Systems and methods for detecting emerging attributes and improving health outcomes

Abstract

The present disclosure describes a system for identifying at least one identifiable feature associated with a state of health of a subject, the system comprising: (i) at least one sensor for measuring a heat flux of the subject and thereby generating a data stream, where the data stream comprises a plurality of heat flux measurements; and (ii) a processor configured to receive the data stream and identify at least one identifiable feature associated with the state of health. Methods are described for (a) evaluating body temperature regulation elasticity of a subject and generating alarms or suggestions to intervene in the subject based on the evaluated body temperature regulation elasticity, and (b) identifying identifiable features associated with a health status of the subject. The method comprises: measuring a heat flux of the subject using at least one sensor and thereby generating a data stream, the data stream comprising a plurality of heat flux measurements; and receiving, using a processor, the data stream and identifying at least one identifiable feature associated with the state of health.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Application No. 63 / 387,276 filed on December 13, 2022, U.S. Provisional Application No. 63 / 486,930 filed on February 24, 2023, and U.S. Provisional Application No. 63 / 488,892 filed on March 7, 2023, the entire contents of each of the above U.S. provisional applications are incorporated herein by reference. Technical Field

[0003] The disclosed technology generally relates to systems, wearable devices, and methods for detecting identifiable features by measuring emergent properties of complex adaptive systems, such as biological systems, organisms, or non-biological systems, such as the human body. Background Art

[0004] The current approach to solving problems in the biological sciences is a bottom-up approach often referred to as "precision biology." In its broadest form, precision biology combines machine learning with detailed measurements of biological components ("omics") to assign functions to those components. This approach is also often referred to as "precision medicine," especially when applied to the discovery, development, and delivery of healthcare solutions.

[0005] Precision biology is based on the idea that knowledge gaps arise from a lack of understanding of the "components," and detailed measurement and analysis will fill these gaps. For example, a foundational tool in modern biological science is organic chemistry, the study of molecules containing carbon and carbon bonded to other key atoms. This is at least in part because the genetic, signaling, and structural molecules of living systems are primarily composed of carbon atoms. Therefore, within the precision biology paradigm, function and functional prediction are sought by quantifying these organic chemical properties in greater detail. However, the field generally fails to recognize that many features of biological systems do not fit the precision biology paradigm. One example of the failure of the precision biology paradigm is the measurement and prediction of emergent properties in complex adaptive (biological) systems. Emergent properties are properties that are not present in a part of a system or that can be easily inferred through a detailed inventory and analysis of the system's components. The precision biology approach, which has now risen to paradigmatic status, suffers from a blind spot regarding emergent properties; this blind spot has significantly limited progress in biology and medicine.

[0006] A historical perspective reveals the many advantages of current technologies, even though none of the past and present understanding of biological systems and how to monitor them and maintain or improve health anticipated or revealed the systems, methods, and uses of current technologies. Known devices and methods for monitoring biological systems, as well as known systems for maintaining or improving health, are inadequate. For example, known wearable devices are often available in the off-the-shelf market; however, many patients and users are excluded from this market.

[0007] The history of measuring human biological systems to understand their function dates back to Hippocrates around 450 BC. Hippocrates is credited with separating medicine from religion in the human biological system, establishing a physical basis for measuring and diagnosing disease and developing predictors. The idea that human biology could be understood through the lens of physical science, rather than religion, developed over the next approximately 2,400 years until the beginning of the Industrial Revolution.

[0008] Inspired by industrial advances, biologists and chemists in the late 19th and early 20th centuries began to employ methods and techniques similar to those successfully employed in physics, engineering, and industry. In the first half of the 20th century, these methods led to the successful identification of vitamins, enzyme cofactors derived from food; the biological basis of viral and bacterial infections and their prevention through vaccines and antibiotics; and the successful identification of DNA, the genetic material, and how this information encodes proteins. These advances led to astonishing progress in our understanding of biological sciences and medicine.

[0009] In the most general sense, the tools and theories that drove industrialization were then and are still being used to solve biological problems. At the core of this theory is a kind of reductionism, which manifests itself in the scientific method as a broad assumption about which parts are responsible for which functions.

[0010] Precision learning methods are most predictive when there is a simple, ordered relationship between parts and their functions. Examples of this in non-biological systems might include the tire on a bicycle, or in biological systems might include the genes and proteins essential for energy synthesis and life itself. In these instances, measurements of the tire or gene are expected to correlate with the system's function. Precision biology methods have the greatest positive predictive value in non-biological systems designed and engineered by humans, because these systems, by definition, follow a 1:1 relationship between parts and function. Precision biology methods also have value in biological systems, where there is a hypothesized and measurable relationship between parts and their functions. However, when a 1:1 relationship between parts and their functions does not exist, precision biology methods lose their positive predictive value in biological systems. An example of a situation where there is no discernible relationship between parts and their functions is when one, two, or more parts form a new structure or perform a new function that cannot be easily predicted or discerned from the part(s) alone. This property, the ability of one or more parts to form a structure or perform a function that is not present in the part(s) alone, is an "emergent structure or function," collectively referred to as an "emergent property."

[0011] Current precision biology approaches to understanding the function of both biological and complex non-biological systems are limited by the inability to measure, quantify, predict, control, maximize, design, and engineer complex adaptive biological and non-biological systems based on emergent properties. These limitations are observed at virtually all levels of biological systems, including the biosphere itself.

[0012] Precision biology approaches are limited in their understanding of biological and human function. A component-based approach implicitly views a biological system or the human body as a collection of discrete parts whose functions can be categorized and calculated. This approach embodies the paradigm that predates vitamins but, ironically, is now limited by an incomplete inventory of parts responsible for function. Until recently, precision biology approaches to the human body ignored the estimated 1-10 trillion bacteria that make up the human microbiome. Precision biology approaches also completely ignore or omit other parts and the context in which they exist. An example is food. While the human diet is estimated to contain over 30,000 small molecules of plant origin (called phytonutrients), the functions of less than 0.1% of these phytonutrients (i.e., vitamins) are understood. Furthermore, precision biology approaches underestimate the critical importance and deprioritize research on certain enzyme classes, including but not limited to enzymes that interact with substances from the environment in metabolism, such as oxidoreductases. When applied to medicine, the precision biology paradigm oversimplifies the complexity of biological systems. When the functions sought to be understood are emergent in origin, the ability to diagnose and develop treatments for disease is severely limited.

[0013] The precision biology approach is also limited in its ability to understand the health of a species or a group of species and resources. It views health as a state of zero or no disease achieved through a process of disease elimination. Today, human health is a concept, not a reality. It should be noted that this is not always the case in many non-reductionist cultures. The concept of health as an energy state, essentially an emergent property independent of disease, is common in many Eastern cultures and religions. Chakras, auras, prana, and qi date back to 400 BC. More recently, in the West, it has been referred to as life force in the 20th century. Health is fundamental to the functioning of biological systems and can also be referred to as homeostasis. However, homeostasis is an emergent property: the complex interactions between many components produce interchangeable forms and functions that are not present or discernible in the precision biology approach. The precision biology approach clearly fails in open systems, where homeostasis (health) depends on complex interactions with both internal and external environments. Consequently, disease indicators can be used to define the absence of health. Disease indicators are a poor proxy for health deficits because they lag significantly behind changes in health or “health capacity”: the resilience (adaptability) of a system is primarily expressed through its ability to sustain or achieve some core functions.

[0014] Precision biology approaches are also limited in “genetic engineering” and industrial biology. The lack of a 1:1 relationship between genetic changes and expected outcomes often leads to unstable (unhealthy) states that are inconsistent with the intended new function (synthetic function) or viability.

[0015] Precision biology approaches are also limited in their implementation. They require highly specialized and expensive equipment for measurements. They are also limited in their learning rate. They result in an unmanageable number of false (positive) discoveries and reduce the likelihood of unexpected results (in other words, unintended consequences). The cost, risk, and time of learning are extremely high and, consistent with Eroom's law, continue to increase. Precision biology approaches are also limited by their invasiveness and ethical nature. While emergent properties can often be quantified externally, precision biology approaches generally involve invasive testing or experimental euthanasia, which can be unethical, harmful, or lethal, all of which reduce the practicality of obtaining frequent and sufficient measurements. Without large sample sizes and realistic artificial test data, it is difficult to achieve the statistical power required to distinguish good hypotheses from bad ones. This exacerbates the problem of false discoveries and further slows the overall learning rate in biological sciences. A limitation of precision biology approaches is that they fail to consider the impact of anthropocentrism on biological function. This approach assumes that DNA contains all relevant biological information and that functions cascade in an immediate manner. It fails to consider other physical or biological information systems, such as temperature, inter- and intra-species dependencies, gravity, magnetic fields, electric currents, and populations, all of which have undergone dramatic changes during the past 100 years of the "Anthropocene." Precision biology approaches are also limited by the "paradigm" assumption that "DNA is the book of life" is "truth," despite evidence to the contrary. Despite these obvious limitations of the precision biology approach / paradigm, the approach has been dogmatically perpetuated, culminating in a series of "omics" revolutions. Because an infinite set of component classification rules is possible, component-based approaches are inherently infinite and therefore unfalsifiable: the precision biology paradigm cannot be disproven. Modern machine learning tools exacerbate this unfalsification. It is now speculated that the knowledge gap in precision biology approaches lies not in the methods themselves, but in the lack of analytical methods to understand the individual components. While machine learning tools are certainly useful for the problems addressed by precision biology approaches, increased analysis and data collection have never replaced the need for new measurements that make the hidden visible. Precision biology approaches simply do not measure or acknowledge the emergent properties of biological systems that define the essence of life.

[0016] Life exists and persists under a wide range of dynamic environmental conditions. Life can be found in diverse forms across extreme temperatures, pressures, pH conditions, and chemical solutions. However, all organisms possess the emergent property of extracting energy from their environment and utilizing that energy according to metabolic strategies that are "adapted" to their environment. While these metabolic strategies are nearly as numerous as there are species, all must adhere to the fundamental thermodynamic principles of heat transfer and, therefore, must be thermally appropriate to their environment. In other words, to survive, all species must be appropriately "thermally adapted" to their environment. If an organism loses the ability to maintain thermal adaptation to its environment, its metabolism fails, and the organism cannot continue to survive (i.e., dies). This fundamental principle of thermal adaptation governs all organisms, from primitive bacteria to plants to organisms as complex as humans. Therefore, effectively maintaining or regulating an organism's thermal adaptation depends on the effective design and execution of corresponding metabolic strategies in the face of dynamic environmental change. Because extracting alternative energy from the environment inherently carries metabolic costs, the aspects of the metabolic strategy most likely to deplete energy pose the greatest risk to an organism's ability to maintain thermal adaptation.

[0017] Therefore, a new approach is needed to measure, quantify, and interpret the emergent properties of both biological and non-biological systems to understand the functioning of complex adaptive systems and to enable prediction, optimization, design, and planning of both biological and non-biological systems. This approach should be considered as part of a "coherent approach" that considers the holistic nature of all biological and non-biological parts and systems and their emergent properties.

[0018] New systems, devices, and methods are needed to more accurately, more easily accessibly, more scalably, and more readily understand the functioning of complex adaptive systems. Ideally, such systems, devices, and methods would be able to predict, optimize, design, and engineer both biological and non-biological systems, taking into account the holistic nature of all living and non-biological parts and systems. Summary of the Invention

[0019] The present disclosure provides systems, devices, and methods for continuously and contextually characterizing an individual's metabolic state and / or thermal adaptation by measuring their thermal signature, thereby assessing the so-called thermoregulatory phenotype. Changes associated with this phenotype are sensitive indicators of changes in health status. These systems, devices, and methods are designed and configured to provide an overall correlation between an individual's thermal signature and physiological reserves in human use. The thermal signature provides more information that can be used to provide a viable assessment of health status.

