above-described features and applications may be implemented as software processes that are specified as a set of instructions recorded on a computer-readable storage medium, as that term is used herein, which may also be referred to as computer-readable media, machine -readable media, or machine-readable storage media. When executed by one or more processing units, the instructions cause the executing processor(s) to perform the actions indicated in the instructions. Examples of computer-readable storage media include optical discs, magnetic disks, flash memory, ROM, PROM, EPROM, EEPROM, solid-state drives, magnetic drives, and other non-transitory tangible storage media, from which a computer can read instructions or data. Computer-readable storage media do not include carrier waves, propagated signals, or other transitory transmission media, including electronic signals transmitted wirelessly or over wired connections.

[0412] In one or more embodiments, a computer program product (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a standalone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.MWS Docket No. 114212-0338

[0413] While the above discussion primarily refers to microprocessor or multi -core processors that execute software, one or more embodiments are performed by one or more integrated circuits, such as application specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs). In one or more embodiments, such integrated circuits execute instructions that are stored on the circuit itself.Other Remarks

[0414] A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by any one of the patent document or the patent disclosure, as it appears in Patent Office patent files or records, but otherwise reserves all copyright rights whatsoever.

[0415] The original applicant acknowledges that the selection and development of technologies in the dynamic field of artificial intelligence are determined based on their utility and relevance for both the applicant and its users. Consequently, it is possible that the systems and methods detailed in this document may not have been, or may not be in the future, employed or developed by the original applicant in the realm of artificial intelligence. Additionally, any implementation or utilization of these systems and methods by the original applicant adheres to its privacy policies, which are designed to uphold and prioritize patient privacy in the context of artificial intelligence, aiming to meet or exceed relevant government and legal requirements.

[0416] In cases where the implementation or use of these systems and methods involves the processing of patient personal information within the artificial intelligence, such processing occurs in accordance with the privacy policies, under a valid legal mechanism, and respecting patient privacy settings or preferences. The original applicant also expresses its intention for these systems and methods, if adopted by other entities in the field of artificial intelligence, to comply with privacy policies and practices aligned with the objective of respecting patient privacy within the artificial intelligence domain.

[0417] While this specification contains many specifics, these should not be construed as limitations on the scope of what may be claimed, but rather as descriptions of particular implementations of the subject matter. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a singleMWS Docket No. 114212-0338embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0418] Unless the context clearly dictates otherwise and where a range of values is provided, it is understood that each intervening value between the upper and lower limit of that range, and any other stated or intervening value in that stated range is encompassed within the technology. The upper and lower limits of these intervening ranges, which can be independently included in the intervening ranges, are also encompassed within the technology, subject to any specifically excluded limit in the stated range. Where the stated range includes one or both of the limits, ranges excluding either or both of those included limits are also included in the technology.

[0419] Furthermore, where a value or values are stated herein as being implemented as part of the technology, it is understood that such values can be approximated, unless otherwise stated, and such values can be utilized to any suitable significant digit to the extent that a practical technical implementation can permit or require it.

[0420] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this technology belongs. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present technology, a limited number of the exemplary methods and materials are described herein.

[0421] The subject headings used in the detailed description are included only for the ease of reference of the reader and should not be used to limit the subject matter found throughout the disclosure or the claims. The subject headings should not be used in construing the scope of the claims or the claim limitations.

[0422] Those of skill in the art would appreciate that the various illustrative blocks, modules, elements, components, methods, and algorithms described herein may be implemented as electronic hardware, computer software, or combinations of both. To illustrate this interchangeability of hardware and software, various illustrative blocks, modules, elements, components, methods, and algorithms have been described aboveMWS Docket No. 114212-0338generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. Various components and blocks may be arranged differently (e.g., arranged in a different order, or partitioned in a different way), all without departing from the scope of the subject technology.

[0423] It is understood that any specific order or hierarchy of blocks in the processes disclosed is an illustration of example approaches. Based upon implementation preferences, it is understood that the specific order or hierarchy of blocks in the processes may be rearranged, or that not all illustrated blocks be performed. Any of the blocks may be performed simultaneously. In one or more embodiments, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0424] The subject technology is illustrated, for example, according to various aspects described above. The present disclosure is provided to enable any person skilled in the art to practice the various aspects described herein. The disclosure provides various examples of the subject technology, and the subject technology is not limited to these examples. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects.

[0425] A reference to an element in the singular is not intended to mean “one and only one” unless specifically stated, but rather “one or more.” Unless specifically stated otherwise, the term “some” refers to one or more. Pronouns in the masculine (e.g., his) include the feminine and neuter gender (e.g., her and its) and vice versa. Headings and subheadings, if any, are used for convenience only and do not limit the disclosure.

[0426] To the extent that the terms “include,” “have,” or the like is used in the description or the claims, such term is intended to be inclusive in a manner similar to the term “comprise” as “comprise” is interpreted when employed as a transitional word in a claim.MWS Docket No. 114212-0338

[0427] The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments. In one aspect, various alternative configurations and operations described herein may be considered to be at least equivalent.

[0428] As used herein, the phrase “at least one of’ preceding a series of items, with the terms “and” or “or” to separate any of the items, modifies the list as a whole, rather than each member of the list (i.e., each item). The phrase “at least one of’ does not require selection of at least one item; rather, the phrase allows a meaning that includes at least one of any one of the items, and / or at least one of any combination of the items, and / or at least one of each of the items. By way of example, the phrases “at least one of A, B, and C” or “at least one of A, B, or C” each refer to only A, only B, or only C; any combination of A, B, and C; and / or at least one of each of A, B, and C.

[0429] A phrase such as an “aspect” does not imply that such aspect is essential to the subject technology or that such aspect applies to all configurations of the subject technology. A disclosure relating to an aspect may apply to all configurations, or one or more configurations. An aspect may provide one or more examples. A phrase such as an aspect may refer to one or more aspects and vice versa. A phrase such as an “embodiment” does not imply that such embodiment is essential to the subject technology or that such embodiment applies to all configurations of the subject technology. A disclosure relating to an embodiment may apply to all embodiments, or one or more embodiments. An embodiment may provide one or more examples. A phrase such as an embodiment may refer to one or more embodiments and vice versa. A phrase such as a “configuration” does not imply that such configuration is essential to the subject technology or that such configuration applies to all configurations of the subject technology. A disclosure relating to a configuration may apply to all configurations, or one or more configurations. A configuration may provide one or more examples. A phrase such as a configuration may refer to one or more configurations and vice versa.

[0430] In one aspect, unless otherwise stated, all measurements, values, ratings, positions, magnitudes, sizes, and other specifications that are set forth in this specification, including in the claims that follow, are approximate, not exact. In one aspect, they are intended to have a reasonable range that is consistent with the functions to which they relateMWS Docket No. 114212-0338and with what is customary in the art to which they pertain. It is understood that some or all steps, operations, or processes may be performed automatically, without the intervention of a user.

[0431] Method claims may be provided to present elements of the various steps, operations, or processes in a sample order, and are not meant to be limited to the specific order or hierarchy presented.

[0432] In one aspect, a method may be an operation, an instruction, or a function and vice versa. In one aspect, a claim may be amended to include some or all of the words (e.g., instructions, operations, functions, or components) recited in other one or more claims, one or more words, one or more sentences, one or more phrases, one or more paragraphs, and / or one or more claims.

[0433] All structural and functional equivalents to the elements of the various configurations described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and intended to be encompassed by the subject technology. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the above description. No claim element is to be construed under the provisions of 35 U.S.C. §112, sixth paragraph, unless the element is expressly recited using the phrase “means for” or, in the case of a method claim, the element is recited using the phrase “step for.”

[0434] The Title, Background, and Brief Description of the Drawings of the disclosure are hereby incorporated into the disclosure and are provided as illustrative examples of the disclosure, not as restrictive descriptions. It is submitted with the understanding that they will not be used to limit the scope or meaning of the claims. In addition, in the Detailed Description, it can be seen that the description provides illustrative examples, and the various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the included subject matter requires more features than are expressly recited in any claim. Rather, as the claims reflect, inventive subject matter lies in less than all features of a single disclosed configuration or operation. The claims are hereby incorporated into the Detailed Description, with each claim standing on its own to represent separately patentable subject matter.MWS Docket No. 114212-0338

[0435] The claims are not intended to be limited to the aspects described herein but are to be accorded the full scope consistent with the language of the claims and to encompass all legal equivalents. Notwithstanding, none of the claims are intended to embrace subject matter that fails to satisfy the requirement of 35 U.S.C. § 101, 102, or 103, nor should they be interpreted in such a way.