[0020] In certain embodiments, a system for identifying at least one identifiable feature associated with a health state of a subject comprises: at least one sensor for measuring heat flux of the subject and generating a data stream therefrom, wherein the data stream comprises a plurality of heat flux measurements; and a processor configured to receive the data stream and identify at least one identifiable feature associated with the health state.

[0021] In certain embodiments, the at least one sensor for measuring heat flux comprises at least one sensor array for simultaneously measuring heat dissipation from the subject and the ambient temperature near the subject.

[0022] In certain embodiments, the plurality of heat flux measurements includes a plurality of heat dissipation measurements expressed as a function of ambient temperature.

[0023] In certain embodiments, the system further includes at least one transition state corresponding to at least one identifiable characteristic of the data stream.

[0024] In certain embodiments, at least one identifiable characteristic associated with the health state corresponds to a biological response.

[0025] In some embodiments, the duration of the at least one identifiable characteristic is less than one hour.

[0026] In some embodiments, the duration of the at least one identifiable characteristic is greater than one hour.

[0027] In certain embodiments, the at least one identifiable characteristic corresponds to a homeostatic state of the subject.

[0028] In certain embodiments, the data stream further includes at least one work quantification associated with the plurality of heat flux measurements.

[0029] In some embodiments, at least one work quantification corresponds to energy expended by a user entering at least one transition state corresponding to at least one identifiable characteristic of the data stream.

[0030] In certain embodiments, the at least one quantification of work further corresponds to energy expended by the subject between the first transition state and the second transition state.

[0031] In some embodiments, at least one work quantification corresponds to motion of the subject.

[0032] In certain embodiments, the system is further configured to identify at least one motif, wherein the at least one motif comprises a plurality of heat flux measurements.

[0033] In certain embodiments, there is at least one transition state between the first motif and the second motif.

[0034] In certain embodiments, the system is further configured to identify at least one inharmony comprising a plurality of heat flux measurements that do not correspond to the at least one identifiable feature.

[0035] In certain embodiments, one or more identifiable features are indicative of thermal regulation.

[0036] In certain embodiments, the one or more identifiable characteristics include one or more unique features, wherein the one or more unique features are at least one of: a thermal range; and a thermal trend.

[0037] In certain embodiments, one or more unique patterns are indicative of a health transition.

[0038] In certain embodiments, the system is further configured to identify a difference between a first heat flux measurement in the plurality of heat flux measurements and a second heat flux measurement in the plurality of heat flux measurements.

[0039] In certain embodiments, at least one transition state indicates a change in homeostasis in the subject.

[0040] In certain embodiments, the processor predicts a plurality of future heat flux measurements based on the identified at least one identifiable feature.

[0041] In some embodiments, the processor predicts a future identifiable feature based on the identified at least one identifiable feature.

[0042] In certain embodiments, the processor determines that the subject is an outlier within the population based on at least one identifiable characteristic.

[0043] In certain embodiments, the population includes one or more subjects having a health state substantially similar to the subject's health state.

[0044] In certain embodiments, a population includes one or more subjects whose health transitions are substantially similar to the subject's health report.

[0045] In certain embodiments, the processor generates a recommended countermeasure based on the at least one identifiable characteristic.

[0046] In some embodiments, the recommended response includes at least one of: applying cold; resting; engaging in physical activity; stopping medication; starting medication; going indoors; going outdoors; increasing hydration; decreasing hydration; and elevating one or more limbs.

[0047] In certain embodiments, a processor is configured to analyze the data stream.

[0048] In certain embodiments, a method of identifying at least one identifiable feature associated with a biological response includes: measuring heat flux of a subject; generating a data stream, wherein the data stream includes a plurality of heat flux measurements; and identifying at least one identifiable feature from the data stream.

[0049] In certain embodiments, the method further includes comparing the analysis of the at least one identifiable feature identified for the first subject with the analysis of the at least one identifiable feature identified for the second subject.

[0050] In certain embodiments, a method of assessing thermoregulatory resilience of a subject and generating a recommendation for intervention with the subject based on the assessed thermoregulatory resilience comprises: generating a thermoregulatory resilience score for the subject over a predetermined time period, wherein the thermoregulatory resilience score is based on a data stream comprising a plurality of thermoregulatory measurements of the subject; determining whether a need for intervention with the subject exceeds a predetermined urgency threshold; and generating a recommendation for intervention with the subject.

[0051] In certain embodiments, the predetermined period of time is at least two days.

[0052] In some embodiments, the predetermined period of time is at least one day.

[0053] In some embodiments, the predetermined period of time is approximately one day.

[0054] In some embodiments, the predetermined period of time is less than a day.

[0055] In certain embodiments, the predetermined period of time is approximately 8 hours.

[0056] In certain embodiments, the thermoregulatory resilience score is the homeostatic robustness of the subject's thermoregulatory system.

[0057] In certain embodiments, the homeostatic robustness of a subject is based on the resilience of the thermoregulatory system during transition phases.

[0058] In certain embodiments, the subject's ability to regulate the thermoregulatory system is based on the subject's health status.

[0059] In certain embodiments, the transition phase includes a plurality of thermoregulatory measurements that are inconsistent with a plurality of thermoregulatory measurements that constitute a normal state of the subject's thermoregulatory system.

[0060] In certain embodiments, the transition phase lasts for an extended period of time that is longer than the predetermined period of time.

[0061] In certain embodiments, the method further includes alerting a medical practitioner that a recommendation has been generated.

[0062] In certain embodiments, the non-extended period of the transition phase is indicative of an elastic thermoregulatory system of the subject.

[0063] In certain embodiments, a prolonged period of the transition phase is indicative of an inelastic thermoregulatory system of the subject.

[0064] In certain embodiments, the generated thermoregulatory elasticity score is greater than a predetermined threshold.

[0065] In certain embodiments, the generated thermoregulatory elasticity score is less than a predetermined threshold.

[0066] In certain embodiments, the thermoregulatory elasticity score is below a predetermined threshold for a predetermined duration.

[0067] In certain embodiments, the method further includes alerting a medical practitioner that a recommendation has been generated.

[0068] In certain embodiments, the thermoregulatory resilience score is associated with one or more interventions.

[0069] In certain embodiments, the method further comprises analyzing changes in the plurality of thermoregulatory measurements of the subject to determine a characteristic of the changes.

[0070] In certain embodiments, the plurality of thermoregulatory measurements of the subject includes a plurality of heat flux measurements.

[0071] In certain embodiments, the characteristic of the change is a pattern.

[0072] In certain embodiments, a method for identifying a subject in urgent need of intervention comprises: measuring multiple thermoregulation measurements of the subject; generating a data stream over a time period, wherein the data stream comprises the multiple thermoregulation measurements; generating a score for the time period based on the data stream; identifying whether the subject is in urgent need of intervention; and sending an alert related to the urgent need for intervention.

[0073] In some embodiments, the score is less than a predetermined score.

[0074] In certain embodiments, the score indicates that the subject's thermoregulatory system is inelastic.

[0075] In certain embodiments, an alarm system configured to generate an alarm to intervene in the health of a subject includes: at least one sensor for generating a plurality of thermoregulation measurements of the subject; a communication component for generating a data stream of the thermoregulation measurements, wherein the data stream includes the plurality of thermoregulation measurements within a predetermined time period; and a processor configured to receive the data stream and generate a score associated with the predetermined time period based on the elasticity of the thermoregulation measurements of the subject.

[0076] In certain embodiments, when the score is greater than a predetermined score threshold, the score is a resiliency score.

[0077] In certain embodiments, the system further includes an alarm configured to alert a user to intervene with the subject when the score is less than a predetermined score threshold.

[0078] In certain embodiments, the score is an inelasticity score, indicating that the subject's thermoregulatory system is inelastic.

[0079] In certain embodiments, a method of identifying a subject requiring intervention and alerting another party regarding the need for intervention includes: measuring multiple thermoregulation measurements of the subject; generating a data stream over a time period, wherein the data stream includes the multiple thermoregulation measurements; generating a score for the time period based on the data stream; grouping the score and multiple other biometrics into a data set; identifying whether the subject requires intervention based at least in part on the score; and sending an alert regarding the need for intervention.

[0080] In certain embodiments, the plurality of other biometric measurements includes at least one of: heart rate; blood pressure; or skin temperature.

[0081] In certain embodiments, it is identified whether the need for intervention is urgent.

[0082] In certain embodiments, the primary basis for determining whether a subject is in urgent need of intervention is the score.

[0083] In certain embodiments, a method for identifying a patient at a health risk includes: measuring a plurality of thermoregulation measurements of a subject; generating a data stream over a time period, wherein the data stream includes the plurality of thermoregulation measurements; generating a score for the time period based on the data stream; grouping the score and a plurality of other biometric measurements into a data set; and identifying whether the subject has a health risk.

[0084] In certain embodiments, identifying whether a subject has a health risk is used to determine at least one of: the subject's health insurance risk; or the subject's heat stroke threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1A An exemplary embodiment of a system for detecting identifiable features is shown.

[0086] Figure 1B An exemplary embodiment of a system for detecting identifiable features is shown.

[0087] Figure 2A An exemplary embodiment of a system for detecting identifiable features is shown.

[0088] Figure 2B An exemplary embodiment of a system for detecting identifiable features is shown.

[0089] Figure 2CAn exemplary embodiment of a system for detecting identifiable features is shown.

[0090] Figure 3A An exemplary embodiment of a system for detecting identifiable features is shown.

[0091] Figure 3B An exemplary embodiment of a system for detecting identifiable features is shown.

[0092] Figure 3C An exemplary embodiment of a system for detecting identifiable features is shown.

[0093] Figure 4A An exemplary embodiment of a system for detecting identifiable features is shown.

[0094] Figure 4B An exemplary embodiment of a system for detecting identifiable features is shown.

[0095] Figure 4C An exemplary embodiment of a system for detecting identifiable features is shown.

[0096] Figure 4D An exemplary embodiment of a system for detecting identifiable features is shown.

[0097] Figure 5A An exemplary embodiment of a system for detecting identifiable features is shown.

[0098] Figure 5B An exemplary embodiment of a system for detecting identifiable features is shown.

[0099] Figure 5C An exemplary embodiment of a system for detecting identifiable features is shown.

[0100] Figure 5D An exemplary embodiment of a system for detecting identifiable features is shown.

[0101] Figure 5E An exemplary embodiment of a system for detecting identifiable features is shown.

[0102] Figure 5F An exemplary embodiment of a system for detecting identifiable features is shown.

[0103] Figure 5G An exemplary embodiment of a system for detecting identifiable features is shown.

[0104] Figure 5H An exemplary embodiment of a system for detecting identifiable features is shown.

[0105] Figure 5IAn exemplary embodiment of a system for detecting identifiable features is shown.

[0106] Figure 6A An exemplary embodiment of a system for detecting identifiable features is shown.

[0107] Figure 6B An exemplary embodiment of a system for detecting identifiable features is shown.

[0108] Figure 6C An exemplary embodiment of a system for detecting identifiable features is shown.