[0436] Embodiments consistent with the present disclosure may be combined with any combination of features or aspects of embodiments described herein.

[0437] Some embodiments provide a method for delivering sleep treatment, comprising: collecting initial patient data and clinical data; generating a baseline of a patient based on the initial patient data and clinical data; receiving sensor data from at least a distal device and a proximal device; generating a Distal Proximal Gradient (DPG) based on the sensor data; generating an individualized treatment plan based on the DPG and the initial patient data and clinical data; and administering at least one treatment based on the individualized treatment plan.

[0438] In some embodiments, the initial patient data comprises subjective inputs to identify patient needs, goals, and patient history.

[0439] In some embodiments, the distal device and the proximal device comprise sensors selected from the group consisting of a core body temperature sensor, a heart rate sensor, a movement sensor, an activity sensor, and an oxygen saturation ( SpO ) sensor.

[0440] In some embodiments, the DPG is used as a biomarker of different sleep stages.

[0441] In some embodiments, the treatment includes warming and heating at least a portion of a body of the patient.

[0442] In some embodiments, the treatment includes at least one of thermoregulation and electrical stimulation.

[0443] In some embodiments, the individualized treatment plan includes personalized recommendations including a light exposure recommendation.

[0444] Some embodiments provide a system, comprising: a sensor measuring a skin temperature and a core temperature of a user; a processor determining Distal ProximalMWS Docket No. 114212-0338Gradient (DPG) based on the skin temperature and the core temperature; and a treatment device configured to provide therapy to the user based on the DPG.

[0445] Some embodiments provide a method for delivering sleep treatment, comprising: collecting initial user data and clinical data; generating a baseline of a user based on the collected initial user data and clinical data; receiving sensor data from at least a distal device and a proximal device; generating a Distal Proximal Gradient (DPG) slope based on the sensor data to measure sleep quality; generating an individualized treatment plan based on the sleep quality; and administering at least one treatment based on the individualized treatment plan.

[0446] In some embodiments, the initial user data includes subjective inputs to identify user needs, goals, and user history.

[0447] In some embodiments, the distal device and the proximal device include dual pod sensors selected from the group consisting of a core body temperature sensor, a heart rate sensor, a movement sensor, an activity sensor, and an oxygen saturation (SpO ) sensor.

[0448] In some embodiments, DPG is used as a biomarker of different sleep stages.

[0449] In some embodiments, the treatment includes warming and heating at least a portion of a body of the user.

[0450] In some embodiments, the treatment includes at least one of thermoregulation and electrical stimulation.

[0451] In some embodiments, the individualized treatment plan includes personalized recommendations including a light exposure recommendation.

[0452] Some embodiments further comprise phenotyping the user based on the sensor data; and diagnosing the user with a sleep disorder based on a phenotype of the user.

[0453] Some embodiments further comprise administering thermoregulation therapy, via one of the distal device and the proximal device, both of the distal device and the proximal device, or a secondary device, based on the DPG slope.

[0454] Some embodiments provide a system for delivering sleep treatment, comprising: one or more processors; and a memory comprising instructions stored thereon, which whenMWS Docket No. 114212-0338executed by the one or more processors, causes the one or more processors to perform: collecting initial user data and clinical data; generating a baseline of a user based on the collected initial user data and clinical data; receiving sensor data from at least a distal device and a proximal device; generating a Distal Proximal Gradient (DPG) slope based on the sensor data to measure sleep quality; generating an individualized treatment plan based on the sleep quality; and administering at least one treatment based on the individualized treatment plan.

[0455] In some embodiments, the initial user data includes subjective inputs to identify user needs, goals, and user history.

[0456] In some embodiments, the distal device and the proximal device include dual pod sensors selected from the group consisting of a core body temperature sensor, a heart rate sensor, a movement sensor, an activity sensor, and an oxygen saturation (SpO ) sensor.

[0457] In some embodiments, DPG is used as a biomarker of different sleep stages.

[0458] In some embodiments, the treatment includes warming and heating at least a portion of a body of the user.

[0459] In some embodiments, the treatment includes at least one of thermoregulation and electrical stimulation.

[0460] In some implementations, the treatment is delivered using an electrical stimulation device delivering non-invasive brain stimulation, prior to sleep or during sleep, to improve sleep onset and maintenance.

[0461] In some implementations, the treatment is an audio treatment delivered using an auditory stimulation device which uses bone conduction audio to enhance slow-wave and REM sleep, without disrupting the sleeper.

[0462] In some embodiments, the individualized treatment plan includes personalized recommendations including a light exposure recommendation. The light exposure recommendation may include a recommendation to adjust an amount of light exposure by a predetermined amount prior to sleep in order to promote circadian alignment.MWS Docket No. 114212-0338

[0463] The light sensor can be used to provide light therapy through personalized guidance on timing and intensity of light exposure, promoting circadian alignment through increased daytime light and reduced evening exposure. By non-limiting example, insomnia management platform 312 can be configured to create parallel relationships to light and physiological behavior which can contribute to misalignments in the patient’s circadian rhythm. Based on data collected from monitoring system 310, the insomnia management platform 312 can generate and provide a recommendation to the client to improve sleep quality (for example, reduce light exposure at least thirty minutes before bedtime).

[0464] In some embodiments, the instructions cause the one or more processors to perform: phenotyping the user based on the sensor data; and diagnosing the user with a sleep disorder based on a phenotype of the user.

[0465] In some embodiments, the instructions cause the one or more processors to perform administering thermoregulation therapy, via one of the distal device and the proximal device, both of the distal device and the proximal device, or a secondary device, based on the DPG slope.

[0466] Some embodiments provide a system, comprising: a sensor measuring a skin temperature and a core temperature of a user; a processor configured to: determine Distal Proximal Gradient (DPG) based on the skin temperature and the core temperature; determine sleep quality based on a DPG slope; and a treatment device configured to provide therapy to the user based on the DPG.

[0467] In some embodiments, the treatment device is configured to adjust a light exposure in an environment of the user and / or apply thermoregulation to a body of the user.

[0468] Some embodiments provide a method for physical activity monitoring and guidance, comprising: receiving physiological data from a first device affixed to a first region of a user and from a second device affixed to a second region of a user, wherein the physiological data comprises skin temperature, wherein the user is engaged in a fitness activity; calculating a Distal Proximal Gradient (DPG) slope based on the received physiological data; based on the DPG slope, generating a recommendation for the user to optimize the fitness activity; and providing the recommendation to the user through a user interface on a user device operated by the user.MWS Docket No. 114212-0338

[0469] In some embodiments, the physiological data further comprises one or more of movement, activity, oxygen saturation (SpCh). heart rate, respiratory rate, light exposure, electrodermal activity (EDA), and galvanic skin response (GSR).

[0470] Some embodiments further comprise calculating additional thermal biomarkers associated with the user, wherein generating the recommendation is further based on the additional thermal biomarkers, wherein the additional thermal biomarkers comprise one or more of core body temperature and heat flux.

[0471] Some embodiments further comprise receiving environmental data from a third device, and generating the recommendation is further based on the environmental data, wherein the environmental data comprises one or more of ambient temperature and light level. In some embodiments, the third device is a charging dock for the first device and the second device, the charging dock comprising at least one of a temperature sensor and a light level sensor.

[0472] Some embodiments further comprise receiving activity data from at least one of the first device and the second device, and generating the recommendation is further based on the activity data.

[0473] In some embodiments, the first region is a core region of the user’s body, and the second region is a limb region of the user’s body.

[0474] In some embodiments, the physical activity is a sleep activity, and optimizing the fitness activity comprises one or more of reducing sleep debt, improving sleep regularity, optimizing heat flow during sleep, optimizing sleep environment temperature, and optimizing sleep environment light.