[0109] Figure 6D An exemplary embodiment of a system for detecting identifiable features is shown.

[0110] Figure 6E An exemplary embodiment of a system for detecting identifiable features is shown.

[0111] Figure 7A An exemplary embodiment of a system for detecting identifiable features is shown.

[0112] Figure 7B An exemplary embodiment of a system for detecting identifiable features is shown.

[0113] Figure 7C An exemplary embodiment of a system for detecting identifiable features is shown.

[0114] Figure 7D An exemplary embodiment of a system for detecting identifiable features is shown.

[0115] Figure 8A An exemplary embodiment of a system for detecting identifiable features is shown.

[0116] Figure 8B An exemplary embodiment of a system for detecting identifiable features is shown.

[0117] Figure 8C An exemplary embodiment of a system for detecting identifiable features is shown.

[0118] Figure 8D An exemplary embodiment of a system for detecting identifiable features is shown.

[0119] Figure 9A An exemplary embodiment of a system for detecting identifiable features is shown.

[0120] Figure 9B An exemplary embodiment of a system for detecting identifiable features is shown.

[0121] Figure 9CAn exemplary embodiment of a system for detecting identifiable features is shown.

[0122] Figure 9D An exemplary embodiment of a system for detecting identifiable features is shown.

[0123] Figure 10A An exemplary embodiment of a system for detecting identifiable features is shown.

[0124] Figure 10B An exemplary embodiment of a system for detecting identifiable features is shown.

[0125] Figure 10C An exemplary embodiment of a system for detecting identifiable features is shown.

[0126] Figure 11A An exemplary embodiment of a system for detecting identifiable features is shown.

[0127] Figure 11B An exemplary embodiment of a system for detecting identifiable features is shown.

[0128] Figure 11C An exemplary embodiment of a system for detecting identifiable features is shown.

[0129] Figure 12A An exemplary embodiment of a system for detecting identifiable features is shown.

[0130] Figure 12B An exemplary embodiment of a system for detecting identifiable features is shown.

[0131] Figure 12C An exemplary embodiment of a system for detecting identifiable features is shown.

[0132] Figure 12D An exemplary embodiment of a system for detecting identifiable features is shown.

[0133] Figure 12E An exemplary embodiment of a system for detecting identifiable features is shown.

[0134] Figure 13A An exemplary embodiment of a system for detecting identifiable features is shown.

[0135] Figure 13B An exemplary embodiment of a system for detecting identifiable features is shown.

[0136] Figure 14A An exemplary embodiment of a system for detecting identifiable features is shown.

[0137] Figure 14BAn exemplary embodiment of a system for detecting identifiable features is shown.

[0138] Figure 14C An exemplary embodiment of a system for detecting identifiable features is shown.

[0139] Figure 14D An exemplary embodiment of a system for detecting identifiable features is shown.

[0140] Figure 14E An exemplary embodiment of a system for detecting identifiable features is shown.

[0141] Figure 14F An exemplary embodiment of a system for detecting identifiable features is shown.

[0142] Figure 14G An exemplary embodiment of a system for detecting identifiable features is shown.

[0143] Figure 14H An exemplary embodiment of a system for detecting identifiable features is shown.

[0144] Figure 15A An exemplary embodiment of a system for detecting identifiable features is shown.

[0145] Figure 15B An exemplary embodiment of a system for detecting identifiable features is shown.

[0146] Figure 15C An exemplary embodiment of a system for detecting identifiable features is shown.

[0147] Figure 15D An exemplary embodiment of a system for detecting identifiable features is shown.

[0148] Figure 15E An exemplary embodiment of a system for detecting identifiable features is shown.

[0149] Figure 15F An exemplary embodiment of a system for detecting identifiable features is shown.

[0150] Figure 15G An exemplary embodiment of a system for detecting identifiable features is shown.

[0151] Figure 15H An exemplary embodiment of a system for detecting identifiable features is shown.

[0152] Figure 15I An exemplary embodiment of a system for detecting identifiable features is shown.

[0153] Figure 15JAn exemplary embodiment of a system for detecting identifiable features is shown.

[0154] Figure 15K An exemplary embodiment of a system for detecting identifiable features is shown.

[0155] Figure 15L An exemplary embodiment of a system for detecting identifiable features is shown.

[0156] Figure 15M An exemplary embodiment of a system for detecting identifiable features is shown.

[0157] Figure 15N An exemplary embodiment of a system for detecting identifiable features is shown.

[0158] Figure 16A An exemplary embodiment of a system for detecting identifiable features is shown.

[0159] Figure 16B An exemplary embodiment of a system for detecting identifiable features is shown.

[0160] Figure 16C An exemplary embodiment of a system for detecting identifiable features is shown.

[0161] Figure 16D An exemplary embodiment of a system for detecting identifiable features is shown.

[0162] Figure 16E An exemplary embodiment of a system for detecting identifiable features is shown.

[0163] Figure 16F An exemplary embodiment of a system for detecting identifiable features is shown.

[0164] Figure 16G An exemplary embodiment of a system for detecting identifiable features is shown.

[0165] Figure 16H An exemplary embodiment of a system for detecting identifiable features is shown.

[0166] Figure 16I An exemplary embodiment of a system for detecting identifiable features is shown.

[0167] Figure 16J An exemplary embodiment of a system for detecting identifiable features is shown.

[0168] Figure 16K An exemplary embodiment of a system for detecting identifiable features is shown.

[0169] Figure 16LAn exemplary embodiment of a system for detecting identifiable features is shown.

[0170] Figure 16M An exemplary embodiment of a system for detecting identifiable features is shown.

[0171] Figure 16N An exemplary embodiment of a system for detecting identifiable features is shown.

[0172] Figure 17A An exemplary embodiment of a system for detecting identifiable features is shown.

[0173] Figure 17B An exemplary embodiment of a system for detecting identifiable features is shown.

[0174] Figure 17C An exemplary embodiment of a system for detecting identifiable features is shown.

[0175] Figure 17D An exemplary embodiment of a system for detecting identifiable features is shown.

[0176] Figure 17E An exemplary embodiment of a system for detecting identifiable features is shown.

[0177] Figure 17F An exemplary embodiment of a system for detecting identifiable features is shown.

[0178] Figure 17G An exemplary embodiment of a system for detecting identifiable features is shown.

[0179] Figure 17H An exemplary embodiment of a system for detecting identifiable features is shown.

[0180] Figure 17I An exemplary embodiment of a system for detecting identifiable features is shown.

[0181] Figure 17J An exemplary embodiment of a system for detecting identifiable features is shown.

[0182] Figure 17K An exemplary embodiment of a system for detecting identifiable features is shown.

[0183] Figure 17L An exemplary embodiment of a system for detecting identifiable features is shown.

[0184] Figure 17M An exemplary embodiment of a system for detecting identifiable features is shown.

[0185] Figure 17NAn exemplary embodiment of a system for detecting identifiable features is shown.

[0186] Figure 18A An exemplary embodiment of a system for detecting identifiable features is shown.

[0187] Figure 18B An exemplary embodiment of a system for detecting identifiable features is shown.

[0188] Figure 18C An exemplary embodiment of a system for detecting identifiable features is shown.

[0189] Figure 18D An exemplary embodiment of a system for detecting identifiable features is shown.

[0190] Figure 18E An exemplary embodiment of a system for detecting identifiable features is shown.

[0191] Figure 18F An exemplary embodiment of a system for detecting identifiable features is shown.

[0192] Figure 18G An exemplary embodiment of a system for detecting identifiable features is shown.

[0193] Figure 18H An exemplary embodiment of a system for detecting identifiable features is shown.

[0194] Figure 18I An exemplary embodiment of a system for detecting identifiable features is shown.

[0195] Figure 18J An exemplary embodiment of a system for detecting identifiable features is shown.

[0196] Figure 18K An exemplary embodiment of a system for detecting identifiable features is shown.

[0197] Figure 18L An exemplary embodiment of a system for detecting identifiable features is shown.

[0198] Figure 18M An exemplary embodiment of a system for detecting identifiable features is shown.

[0199] Figure 18N An exemplary embodiment of a system for detecting identifiable features is shown.

[0200] Figure 19A An exemplary embodiment of a system for detecting identifiable features is shown.

[0201] Figure 19BAn exemplary embodiment of a system for detecting identifiable features is shown.

[0202] Figure 19C An exemplary embodiment of a system for detecting identifiable features is shown.

[0203] Figure 19D An exemplary embodiment of a system for detecting identifiable features is shown.

[0204] Figure 19E An exemplary embodiment of a system for detecting identifiable features is shown.

[0205] Figure 19F An exemplary embodiment of a system for detecting identifiable features is shown.

[0206] Figure 19G An exemplary embodiment of a system for detecting identifiable features is shown.

[0207] Figure 19H An exemplary embodiment of a system for detecting identifiable features is shown.

[0208] Figure 19I An exemplary embodiment of a system for detecting identifiable features is shown.

[0209] Figure 19J An exemplary embodiment of a system for detecting identifiable features is shown.

[0210] Figure 19K An exemplary embodiment of a system for detecting identifiable features is shown.

[0211] Figure 19L An exemplary embodiment of a system for detecting identifiable features is shown.

[0212] Figure 19M An exemplary embodiment of a system for detecting identifiable features is shown.

[0213] Figure 19N An exemplary embodiment of a system for detecting identifiable features is shown.

[0214] Figure 20A An exemplary embodiment of a system for detecting identifiable features is shown.

[0215] Figure 20B An exemplary embodiment of a system for detecting identifiable features is shown.

[0216] Figure 20C An exemplary embodiment of a system for detecting identifiable features is shown.

[0217] Figure 20DAn exemplary embodiment of a system for detecting identifiable features is shown.

[0218] Figure 20E An exemplary embodiment of a system for detecting identifiable features is shown.

[0219] Figure 20F An exemplary embodiment of a system for detecting identifiable features is shown.

[0220] Figure 20G An exemplary embodiment of a system for detecting identifiable features is shown.

[0221] Figure 20H An exemplary embodiment of a system for detecting identifiable features is shown.

[0222] Figure 20I An exemplary embodiment of a system for detecting identifiable features is shown.

[0223] Figure 20J An exemplary embodiment of a system for detecting identifiable features is shown.

[0224] Figure 20K An exemplary embodiment of a system for detecting identifiable features is shown.

[0225] Figure 20L An exemplary embodiment of a system for detecting identifiable features is shown.

[0226] Figure 20M An exemplary embodiment of a system for detecting identifiable features is shown.

[0227] Figure 20N An exemplary embodiment of a system for detecting identifiable features is shown.

[0228] Figure 21A and 21B An exemplary embodiment of a plurality of thermoregulatory measurements of a subject over a period of time is shown, wherein: Figure 21A The data shown in the Figure 21B The data shown in are represented as space-filling hexagons to facilitate point-to-point distance calculations.

[0229] Figure 22A 、 22B , 22C, 22D, 22E, 22F, 22G, 22H, 22I, 22J, 22K, 22L, 22M, 22N, and 22O show exemplary embodiments of a plurality of thermoregulatory measurements categorized by a subject over a fifteen day period.

[0230] Figure 23An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a subject over a time period defined as one month is shown.

[0231] Figure 24 An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a subject over a time period defined as one month is shown.

[0232] Figure 25 An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a subject over a time period defined as one month is shown.

[0233] Figure 26 An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a subject over a time period defined as one month is shown.

[0234] Figure 27 An exemplary embodiment of a plurality of thermoregulatory measurements for three subjects over a time period defined as one day is shown.

[0235] Figure 28 An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a plurality of individuals is shown, plotted as a function of a combination of the plurality of thermoregulatory elasticity scores and a plurality of other biometric measurements.

[0236] Figure 29 An exemplary embodiment of a plurality of thermoregulatory elasticity scores for a plurality of individuals is shown, plotted as a function of a combination of the plurality of thermoregulatory elasticity scores and a plurality of other biometric measurements. DETAILED DESCRIPTION

[0237] All patents, patent applications, and other publications cited herein, including all sequences disclosed in such references, are expressly incorporated herein by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference. The relevant portions of all cited documents are incorporated herein by reference in their entirety for the purposes indicated by the context in which they are cited. However, the citation of any document should not be construed as an admission that such document is prior art with respect to the present disclosure.

[0238] The generation, analysis, and use of data related to the health of biological systems have been explored. More specifically, the use of sensors and sensor combinations to capture data related to the health of biological systems has been explored. Health can refer to the resilience (adaptability) of a system, primarily expressed through its ability to sustain or achieve some core function. To assess the health of a system, emergent factors of the system can be interpreted.

[0239] The Scholander-Irving model describes how resting metabolism changes in endothermic, homeothermic animals across a range of ambient temperatures. Per Scholander and Laurence Irving were interested in how warm-blooded birds and mammals maintain their body temperature. They discovered that these birds and mammals maintain their body temperature by balancing their metabolic heat production with their heat loss to the environment.

[0240] However, humans may have limited knowledge of their own health capabilities, health status, disease states, overall health status, etc. This limited understanding of these areas may only be achieved through the use of sophisticated physiological measurement tools that are accessible to a limited number of people.

[0241] definition

[0242] As used herein, "analysis" refers to any description of the characteristics or features of any observed sequence of information. Types of analysis include, but are not limited to: analysis of raw measurements, e.g., the numerical values ​​of raw measurements can be used directly as features; resampled measurements, e.g., a set of raw measurements can be grouped and represented by the group mean or other group statistic; distribution representation of measurements, e.g., the distribution of a set of measurements can be represented by regularly spaced boxes or irregular boxes that have been determined by some other process (e.g., Gaussian mixture model); statistical tests on multiple sets of measurements, such as the Hartigan DIP multimodal test or stationarity test, which can be used to detect changes over time; parameters of fitted physical models, such as the three-compartment model of body heat content and its extensions, or the hemodynamic parameters of the human circulatory system; parameters of general mathematical models, e.g., parameters that cannot be reduced to any simple parameters of the physical model, and parameters that may include non-physical control parameters that summarize the structure of the data set, such as the bifurcation parameters of the conjugate logistic map and the eigenvalues ​​of the Hessian matrix of the "sloppy" physical model fit.

[0243] " biological system " used in this article refers to any network of biological related entities. In the broadest sense, a biological system is any chemical reaction network of a persistent non-equilibrium configuration that exists in the form of its own equipment. Biological systems include and span different scales, and determine different structures according to the properties of the biological system. Examples of large-scale biological systems include, for example, microbial colonies, homogeneous colonies of similar organisms living together (for example, cell cultures or human colonies), heterogeneous biological colonies living in a single ecosystem, biological networks. Examples of smaller-scale biological systems include single organisms, for example, single mammals (such as humans), organs or tissue systems, organelle systems, or artificial life systems in such organisms.

[0244] As used herein, a "data stream" refers to a series of digitally encoded coherent signals (data packets or data packets) used to send or receive information being transmitted. A data stream can be a set of information extracted from a data provider and can contain, for example, a series of ordered lists of elements (representing different signal components) and an associated sequence of time stamps.

[0245] As used herein, "disease" refers broadly to any condition that causes pain, dysfunction, suffering, or death to a patient. Thus, a disease can include one or more injuries, disabilities, disorders, syndromes, infections, isolated symptoms, abnormal behaviors, and atypical changes in structure and function. Disease affects a biological organism not only physically but also mentally. Thus, when a person becomes ill, contracting the disease and living with the disease may change that person's perspective on life. Examples of diseases include those identified and classified in the World Health Organization's tenth revised International Statistical Classification of Diseases and Related Health Problems (ICD-10). Diseases that can affect humans include: infectious and parasitic diseases, tumors, diseases of the blood and hematopoietic organs, disorders of the immune mechanism, endocrine diseases, nutritional diseases, metabolic diseases, mental and behavioral disorders, diseases of the nervous system, diseases of the eyes and appendages, diseases of the ears and mastoid process, diseases of the circulatory system, diseases of the respiratory system, diseases of the digestive system, diseases of the skin and subcutaneous tissue, diseases of the musculoskeletal system and connective tissue, diseases of the genitourinary system, diseases associated with pregnancy, childbirth and the postpartum period, diseases originating in the perinatal period, congenital malformations, deformations and chromosomal abnormalities, as well as the consequences of injuries, poisoning and external causes.

[0246] As used in this paper, “dissonance” refers to any unusual or anomalous subsequence in a time series.

[0247] As used herein, "energy expenditure" refers in the most general sense to a parameter that measures heat or work in a biological system. "Energy expenditure" also refers to the free energy expenditure that produces entropy (irreversible) to drive adaptive tasks within a biological system. Energy expenditure is largely irreversible (generating entropy) and therefore represents energy that cannot be used for other tasks. "Energy homeostasis" or "homeostatic control of energy balance" as used herein refers to the biological process involving the coordinated homeostatic regulation of food intake (energy inflow) and energy expenditure (energy outflow).

[0248] As used herein, "emergent factors" or "emergent properties" refer to properties that are not present in a part of a system, or that can be readily inferred from a detailed inventory and analysis of the various parts contained within the system. These properties can be revealed by events, deviations from the norm, or other time-dependent characteristics of some measurable parameter of the system. Emergent properties can be observed directly or indirectly. Examples of emergent properties include: acid-base affinity, electrical conductivity, solvation ability, ion mobility, redox potential, ligand association, hydration, electrolysis, thermal conductivity, heat capacity, thermal absorptivity, adhesion, cohesion, transparency, turbidity, incompressibility, polarity, dipole, dipole moment, diamagnetism, liquidus voltage range, liquidus temperature range, abundance and morphology, energy flux, momentum, particles or other substances. Emergent factors also include thermoregulation and heat dissipation, which can be absolute static values ​​for heat dissipation or periodic functions, such as the diurnal cycle for heat dissipation.

[0249] As used herein, "feature" refers to any descriptive aspect, characteristic, trait, quality, feature, or property of a sequence, subsequence, or information data. Examples of features include, but are not limited to: disorder, repetition, predictability, spiral, meandering, rotation, orbit, dense / diffuse, symmetric / asymmetric, regular / irregular / intermittent, periodic / aperiodic, cyclical, similar / dissimilar, dynamic / static, rate of change, direction of change, curvature, sequence, state transition, anomaly / outlier, interruption / break, oscillation / persistence, damped / undampened, increase / decrease, improvement / decline, intersecting / non-intersecting, linear / non-linear, homogeneous / diverse, monotonic / polytonic, serial / disordered, balanced / unbalanced, long / short, range, mode / median / mean / standard deviation, balanced / unbalanced, stable / unstable, controlled / uncontrolled, homeomorphic / isomorphic, unimodal / multimodal, bounded / unbounded, trend, exceeding / not exceeding a threshold value, rise / fall, growth / shrinkage, acceleration / deceleration, constant / fluctuation, peak / valley, highest point / lowest point, asymptotic, abrupt, steep / flat, logistic / polynomial mapping, discrete / continuous / interval / discontinuous, proportion, gain / loss, energy / active / inactive, complexity / simplicity, attractor / repeller, state, state transition, curve, manifold, trajectory, expansion / deflation, fractal, momentum, iteration, dissipation / evolution, presence / absence, perturbation, change / invariance, finite / infinite, convergence / divergence, speed, derivative / integral, exponent, minimum / maximum, forward / reverse / inverse, pulse, coalescence, saturation / unsaturation, gain, gradient, deep / shallow, bifurcation / splitting, point / line / surface, early / late, and distribution / grouping.

[0250] As used in this article, “forecast” refers to any prediction of future data points in a time series based on what happened before that future data point.

[0251] As used in this article, “health” refers to the baseline functioning of a biological system, which can also be called homeostasis. Health is more than the absence of disease, as health is a positive state independent of disease. Health is related to the ability of a biological system or organism to successfully adapt to various challenges without significant loss of function. For example, a physiologist may describe health as the adequacy of a certain form of stored energy, called physiological reserve, which is the body's ability to actively respond to stress. As another example, a physicist may describe health as the ability to absorb, transform, and dissipate energy to maintain survival. As another example, a cell biologist may describe health as a baseline state of homeostasis, which is the ability of a cell or tissue to self-regulate. As another example, a biochemist may describe health as the control of anabolic and catabolic reactions in metabolic networks that are critical to biological function.

[0252] As used in this article, “health capacity” refers to the resilience (adaptability) of a system, primarily expressed through its ability to sustain or achieve some core functions. The adjectives associated with high or low health capacity are “robust” and “frail,” respectively. Low health capacity, or “frail,” increases the risk of illness or injury and reduces the ability to withstand external stress. Disease impairs function, leading to a decline in health capacity. High health capacity, or “robust,” reduces the risk of injury and improves the ability to perform and withstand external stress. Early interception of disease can preserve and maintain health capacity, and careful management of health capacity can prevent disease. Health capacity can be thought of as the correlation between the state or energy budget and the function of a biological system, defining the ability of a biological system to sustain. Health capacity can be composed of several quantities that are not necessarily comparable in the same way or reduced to a single score. Data analysis can be used to discover the relationship between raw measurements and abstract health capacity scores. Dimensionality reduction or machine learning methods can be used to obtain health capacity scores based on raw measurement time series data and predict adaptation and health outcomes.

[0253] The “health capability rule” used in this paper refers to the minimum set of attributes that confer the “energy budget” required for “health capability”.

[0254] As used herein, "homeostasis" refers to the processes and mechanisms that regulate the internal environment of a biological system, generally to limit changes in state and / or maintain a stable state. An example of a homeostatic mechanism at the organismal level is sweating, which is used to reduce body temperature. An example of a homeostatic mechanism at the biochemical and cellular level is redox control and its regulation of metabolism.

[0255] As used herein, "infection" refers to the invasion of a biological system (typically, an organism) by one or more pathogens (or pathogenic bacteria) that are not usually associated with the biological system. Pathogens are usually pathogens that cause disease. Infection also includes the reproduction and proliferation of pathogens, as well as the response of the host biological system or organism. Infection also includes the production of toxins by pathogens or as a proximal cause of pathogens. Infectious diseases, sometimes also referred to as "communicable diseases" or "infectious diseases", are disease states caused by infection. Pathogenic bacteria include, but are not limited to, viruses and related pathogens, such as viroids and prions, bacteria, and fungi. Fungi can be further classified into, for example, Ascomycetes, including yeasts (e.g., Candida), filamentous fungi (e.g., Aspergillus), Pneumocystis and dermatophytes; Basidiomycetes, including Cryptococcus, which is pathogenic to humans, can be further classified into, for example, single-cell organisms (including, for example, malaria, Toxoplasma, Babesia), large parasites (including helminths or intestinal worms), such as nematodes, such as parasitic roundworms and pinworms, tapeworms (tapeworms), and trematodes (trematodes, such as schistosomes). Arthropods such as ticks, mites, fleas, and lice can also cause human diseases, which are conceptually similar to infections. The invasion of an animal body (e.g., a human body) by large parasites can also be referred to as an infestation, but are considered herein to be a form of infection.