[0475] In some embodiments, the fitness activity is a training activity, and optimizing the fitness activity comprises one or more of (i) determining at least one optimum time period to perform the training activity, (ii) providing real-time, quantitative measurements of power and energy during the training activity, (iii) determining in real time an optimum time for additional exertion during the training activity, (iv) determining in real time an optimum time for resting during the training activity, or (v) determining in real time an optimum time for cooling or hydrating during the training activity.MWS Docket No. 114212-0338

[0476] In some embodiments, the fitness activity is a resting activity, and optimizing the fitness activity comprises determining at least one optimum time period to perform the resting activity.

[0477] In some embodiments, the physical activity is an eating activity, and optimizing the fitness activity comprises determining at least one optimum time period to perform the eating activity.

[0478] In some embodiments, the physical activity is a focus activity, and optimizing the fitness activity comprises determining at least one optimum time period during the day to perform the focus activity.

[0479] In some embodiments, the first region of the user’s body is a left-side muscle, and the second region of the user’s body is a right-side muscle corresponding to the left-side muscle. In some embodiments, the computing system may calculate a bilateral muscle balance metric representing a difference, ratio, or other comparison of power output or activity levels associated with the left-side muscle and the right-side muscle and may generate a recommendation based on the bilateral muscle balance metric.

[0480] Some embodiments provide a method for physical activity monitoring and guidance, performed by one or more processors of a computing system, the method comprising: receiving physiological data from a first device affixed to a left-side muscle of a user and from a second device affixed to a right-side muscle of the user corresponding to the left-side muscle, while the user is engaged in a fitness activity, wherein the physiological data comprises skin temperature; calculating a bilateral muscle balance metric representing a difference, ratio, or other comparison of power output or activity levels associated with the left-side muscle and the right-side muscle; generating, based on the bilateral muscle balance metric, a recommendation associated with the physical activity; and causing presentation of the recommendation in a user interface on a user device operated by the user.

[0481] In some embodiments, the recommendation identifies an asymmetry or imbalance between the left-side muscle and the right-side muscle. In some embodiments, the bilateral muscle balance metric is based on one or more of power output, activity level, or temperature associated with the left-side muscle and the right-side muscle. In some embodiments, the recommendation includes a training recommendation to correct an asymmetry, refine technique, or improve bilateral performance. In some embodiments, the recommendation is noMWS Docket No. 114212-0338presented as one or more of instantaneous values, time-series plots, or summary statistics representing the left-side muscle and the right-side muscle.

[0482] Some embodiments provide a method for physical activity monitoring and guidance, performed by one or more processors of a computing system, the method comprising: receiving physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user while the user is engaged in a fitness activity, wherein the physiological data comprises skin temperature; calculating, based on the physiological data, a Distal Proximal Gradient (DPG) slope; receiving environmental data from a third device; generating, based on the DPG slope and the environmental data, a recommendation identifying at least one recommended time period, condition, or action associated with the physical activity; and causing presentation of the recommendation in a user interface on a user device operated by the user.

[0483] In some embodiments, the environmental data comprises one or more of ambient temperature and light level. In some embodiments, the third device is a charging dock for the first device and the second device, the charging dock comprising at least one of a temperature sensor and a light level sensor. In some embodiments, the physical activity is a sleep activity, and the recommendation identifies one or more of a bedroom temperature condition or a bedroom lighting condition.

[0484] Some embodiments provide a method for physical activity monitoring and guidance, performed by one or more processors of a computing system, the method comprising: receiving physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, while the user is engaged in a physical activity, the physiological data comprising skin temperature; calculating, based on the physiological data, a Distal Proximal Gradient (DPG) slope; calculating, based on the physiological data, one or more additional thermal biomarkers associated with the user, wherein the additional thermal biomarkers comprise one or more of core body temperature and heat flux; generating, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity; and causing presentation of the recommendation in a user interface on a user device operated by the user.MWS Docket No. 114212-0338

[0485] In some embodiments, the physiological data further comprises one or more of movement, activity, oxygen saturation (SpCh). heart rate, respiratory rate, light exposure, electrodermal activity (EDA), and galvanic skin response (GSR).