[0256] As used herein, "inflammation" refers to a specific, universal set of biological responses of body tissues to stimuli (such as pathogens, damaged cells, or irritants). Inflammation (and related states, pre-inflammation) is a response involving immune cells, blood vessels, and molecular mediators that is at least partially used to eliminate the initial cause of cell damage, clear necrotic tissue damaged by the original injury, and initiate tissue repair. Symptoms of inflammation include fever, pain, redness, swelling, and loss of function. Compared to adaptive immunity to specific pathogens, inflammation can be considered an innate immune mechanism. Inflammation can be divided into acute or chronic. Acute inflammation is the body's initial response to stimulation and can be achieved by increasing the movement of plasma and white blood cells (especially granulocytes) from the blood into damaged tissues. A series of biochemical events allow the inflammatory response to spread and mature, involving the local vascular system, immune system, and various cells within the damaged tissue. Chronic inflammation, commonly referred to as long-term inflammation, can lead to a gradual shift in cell types (such as monocytes) at the site of inflammation, characterized by the simultaneous destruction and repair of tissues.

[0257] As used herein, "metabolism" refers to the conversion of energy by converting chemicals and energy into cellular components (anabolism) and breaking down organic matter (catabolism). Organisms require energy to maintain internal tissues (homeostasis) and to produce other phenomena associated with life.

[0258] As used herein, "modeling" refers to any descriptive representation or understanding of the processes or operations of a biological system that mimics real-world processes or operations.

[0259] As used herein, a "motif" refers to any repeated informative subsequence.

[0260] As used herein, "novel subsequence" refers to any emerging motif that is both novel and evolving relative to the historical distribution of informative sequences.

[0261] As used herein, "oncogenesis" refers to the development of cancer, i.e., the transformation of normal cells into cancer cells, also known as "tumorigenesis" or "carcinogenesis." This process is characterized by changes at the cellular, genetic, and epigenetic levels, as well as abnormal cell division. DNA mutations and epimutations disrupt the processes involved in programming and regulating the normal balance between proliferation and programmed cell death.

[0262] As used herein, a "response" refers to an action or change in a biological system caused by an external stimulus. Reactions can take many forms. For example, in a single-celled organism, a response might be contraction due to exposure to a chemical in the environment. Another example might be a complex set of responses involving all the senses of a multicellular organism. Reactions are often expressed in terms of movement; for example, plant leaves turning toward the sun (phototropism) and chemotaxis.

[0263] As used in this paper, a “shape subsequence” refers to any small subsequence in an information sequence that can indicate the state of a system.

[0264] As used herein, a "fragment" refers to any subsequence representing an information sequence.

[0265] General criteria for identifying and selecting emergent factors

[0266] Identify and select emergent factors or emergent properties for measurement based on various criteria. In general, emergent factors that can be measured directly are preferred over those that can only be measured indirectly. Less invasive techniques for measurement (direct or indirect) are preferred over more invasive techniques. Preference is given to reliable measurements that relate to a single emergent factor rather than multiple emergent factors.

[0267] General Exemplary Embodiments

[0268] The technology disclosed in this disclosure can provide a deep understanding of the unique signatures of one or more living systems or groups of living systems, thereby understanding the health capacity of such living systems. For example, the technology allows the measurement of the emergent property "heat dissipation", measured in absolute and / or periodic values. The absolute value of heat dissipation can indicate or reflect energy consumption. The absolute value of heat dissipation can indicate or reflect insight into metabolic rate. The periodicity of heat dissipation can provide a deeper understanding of health capacity. The periodicity of heat dissipation can be a diurnal periodicity (i.e., a period of approximately 23 hours to 25 hours), a period shorter than the diurnal periodicity (e.g., a period of approximately 12, 14, 16, 18 or 20 hours), or a period longer than the diurnal periodicity (e.g., every 2, 3, 4, 5 or 6 days, every week, or approximately monthly or 28-day, lunar or annual cycles). Any such heat dissipation periodicity can be used as or reflect a unique signature of a living system with a standard, acceptable health capacity. Deviations from this standard, acceptable heat capacity periodicity can indicate or reflect substandard or unacceptable health capacity.

[0269] In terms of health capacity, "presymptomatic disease" as used herein refers to a process in which health capacity is depleted due to a metabolic task that is to compensate for environmental stress, with the ultimate result being disease and loss of function. This decline in health capacity can be detected as abnormal energy consumption related to compensation or as a more general abnormal energy marker. This state of low or reduced health capacity puts an individual at higher risk for overall loss of function, not just due to the initial stress, or more specifically, in a state of overall susceptibility to disease or infection. In addition, "symptomatic disease" as used herein refers to a state of impaired function, or more specifically, a disease state or a state in which an organism is infected, such as by a viral pathogen. Current methods, exemplified by the precision medicine paradigm, use symptoms as indicators of disease (as shown in Figures 1 and 2). Various aspects of the presently disclosed invention provide systems, devices, and methods for quantifying more comprehensive health indicators, such as measuring and assessing "health capacity" through static or dynamic measurements to assess and improve health capacity, and identifying presymptomatic changes in health capacity for early detection of disease, or more specifically, infection (e.g., as shown in Figures 2 and 3). FIG4 illustrates an embodiment describing a learning strategy for learning health capability rules using energy measurements and annotations.

[0270] In one embodiment, health relates to the ability of a biological system or organism to successfully adapt to various challenges without significant loss of function. For example, a physiologist might describe health as the adequacy of a certain form of stored energy, called physiological reserve, which is the body's ability to proactively respond to stress. Another example is a physicist who might describe health as the ability to absorb, transform, and dissipate energy to maintain survival. Another example is a cell biologist who might describe health as a baseline state of homeostasis, the ability of a cell or tissue to self-regulate. Another example is a biochemist who might describe health as the control of anabolic and catabolic reactions in metabolic networks that are critical for biological function.

[0271] Each of the above perspectives or understandings of health is appropriate in its context, whether from a physiologist's, physicist's, cell biologist's, or biochemist's perspective, and is helpful in applying the disclosed technology. More specifically, the disclosed technology reconciles the above perspectives and understandings and adopts a new concept of health in which high health capacity and the absence of disease coexist, i.e., function and health. In one embodiment, health capacity reveals how to quantify health by measuring physical properties of homeostasis. That is, health can be quantified as the health capacity of a biological system. Other aspects of the disclosed technology relate to technologies for developing a series of indicators that accurately measure the state of a biological system (e.g., including the health status of a biological system). These technologies acquire and process information at a sufficiently high resolution on an operational time scale.

[0272] Other aspects of the disclosed technology include: detecting features of emergent properties of biological systems; automatically identifying and detecting emergent properties of biological systems to improve life; action plans for acquiring, maintaining, and promoting health; allowing faster learning and interpretation of complex biology from new health accuracy data streams; allowing frictionless collection, analysis, and decision support of subjects' health status; developing scalable disease interception solutions; reducing false positives in diagnosis; finding the cause of disease; preventing further progression of disease; diagnosing disease early; and explaining the development of symptoms. In some embodiments of the disclosed technology, properties of living systems and their physicochemical properties are measured; these properties capture the emergent properties of living systems. In other embodiments, the disclosed technology focuses on emergent properties that lead to the boundary between physical systems and biological systems. Therefore, the disclosed technology is applicable to synthetic biology and artificial biological systems, such as primitive cells or industrial biological systems.

[0273] On the other hand, the disclosed technology relates to methods for detecting identifiable features or patterns from a range of health indicators of a subject. In some embodiments, these methods are integrated into the Internet of Things (IoT) architecture and infrastructure. In some embodiments, these methods detect metabolic features or patterns at the cellular scale. These measurements that can produce features can be intermittent, regular, or continuous. In some embodiments, these methods also include streaming these indicator arrays to the cloud, applying machine learning to "quantify metabolism," and detecting changes before disease symptoms appear. In some embodiments, these methods measure discrete physical parameters of biological systems non-invasively with the resolution and frequency to measure cellular physiology and homeostasis in real time. In some embodiments, these methods define and quantify a quantity called health capacity of a subject based on the physical properties, energy, and information measured on the subject, which is related to the resilience of the subject's homeostasis.

[0274] The disclosed technology provides actionable information that enables the health of biological systems to be improved. In preferred embodiments, individuals gain insights into their own health that were previously unavailable. This actionability allows for observation of responses to specific stimuli in specific biological systems and allows for changes or influences to be made to future stimuli. For example, an individual or healthcare professional can use the disclosed technology to change the health of a biological system, such as a patient or the individual themselves. This actionability also allows for a better understanding of the determinants that have the greatest impact on health, such as sleep patterns and duration, nutrition (including diet, supplements, medications, etc.), exercise (neuromuscular input, type, duration, periodicity, etc.), and other lifestyle decisions or adverse factors (such as pollution) that affect health. In preferred embodiments, the disclosed technology allows individuals to become effective agents of their own health and also allows for the ability to better plan or prepare for action based on an individual's health status.

[0275] The disclosed technology provides the ability to compare identifiable characteristics detected in an individual with similar or different identifiable characteristics detected in a larger population.

[0276] The disclosed technology provides automated and automatable methods, addressing a major source of healthcare inefficiency: manual testing and interpretation. Currently, healthcare testing and interpretation are typically centralized, with interpretation of such tests often performed manually by healthcare professionals. Both tasks are costly and inefficient. The disclosed technology allows for the digitization of health data and interpretation associated with health capabilities. This digitization leverages the full strengths of the existing IoT ecosystem and cloud computing.

[0277] The disclosed technology provides scientists and healthcare professionals with systems and methods for optimizing health by enhancing health capabilities. Current technology no longer views health as an elusive concept, but rather as a system with measurable tasks or goals that can be quantified, concrete, or modular.

[0278] The disclosed technology allows for quantification of health as health capabilities and detection of changes over time, including changes in the amplitude or frequency of circadian rhythms or other cyclical components. Unlike the current paradigm, which considers the absence of health as the presence of symptomatic disease, the disclosed technology provides a substantially continuous measurement of health, quantifies health declines, and detects changes in health before symptomatic disease occurs. Thus, the disclosed technology allows individuals, public health professionals, and / or medical professionals to take corrective actions with more accurate and reliable information to prevent the onset of disease, reduce morbidity, reduce mortality, and reduce the cost of care.

[0279] The disclosed technology can also improve the efficiency of currently available precision medicine tools by reducing the rate of false or incorrect diagnostic findings using simple, basic and translatable energy usage indicators ("energy signatures"), thereby reversing the trend of inefficiency according to Eroom's Law.

[0280] In some aspects, the disclosed technology relates to methods for detecting identifiable features by acquiring physical, chemical, and biological measurements of emergent properties of biological and non-biological systems; and systems or technology platforms for processing, storing, transmitting, analyzing, compiling, distributing, and displaying emergent property measurement data to quantify, predict, control, maximize, design, and engineer complex adaptive biological and non-biological systems.

[0281] In some embodiments, the biological system can be a eukaryotic, prokaryotic or archaeal organism (e.g., bacteria), a germ cell or red blood cell, a white blood cell, a cell derived from a tissue or organ (e.g., a muscle cell), or a simple or complex multicellular organism (e.g., an apple or a human body), or engineered cells and / or collections thereof to form an interactive ecosystem in combination with non-biological essential chemical materials or energy sources.