[0486] In some embodiments, the proximal region is a core region of the user’s body, the distal region is a limb region of the user’s body, and calculating the one or more additional thermal biomarkers is based on measurements of physiological data from the first device positioned at the core region and the second device positioned at the limb region.

[0487] In some embodiments, the method further comprises receiving activity data from at least one of the first device and the second device, and the recommendation is further based on the activity data, the activity data comprising one or more of heart rate, respiratory rate, and user motion.

[0488] In some embodiments, the physical activity is a sleep activity, and the recommendation identifies one or more of a sleep-debt condition, a sleep-regularity condition, a heat-flow condition during sleep, a bedroom temperature condition, or a bedroom lighting condition.

[0489] In some embodiments, the physical activity is a fitness activity, and the recommendation identifies at least one time period during a day to perform the fitness activity, the fitness activity comprising one of a training activity, or a rest or recovery activity. In some embodiments, the recommendation includes a heat-flow condition or a cooling-efficiency state associated with the fitness activity.

[0490] In some embodiments, the fitness activity is a training activity, and the recommendation includes real-time, quantitative measurements of power and energy during the training activity. In some embodiments, the fitness activity is a training activity, and the recommendation includes determining in real time one or more optimum times for additional exertion during the training activity, resting during the training activity, cooling during the training activity, and / or hydrating during the training activity. In some embodiments, the recommendation further includes caloric expenditure associated with the training activity.

[0491] In some embodiments, the physical activity is an eating activity, and the recommendation includes determining an optimum time period to perform the eating activity.MWS Docket No. 114212-0338

[0492] In some embodiments, the physical activity is a focus activity, and the recommendation includes determining an optimum time period to perform the focus activity.

[0493] In some embodiments, the recommendation includes a circadian phase alignment indication or a body-clock time window associated with one or more of cognitive focus, coordination, strength, endurance, refueling, sleep, or rest or recovery.

[0494] Some embodiments provide a non-transitory, computer-readable storage medium storing instructions for physical activity monitoring and guidance, wherein the instructions, when executed by one or more processors of a computing system, cause the computing system to perform any of the methods and associated embodiments described above.

[0495] Some embodiments provide a system for physical activity monitoring and guidance, comprising one or more processors and further comprising one or more non-transitory, computer-readable media storing instructions that when executed by the one or more processors, cause the computing system to perform any of the methods and associated embodiments described above.

Claims

MWS Docket No. 114212-0338CLAIMS WHAT IS CLAIMED IS:

1. A method for physical activity monitoring and guidance, performed by one or more processors of a computing system, the method comprising:receiving physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, while the user is engaged in a physical activity, the physiological data comprising skin temperature;calculating, based on the physiological data, a Distal Proximal Gradient (DPG) slope; calculating, based on the physiological data, one or more additional thermal biomarkers associated with the user, wherein the additional thermal biomarkers comprise one or more of core body temperature and heat flux;generating, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity; andcausing presentation of the recommendation in a user interface on a user device operated by the user.

2. The method of claim 1, wherein the physiological data further comprises one or more of movement, activity, oxygen saturation (SpCh). heart rate, respiratory rate, light exposure, electrodermal activity (EDA), and galvanic skin response (GSR).

3. The method of claim 1 wherein the proximal region is a core region of the user’s body, the distal region is a limb region of the user’s body, and calculating the one or more additional thermal biomarkers is based on measurements of physiological data from the first device positioned at the core region and the second device positioned at the limb region.

4. The method of claim 1, further comprising receiving activity data from at least one of the first device and the second device, and wherein the recommendation is further based on the activity data, the activity data comprising one or more of heart rate, respiratory rate, and user motion.

5. The method of claim 1, wherein the physical activity is a sleep activity, and the recommendation identifies one or more of a sleep-debt condition, a sleep-regularityMWS Docket No. 114212-0338condition, a heat-flow condition during sleep, a bedroom temperature condition, or a bedroom lighting condition.

6. The method of claim 1, wherein the physical activity is a fitness activity, and the recommendation identifies at least one time period during a day to perform the fitness activity, wherein the fitness activity comprises one of a training activity, or a rest or recovery activity.