[0282] In some embodiments, the non-biological system can be an engineered non-biological system that resembles a biological system but lacks genetic material (protocells), or any other engineered or biomimetic-based design system or semi-synthetic system.

[0283] In some embodiments, the disclosed technology also relates to using these measures to measure the state of existence and the ability to persist in biological and non-biological systems. The ability of a biological or non-biological system to exist or persist is related to the "healthiness" of the system.

[0284] Advantages of the disclosed technology include the ability to quantify, predict, control, maximize, engineer, and design biological or non-biological systems based on measurements of physical, chemical, and biological parameters related to resilience (adaptability), which is primarily indicated by the ability to sustain or achieve some core function.

[0285] In some embodiments, the disclosed technology also relates to technology platforms and methods for acquiring physical, chemical, and biological parameters, including wearable, implantable, embedded, or otherwise coupled devices. Once these measurements are taken, they can be stored, quantified, analyzed, compiled, distributed, and displayed to quantify, predict, control, maximize, engineer, and design biological systems. Measures of health capabilities can also be analyzed along with measures of other non-emergent properties to improve the ability of measurement technologies and learning platforms to quantify, predict, control, maximize, engineer, and design biological or non-biological systems.

[0286] In the case of single-cell eukaryotic, prokaryotic, or archaeal organisms, the disclosed technology allows for quantification, prediction, and maximization of function. For example, in the case of germ cells, the disclosed technology allows for quantification of fitness to maximize fertility for in vivo or in vitro fertilization. In bacteria, yeast, or human cells, the disclosed technology can be used to quantify fitness; in the case of industrial or synthetic biology, the disclosed technology can be used for molecular synthesis. In the case of non-pathogenic enteric bacteria, the disclosed technology can be used to maximize the function of the microbiome.

[0287] In the case of multicellular eukaryotic organisms, the disclosed technology allows for quantification, prediction, and maximization of function. For example, in humans, the disclosed technology enables measurement and maximization of health status and diagnosis and / or pre-symptomatic diagnosis of disease, as well as design of methods for treatment or interception of disease, where the disease can be infectious, cancer, toxic, iatrogenic, or metabolic, and the determinants of health are food / nutrition, sleep, exercise, neuromuscular activation, and lifestyle changes such as smoking, inactivity, and addiction.

[0288] In certain embodiments, the advantages of the disclosed technology may also include applications in non-human multicellular eukaryotic organisms, such as in agricultural systems, such as plant and animal farming, where the disclosed technology can maximize food production and / or reduce abiotic or biotic stress.

[0289] In certain embodiments, the advantages of the disclosed technology can also include application to simple ecosystems of species and chemical resources. For example, in a biological system of two or more species and one or more resources, the disclosed technology maximizes the functional interdependencies between these species and resources. For example, if one of the species is human, the technology can maximize human functional parameters such as sleep, activity, physical or cognitive performance, and disease prevention.

[0290] In certain embodiments, the advantages of the disclosed technology can also include applications in complex ecosystems. For example, in a biological system with many species and many resources, the disclosed technology maximizes the functional interdependencies between these species and resources. If the complex system is a farm, the disclosed technology can maximize the functionality of the ecosystem, such as sustainability.

[0291] In certain embodiments, the advantages of the disclosed technology may also include applications in synthetic biology, such as in eukaryotic and prokaryotic cells. In these biological systems, the disclosed technology can be designed and engineered to maximize functionality; for example, the synthesis of proteins, lipids, or small molecules, or the ability to maintain viability under abiotic or biotic stress conditions.

[0292] In certain embodiments, the advantages of the disclosed technology may also include applications in biostatistics. For example, the disclosed technology can identify biological systems that do not rely on or bind genetic material.

[0293] In certain embodiments, the advantages of the disclosed technology can also include applications in non-biological systems. For example, the disclosed technology can design and engineer a non-living system that is similar to a biological system but lacks genetic material (a "protocell"). Such a protocell can be used to learn and / or perform work, where "work" can be understood as any output other than simply heat production.

[0294] In certain embodiments, the advantages of the disclosed technology may also include application in biological systems to quantify biological time, i.e., "healthspan." For example, the disclosed technology can be used to calculate the theoretical and actual lifespan of a biological system and, in combination with these applications, maximize functional or healthspan.

[0295] Generally, body temperature regulation consists of two main components: heat production and heat dissipation. Healthy homeostasis requires a balance between these two components. A dynamic equilibrium exists where the energy demands and rates of change of these two components remain roughly equal over a wide range. By continuously measuring both components and analyzing their temporal consistency, a system can assess health in greater detail than by measuring only one component.

[0296] Example

[0297] In certain embodiments, heat flux can be conceptually plotted as a function of ambient temperature. Those skilled in the art will appreciate that visual multidimensional plots do not need to be physically generated; rather, the computations and analysis behind such plots can be directly performed. This approach allows for understanding how internal and external signals reflect a subject's health. In some embodiments, internal and external signals can be analyzed simultaneously, providing a deeper understanding of the subject's overall health. Heat can be highlighted as an emergent factor. In certain embodiments, systems, methods, and devices can collect and / or generate a data stream that may include multiple heat flux data sets and multiple ambient temperature data sets. In certain embodiments, the heat flux data may include multiple heat dissipation measurements expressed as a function of ambient temperature. In certain embodiments, the systems, methods, or devices may include a processor that receives the data stream. In certain embodiments, the systems, methods, and devices may detect feature or shape subsequences that are associated with and / or correlated to an individual's health status or condition. In certain embodiments, the detected features may represent a state of homeostasis. A state of homeostasis may be represented by a densely populated area within the data stream. This may be an example of a motif detected by the system. In some embodiments, the system may detect a state of homeostasis before or after detecting a novel subsequence. In some embodiments, denser areas of fill within a data stream can indicate that the subject's health state is likely to be maintained at that point in time. In some embodiments, lower density and more dispersed regions of a data stream in the system can indicate a more unstable or unstable subject's thermal system. This can indicate that a new subsequence is forming, which the system can detect. In some embodiments, the system can detect overall features or segments of the collected data by detecting the overall structure of the data. In some embodiments, the system can detect subfeatures or shape subsequences within the overall pattern of the data.

[0298] In some embodiments, when conceptually plotted as heat flux versus ambient temperature, the overall pattern detectable by the system can be a boomerang shape, an L shape, or the like. In some embodiments, the system can identify peaks or turning points in the detected overall shape. The system can detect sub-patterns within the detected overall shape. For example, the system can detect the extent or articulation of turning points or transition points detected within the detected overall shape. In some embodiments, the extent or articulation of the detected turning points can indicate age, health system efficiency, homeostasis, the ability to achieve homeostasis under different circumstances, or the like. For example, the system can detect more defined turning points that can reflect a younger age or better cardiorespiratory fitness of the subject. In some embodiments, the system can detect sub-features located at the ends of the detected overall shape and / or within the detected overall shape. Sub-features can include variability within the data associated with the identifiable feature. For example, the system can detect sub-features that can indicate a subject's ability to withstand cold, a subject's cardiac function, a subject's prognosis, or the like.

[0299] In certain embodiments, the system can detect features associated with a subject's health state. In certain embodiments, the health state may be associated with a stage of health or a response to an infection, disease, or the like. This can be based on the amount of heat a subject stores or dissipates at a given ambient or skin temperature. In certain embodiments, the system can detect identifiable features based on the amount of heat a subject dissipates at a given temperature. In some embodiments, the system can detect identifiable features for various diseases, infections, health-related conditions, and the like. Within each detectable identifiable feature, the system can determine the subject's response to the disease, infection, or health-related condition. Furthermore, the system can predict the subject's future response to the disease, infection, or health-related condition based on the detectable identifiable features. For example, the system can determine whether a subject is recovering from, battling, or responding to a disease. In certain embodiments, the system can detect when a subject transitions between stages of disease response. In some embodiments, detecting transition states allows the subject to understand the timeline of the disease, disease, or condition and to prepare accordingly. In certain embodiments, this understanding can be provided to the subject in a minimally invasive manner without compromising the strength of the data stream signal.

[0300] In certain embodiments, the identifiable characteristic may be the maintenance of homeostasis. This may be where the subject's thermoregulatory system spends the most time. While the system can detect motion, sub-characteristics detected by the system may indicate the maintenance of homeostasis. This can include any increment or change in position over time, regardless of direction, indicating a change in heat flux.

[0301] In certain embodiments, the more data collected, the more representative the detected identifiable features become of a condition, illness, disease, etc. This allows the system to predict future features that the system may detect based on previously identified features in the data stream. The system may also be configured to classify the data stream into a specific category of behavior based on the detected identifiable features.

[0302] In certain embodiments, identifiable features can be generalized to a larger population. For example, an overall pattern in the data can be generalized to a population of subjects with the same or similar disease or condition. Furthermore, for example, a subpattern in the data can be generalized to a larger population to understand how a subject's thermoregulatory system fluctuates over time. In summary, the system can identify anomalies or outliers, thereby providing additional information to the subject. Anomalies can exist in the subject's own features detected by the system, or in the features of a larger population.

[0303] In certain embodiments, a user may use the identifiable features detected by the system in various ways. For example, a user may use the detected identifiable features to detect disease early, which may include determining a patient's nominal heat flux, measuring the patient's current heat flux, and comparing the patient's current heat flux to the patient's nominal heat flux to detect disease. For another example, a user may use the detected identifiable features to recommend thermal regulation guidelines, which may include determining the current phase of the user's menstrual cycle, measuring the user's current heat flux, and comparing the current phase of the menstrual cycle to the current heat flux to determine thermal regulation guidelines. For another example, a user may use the detected identifiable features to determine the readiness of a combatant, which may include determining the current state of a potential combatant, measuring the potential combatant's current heat flux, and comparing the potential combatant's current heat flux to the potential combatant's current state to determine the combatant's readiness.

[0304] For another example, a user may use the detected identifiable features to regulate sleep, which may include determining the user's current circadian rhythm, measuring the user's current heat flux, and comparing the user's current heat flux to the user's current circadian rhythm to regulate the user's sleep. For another example, a user may use the detected identifiable features to determine the user's readiness for conception, which may include determining the user's current stage of the menstrual cycle, measuring the user's current heat flux, and comparing the user's current stage of the menstrual cycle to the current heat flux to determine the user's readiness for conception. For another example, a user may use the detected identifiable features to determine the user's stage of pregnancy, which may include determining the user's current state, measuring the user's current heat flux, and comparing the user's current state to the user's current heat flux to determine the user's pregnancy state.

[0305] For another example, a user may use the detected identifiable features to determine the user's intestinal health status, which may include: determining the user's current digestion stage of at least one food, measuring the user's current heat flux, and comparing the current digestion stage with the current heat flux to determine the user's intestinal health status. For another example, a user may use the detected identifiable features to determine the user's athletic ability, which may include: determining the user's current state of health ability, measuring the user's current heat flux, and comparing the user's current state of health ability with the user's current heat flux to determine the user's athletic ability. For another example, a user may use the detected identifiable features to determine the user's metabolic rate, which may include: determining the user's current muscle mass, measuring the user's current heat flux, and comparing the user's current muscle mass with the user's current heat flux to determine the user's metabolic rate.

[0306] For another example, a user may use the detected identifiable features to determine a syncope event of the user, which may include: determining the user's current physical state, measuring the user's current heat flux, and comparing the user's current physical state with the user's current heat flux to determine an impending syncope event. For another example, a user may use the detected identifiable features to determine the user's health capacity, which may include: determining the user's current quasi-periodic rhythm, measuring the user's current heat flux, and comparing the user's current quasi-periodic rhythm with the user's current heat flux to determine the user's health capacity. For another example, a user may use the detected identifiable features to determine the user's cardiac function efficiency, which may include: determining the user's current cardiac function, measuring the user's current heat flux, and comparing the current cardiac function with the current cardiac flux to determine the user's cardiac function efficiency.

[0307] For another example, a user may use the detected identifiable features to determine the efficiency of their immune system, which may include determining the current state of the user's immune system, measuring the user's current heat flux, and comparing the current state of the user's immune system with the user's current heat flux to determine the efficiency of the user's immune system. For another example, a user may use the detected identifiable features to determine the user's ability to lose weight, which may include determining the user's current weight, measuring the user's current heat flux, and comparing the user's current weight with the user's current heat flux to determine the user's ability to lose weight. For another example, a user may use the detected identifiable features to determine the effectiveness of a medication for treating a disease, which may include determining the current stage of the disease, measuring the user's current heat flux, and comparing the current stage of the disease with the user's current heat flux to determine the effectiveness of the medication for treating the disease.

[0308] For another example, a user may use the detected identifiable features to determine the risk of miscarriage, which may include determining the current stage of pregnancy, measuring the user's current heat flux, and comparing the current stage of pregnancy with the user's current heat flux to determine the risk of miscarriage. For another example, a user may use the detected identifiable features to determine the user's level of sobriety, which may include determining the user's current alcohol consumption, measuring the user's current heat flux, and comparing the user's current alcohol consumption with the user's current heat flux to determine the user's level of sobriety. For another example, a user may use the detected identifiable features to determine the user's rehabilitation regimen, which may include determining the user's current injury stage, measuring the user's current heat flux, and comparing the current injury stage with the user's current heat flux to determine the user's rehabilitation regimen. For another example, a user may use the detected identifiable features to recommend thermal regulation guidelines to the user, which may include determining the user's current menopausal stage, measuring the user's current heat flux, and comparing the current menopausal stage with the current heat flux to determine the thermal regulation guidelines.

[0309] In certain embodiments, subjects are categorized into one of at least two groups: those with positively functioning thermoregulatory systems or those with negatively functioning thermoregulatory systems. In some embodiments, subjects may also fall between these two groups. In other words, the level of function (functionality) of a subject's thermoregulatory system or the efficiency with which the subject's thermoregulatory system operates may fall within a range. In some embodiments, the functionality of a subject's thermoregulatory system may be related to the resilience of the subject's thermoregulatory system. In some embodiments, the functionality of a subject's thermoregulatory system may be based on the subject's health status. For example, the resilience of a subject's thermoregulatory system may be related to the subject's ability to control their thermoregulatory system, the subject's ability to return to a steady state when the thermoregulatory system deviates from homeostasis, or the subject's ability to return to a steady state in an orderly manner or pattern. In other words, there may be multiple thermoregulatory measurements that constitute transitional phases of the thermoregulatory system. When the thermoregulatory system deviates from homeostasis, the thermoregulatory system may be in a transitional phase. Homeostasis can be considered the normal state of a subject's thermoregulatory system. The resilience of a subject's thermoregulatory system may be based on the thermoregulatory system's ability to self-control as it transitions from a normal state to a transitional phase over a period of time. The resilience of the thermoregulatory system can be related to the duration, effective manner, or lack of effective manner for the subject's thermoregulatory system to return to a steady state or normal state. In some embodiments, the manner in which the subject's thermoregulatory state returns to a steady state or normal state can be associated with a phenotype. A phenotype associated with the manner in which the subject's thermoregulatory state returns to a steady state or normal state can allow the use of various biometrics to assess the subject's thermoregulatory system. For example, heart rate, heat flux, skin temperature, etc. can be used to assess the subject's thermoregulatory system.

[0310] In some embodiments, if the inelastic thermoregulatory system remains in a transition state or deviates from a steady state or normal state, it may not return to a steady state or normal state. In some embodiments, the inelastic thermoregulatory system may return to a steady state over an extended period of time. In other words, the inelastic thermoregulatory system may remain in a transition state for an extended period of time. This may mean that the thermoregulatory system is unable to self-control. In some embodiments, the inelastic thermoregulatory system may return to a steady state or normal state in a disordered manner or pattern.

[0311] In some embodiments, the elasticity of the subject's thermoregulatory system is assessed. Assessing the elasticity of the thermoregulatory system can provide a recommendation to the subject. In some embodiments, the recommendation can include recommending that the subject participate in an intervention based on the assessed thermoregulatory elasticity. In some embodiments, a thermoregulatory elasticity score can be generated for the subject over a predetermined time period. In some embodiments, the thermoregulatory elasticity score can be based on a data stream comprising multiple thermoregulatory measurements of the subject. Multiple thermoregulatory measurements can be collected from any of the above-mentioned devices. In some embodiments, the multiple thermoregulatory measurements can include any biometric measurements related to the subject's thermoregulatory system.

[0312] The assessment may include determining whether the need for intervention for the subject is above a predetermined emergency threshold. A recommendation for intervention for the subject may also be generated. In this manner, the recommendation may be formulated based on the thermoregulatory resilience score, the need for intervention, or a combination thereof.

[0313] In some embodiments, the urgency threshold may be related to the urgency with which intervention is required for the subject. For example, the higher the thermoregulatory elasticity score, the less urgent the intervention for the subject. In some embodiments, a predetermined urgency threshold may determine the urgency with which intervention is required for the subject. For example, a subject's thermoregulatory elasticity score may be greater than a predetermined urgency threshold, which may result in an assessment that intervention for the subject is less urgent than intervention for a subject whose thermoregulatory elasticity score is less than a predetermined urgency threshold. In some embodiments, the predetermined urgency threshold may be specific to the subject. For example, the predetermined urgency threshold may be based on the subject's health status or may vary based on the subject's health status.

[0314] In some embodiments, it may be useful to refresh, reanalyze, recalculate, observe, and / or reconfigure health indicators monthly, every three weeks, every 14 days, every 10 days, every 7 days, every 5 days, every 3 days, every 2 days, every 1 day, every day, less than a day, or any interval therebetween. This is because a subject's health status can change over time. The frequency with which health indicators are calculated or observed allows the subject to quantify possible transient phenomena in the subject's health. For example, transient phenomena may include transition phases, or the aforementioned transition or transition states. Similarly, transient phenomena may include the resilience of the subject's thermoregulatory system and its ability to respond to factors that cause the thermoregulatory system to deviate from a steady state or normal state. This ability may be related to the subject's steady-state robustness. In other words, the subject's steady-state robustness may be based on the resilience of the subject's thermoregulatory system. In some embodiments, steady-state robustness may facilitate the identification of patterns within multiple data sets or the characterization of multiple data sets. In some embodiments, the more resilient the subject's thermoregulatory system, the greater the subject's steady-state robustness. In some embodiments, the transition phase may last for a period of time. This period of time may be of any length. For example, the transition period can last for an extended period of time, a non-extended period of time, or a predetermined period of time. In some embodiments, if the transition period lasts for an extended period of time, the transition period may indicate an inelastic thermoregulatory system in the subject. This is because the subject's thermoregulatory system has less control over itself when it deviates from its normal state. In some embodiments, if the transition period lasts for a non-extended period of time, the transition period may indicate an elastic thermoregulatory system in the subject.

[0315] In some embodiments, the evaluation and generation of a recommendation can include alerting a healthcare practitioner that a recommendation has been generated. The healthcare practitioner can be alerted to intervene with the subject if necessary or in accordance with the recommendation.

[0316] In some embodiments, the thermoregulatory elasticity score can be viewed in conjunction with other biometric measurements. This can more likely identify subjects whose health conditions may require or be at risk of treatment or intervention. For example, comparing the thermoregulatory elasticity score with the thermoregulatory elasticity score combined with other biometric measurements can better identify subjects whose health conditions may require or be at risk of treatment or intervention. This is because there is a positive correlation between the elasticity of the subject's thermoregulatory system and the subject's health condition. This correlation can also be supported by other biometric measurements of the subject. In some embodiments, other biometric measurements can be collected from any device capable of sensing and / or collecting biometric measurements.

[0317] In some embodiments, multiple thermoregulatory elasticity scores for multiple subjects can be plotted against a combination of multiple thermoregulatory elasticity scores and multiple other biometric measurements. This combination can be considered a risk level. The lower the risk level, the greater the risk faced by the subject. In some embodiments, by including thermoregulatory elasticity scores and other biometric measurements in the risk level, it is possible to identify subjects whose health conditions are considered to be at risk with a greater probability. For example, such a risk assessment can increase the probability of identifying subjects at risk by approximately 2 to 2.5 times.

[0318] In some embodiments, the risk assessment can be customized to remove at least one outlier that may be included in a combined plot of multiple thermoregulatory elasticity scores and multiple other biometric measurements. The at least one outlier that can be removed can include outliers at the high end of the risk level scale and at the low end of the risk level scale. By removing outliers, the probability of identifying subjects whose health condition is considered to be at risk can be increased by approximately 4 to 5 times.

[0319] In some embodiments, the risk assessment described above can be used to identify serious medical events in frail elderly subjects. For example, the risk of a frail elderly subject can be continuously assessed by continuously collecting multiple biometric measurements and calculating a thermoregulatory resilience score for the frail elderly subject. The risk assessment described above can be used to predict the probability of a medical event occurring. Furthermore, the risk assessment described above can be used to triage outpatient care resources, thereby multiplying the effective capacity of skilled healthcare practitioners, reducing morbidity associated with aging, and lowering associated hospitalization costs by identifying individual health risks before a medical event occurs.

[0320] In some embodiments, the above-described risk assessment can be used to determine medical insurance coverage for young individuals who are considered healthy. For example, young individuals generally require minimal medical care unless a medical event, traumatic injury, and / or unexpected illness occurs. By assessing risk in young individuals as described above, subjects within the young population who are at risk or have physiological risk factors can be identified. By identifying these subjects, the subjects can be divided into subgroups with varying risk profiles. Each subgroup can then be encouraged to perform self-screening to identify subjects within that subgroup who are at higher risk than others.

[0321] In some embodiments, the above-described risk assessment can be used to identify workers or laborers who are at higher risk for heat stroke than others. For example, workers or laborers who work in hot environments are more likely to suffer from heat stroke than others. Generally speaking, a business may set a restriction such that workers or laborers are not allowed to work when the outdoor temperature exceeds a certain temperature threshold. However, some people may be at risk for heat stroke at lower temperature thresholds. This can be an all-or-nothing strategy. By using the above-described risk assessment to identify subjects who are at higher risk for heat stroke than others, targeted work management can be implemented. This can reduce downtime for the business, workers, and / or laborers, and can also reduce costs caused by worker or laborer injuries.