7. The method of claim 6, wherein the fitness activity is a training activity, and the recommendation includes real-time, quantitative measurements of power and energy during the training activity.

8. The method of claim 6, wherein the fitness activity is a training activity, and the recommendation includes determining in real time one or more optimum times for additional exertion during the training activity, resting during the training activity, cooling during the training activity, and / or hydrating during the training activity.

9. The method of claim 1, wherein the physical activity is an eating activity, and the recommendation includes determining an optimum time period to perform the eating activity.

10. The method of claim 1, wherein the physical activity is a focus activity, and the recommendation includes determining an optimum time period to perform the focus activity.

11. A non-transitory, computer-readable storage medium storing instructions for physical activity monitoring and guidance, wherein the instructions, when executed by one or more processors of a computing system, cause the computing system to:receive physiological data from a first device affixed to a proximal region of a user and from a second device affixed to a distal region of a user, while the user is engaged in a physical activity, the physiological data comprising skin temperature;calculate, based on the physiological data, a Distal Proximal Gradient (DPG) slope; calculate, based on the physiological data, one or more additional thermal biomarkers associated with the user, wherein the additional thermal biomarkers comprise one or more of core body temperature and heat flux;MWS Docket No. 114212-0338generate, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity; andcause presentation of the recommendation in a user interface on a user device operated by the user.

12. The non-transitory, computer-readable storage medium of claim 11, wherein the physiological data further comprises one or more of movement, activity, oxygen saturation (SpCh). heart rate, respiratory rate, light exposure, electrodermal activity (EDA), and galvanic skin response (GSR).

13. The non-transitory, computer-readable storage medium of claim 11, wherein the proximal region is a core region of the user’s body, the distal region is a limb region of the user’s body, and calculating the one or more additional thermal biomarkers is based on measurements of physiological data from the first device positioned at the core region and the second device positioned at the limb region.

14. The non-transitory, computer-readable storage medium of claim 11, wherein the instructions, when executed by the one or more processors, further cause the computing system to receive activity data from at least one of the first device and the second device, and wherein the recommendation is further based on the activity data, the activity data comprising one or more of heart rate, respiratory rate, and user motion.

15. The non-transitory, computer-readable storage medium of claim 11, wherein the physical activity is a sleep activity, and the recommendation identifies one or more of a sleep-debt condition, a sleep-regularity condition, a heat-flow condition during sleep, a bedroom temperature condition, or a bedroom lighting condition.

16. The non-transitory, computer-readable storage medium of claim 11, wherein the physical activity is a fitness activity, and the recommendation identifies at least one time period during a day to perform the fitness activity, wherein the fitness activity comprises one of a training activity, or a rest or recovery activity.

17. The non-transitory, computer-readable storage medium of claim 16, wherein the fitness activity is a training activity, and the recommendation includes at least one of: (i) real-time, quantitative measurements of power and energy during the training activity, andMWS Docket No. 114212-0338(ii) determining in real time one or more optimum times for additional exertion during the training activity, resting during the training activity, cooling during the training activity, and / or hydrating during the training activity.

18. The non-transitory, computer-readable storage medium of claim 11, wherein the physical activity is an eating activity, and the recommendation includes determining an optimum time period to perform the eating activity.

19. The non-transitory, computer-readable storage medium of claim 11, wherein the physical activity is a focus activity, and the recommendation includes determining an optimum time period to perform the focus activity.

20. A system for physical activity monitoring and guidance, comprising: one or more processors;a first device affixed to a proximal region of a user;a second device affixed to a distal region of a user; andone or more non-transitory, computer-readable media storing instructions that when executed by the one or more processors, cause the system to:receive physiological data from the first device and from the second device while the user is engaged in a physical activity, the physiological data comprising skin temperature;calculate, based on the physiological data, a Distal Proximal Gradient (DPG) slope;calculate, based on the physiological data, one or more additional thermal biomarkers associated with the user, wherein the additional thermal biomarkers comprise one or more of core body temperature and heat flux;generate, based on the DPG slope and the one or more additional thermal biomarkers, a recommendation identifying at least one recommended time period, condition or action associated with the physical activity; andcause presentation of the recommendation in a user interface on a user device operated by the user.