[0322] Figure 1A and Figure 1B An exemplary embodiment of a system detecting identifiable features from a subject's response to LPS injection is shown. Since each figure shows the same or similar identifiable features identified by the system in two different subjects (otherwise healthy subjects), the following description will be made. Figure 1A , but the description also applies to Figure 1B . Figure 1A The thermoregulatory response to the LPS injection can be seen in the figure. As shown in the figure, the system can analyze the data generated by grouping the data into bins with a time period of approximately every 5 minutes. After the LPS injection, the system can detect a decrease in heat flux or heat dissipation. This is because the subject's thermoregulatory system attempts to retain heat due to the LPS injection; by retaining heat, the subject will develop a fever in an attempt to fight the infection. Figure 1A As shown, the system can detect identifiable sub-features associated with LPS injection and / or transition to heat retention. The detected identifiable sub-features can be a downward trend. The system can detect whether the body temperature regulation system continues to retain heat by identifying identifiable features generated by the subject retaining heat. Figure 1A As shown, when the subject's body temperature regulation system releases the heat it previously retained, the system can detect another identifiable sub-feature. The identifiable sub-feature detected can be an upward trend. The system can detect the identifiable feature as dissipating more heat than normal. This is because the subject's body temperature regulation system previously retained more heat than normal and therefore needs to dissipate more heat. Figure 1A As shown, when heat flux is plotted as a function of ambient temperature, the overall identifiable feature can be J-shaped. The overall identifiable feature detected by the system can be created by at least one transition phase before and after each identifiable sub-feature. Figure 1A As further shown, the detected overall identifiable features may be presented in a counter-clockwise direction.

[0323] Figure 2A 、 2B2C show exemplary embodiments of identifiable features detected by the system from the circadian rhythm of a healthy sleep subject during the night. The detected identifiable features can be illustrated by a graph comprising heat flux as a function of ambient temperature. Since each graph shows the same or similar identifiable features identified by the system on three different subjects (otherwise healthy subjects), the following description will be made. Figure 2A , but the description also applies to Figure 2B and Figure 2C As shown in the figure, Figure 1A Similarly, the system can group data points into bins of approximately 5-minute spans. Figure 2A As shown, when the subject is falling asleep, the system can detect an increase in heat retention. The system can detect the identifiable sub-feature as a downward trend, indicating that the subject is falling asleep. When the subject remains asleep, the system can detect the identifiable sub-feature indicating that the subject is sleeping. The identifiable feature can be a group of data points in the lower right quadrant of the figure. When the subject wakes up, the system can detect the identifiable sub-feature indicating that the subject is waking up. The system can detect the identifiable sub-feature as an upward trend, indicating that the subject is releasing previously retained heat. When the subject remains awake, the system can detect the identifiable sub-feature indicating that the subject has woken up. The identifiable feature can be a group of data points in the upper right quadrant. Although the system can detect identifiable sub-features for each stage of the sleep cycle, the system can also detect an overall identifiable feature of the sleep cycle. As shown in the figure, for example, the identifiable feature of the sleep cycle of a healthy person can be an ellipse. In addition, when as Figure 2A When drawn as shown, the ellipse can be rotated counterclockwise.

[0324] Figure 3A 、 3B 3C show exemplary embodiments of identifiable features detected by the system from the circadian rhythm of a subject who sleeps unhealthily at night. The detected identifiable features can be illustrated by a graph comprising heat flux as a function of ambient temperature. Since each graph shows the same or similar identifiable features identified by the system on three different subjects (otherwise considered unhealthy subjects), the following will be described. Figure 3A , but the description also applies to Figure 3B and Figure 3C .like Figure 1A and Figure 2A As shown in , the system can group data points into bins of approximately 5-minute spans. Figure 3AAs shown, when the subject is falling asleep, the system can detect an increase in heat retention. The system can detect a decreasing trend in the identifiable sub-feature, indicating that the subject is falling asleep. When the subject remains asleep, the system can detect an identifiable sub-feature indicating that the subject is sleeping. However, unhealthy subjects cannot regulate their body temperature as well as healthy subjects, as shown in FIG. Figure 2A As shown, the system can detect an identifiable sub-feature that indicates the subject is awake rather than asleep. This results in the identifiable sub-feature being a broad group of data points in the upper left quadrant of the figure. When the subject wakes up, the system can detect an identifiable sub-feature that indicates the subject is waking up. The system can detect the identifiable sub-feature as an upward trend, indicating that the subject is releasing previously retained heat. When the subject remains awake, the system can detect an identifiable sub-feature that indicates the subject has woken up. This identifiable sub-feature can be a group of data points in the upper left quadrant. While the system can detect identifiable sub-features for each stage of the sleep cycle, the system can also detect an overall identifiable feature of the sleep cycle. As shown in the figure, the identifiable feature of the sleep cycle of an unhealthy person can be an inverted triangle. This is because unhealthy subjects cannot retain heat well and therefore release more heat than they can retain.

[0325] Figure 4A 、 4B 4C and 4D show exemplary embodiments of identifiable features detected by the system from the motion of an otherwise considered healthy subject. Figure 4A As shown, the system can detect a discernible feature indicating that the subject is transitioning from sleep to wakefulness. The discernible feature can be identified starting from the lower right quadrant of the graph and moving counterclockwise and showing an upward trend, indicating that the subject is dissipating heat. Figure 4B As shown, the system can detect a discernible feature indicating that the subject is climbing a steep slope. The discernible feature can be a group of data points in the upper left quadrant. This is because the subject's body temperature regulation system can be dissipating heat to maintain body temperature regulation homeostasis. Figure 4C As shown, the system can detect a discernible feature that indicates that the subject is resting after expending energy. This discernible feature can be a group of data points that are widely distributed in the lower right quadrant of the graph. This can indicate that the subject still retains heat after dissipating heat during the process of expending energy. Figure 4D As shown, the system can detect a discernible feature indicating that the subject is expending energy during exercise. The discernible feature can be a cluster of data points in the upper right quadrant of the graph. This can indicate that the subject is dissipating heat to regulate the body's thermoregulatory system during energy expenditure.

[0326] Figure 5A 、 5B , 5C, 5D, 5E, 5F, 5G, 5H, and 5I illustrate exemplary embodiments of identifiable features detected by the system from an inflammatory response in a subject.

[0327] Figure 6A 、 6B , 6C, 6D, and 6E show exemplary embodiments of identifiable features detected by the system from the sleep sequence of an otherwise considered healthy subject.

[0328] Figure 7A 、 7B 7C and 7D show exemplary embodiments of identifiable features detected by the system from the sleep sequence of an otherwise considered healthy subject.

[0329] Figure 8A 、 8B , 8C, and 8D illustrate exemplary embodiments of identifiable features detected by the system from the sleep sequence of an otherwise considered healthy subject.

[0330] Figure 9A 、 9B , 9C, and 9D illustrate exemplary embodiments of identifiable features detected by the system from the sleep sequence of an otherwise considered healthy subject.

[0331] Figure 10A 、 10B 10C illustrate exemplary embodiments of identifiable features detected by the system from the sleep sequence of a subject who is otherwise considered unhealthy.

[0332] Figure 11A 、 11B 11C show exemplary embodiments of identifiable features detected by the system from the sleep sequence of a subject who is otherwise considered unhealthy.

[0333] Figure 12A 、 12B , 12C, 12D, and 12E illustrate exemplary embodiments of identifiable features detected by the system from the sleep sequence of a subject who is otherwise considered unhealthy.

[0334] Figure 13A and 13B An exemplary embodiment of identifiable features detected by the system from menopausal hot flashes in a subject is shown.

[0335] Figure 14A 、 14B , 14C, 14D, 14E, 14F, 14G, and 14H illustrate exemplary embodiments of identifiable features detected by the system from a subject's physical exertion. Figure 14A An exemplary embodiment of identifiable features detected by the system when a subject is awakened from sleep is shown. Figure 14B An exemplary embodiment of identifiable features detected by the system as a subject drives to the start of a route is shown. Figure 14CAn exemplary embodiment of identifiable features detected by the system is shown when a subject is hiking on flat ground toward a steep uphill slope. Figure 14D An exemplary embodiment of identifiable features detected by the system while a subject rests at the top of a mountain is shown. Figure 14E An exemplary embodiment of identifiable features detected by the system when a subject is on a steep downhill slope is shown. Figure 14F An exemplary embodiment of identifiable features detected by the system while a subject cools off in a river is shown. Figure 14G An exemplary embodiment of identifiable features detected by the system as a subject completes a hike is shown. Figure 14H An exemplary embodiment of identifiable features detected by the system while a subject is asleep is shown.

[0336] Figure 15A 、 15B , 15C, 15D, 15E, 15F, 15G, 15H, 15I, 15J, 15K, 15L, 15M and 15N show exemplary embodiments of identifiable features detected by the system in an otherwise considered healthy subject over an 8-hour period over multiple days.

[0337] Figure 16A 、 16B , 15C, 16D, 16E, 16F, 16G, 16H, 16I, 16J, 16K, 16L, 16M and 16N show exemplary embodiments of identifiable features detected by the system in an otherwise considered healthy subject over an 8-hour period over multiple days.

[0338] Figure 17A 、 17B , 17C, 17D, 17E, 17F, 17G, 17H, 17I, 17J, 17K, 17L, 17M and 17N show exemplary embodiments of identifiable features detected by the system in subjects who were otherwise considered healthy over an 8-hour period over multiple days.

[0339] Figure 18A 、 18B , 18C, 18D, 18E, 18F, 18G, 18H, 18I, 18J, 18K, 18L, 18M and 18N show exemplary embodiments of identifiable features detected by the system in subjects with chronic heart failure over an 8-hour period over multiple days.

[0340] Figure 19A 、 19B , 19C, 19D, 19E, 19F, 19G, 19H, 19I, 19J, 19K, 19L, 19M and 19N show exemplary embodiments of identifiable features detected by the system in subjects with chronic heart failure over an 8-hour period over multiple days.

[0341] Figure 20A 、 20B , 20C, 20D, 20E, 20F, 20G, 20H, 20I, 20J, 20K, 20L, 20M and 20N show exemplary embodiments of identifiable features detected by the system in subjects with chronic heart failure over an 8-hour period over multiple days.

[0342] Figure 21A and 21B An exemplary embodiment of multiple thermoregulation measurements of a subject over a period of time is shown. In some embodiments, multiple thermoregulation measurements can be collected using any of the devices described above. Figure 21A Raw data for a number of thermoregulatory measurements are shown, with external temperature as a function of the thermoregulatory measurements. Figure 21B A plurality of thermoregulation measurements are shown grouped together and represented as space-filling hexagons to facilitate point-to-point distance calculations. Grouping the plurality of thermoregulation measurements into a plurality of hexagons can allow for various geometric distance calculations. For example, grouping the plurality of thermoregulation measurements into a plurality of hexagons can allow for the absolute distance between a first thermoregulation measurement in the plurality of thermoregulation measurements and a second thermoregulation measurement in the plurality of thermoregulation measurements, thereby enabling a more accurate assessment of the collected data and helping to determine whether the subject's thermoregulatory system is resilient and / or whether intervention is required for the subject and the urgency of such intervention.

[0343] Figure 22A 、 22B , 22C, 22D, 22E, 22F, 22G, 22H, 22I, 22J, 22K, 22L, 22M, 22N, and 22O show exemplary embodiments of a plurality of thermoregulatory measurements categorized by a subject over a fifteen day period. Figures 22A to 22OIt is shown that the overall recognizable pattern shown by collecting multiple thermoregulatory measurements each day can be different or change from day to day. Collecting multiple thermoregulatory measurements each day over a period of time (e.g., each day for 15 days) can more accurately determine the resilience of a subject's thermoregulatory system and / or the resilience score of the subject's thermoregulatory system. The resilience score can be calculated by first determining the probability of a shift of a categorized thermoregulatory measurement and then changing the absolute difference between the thermoregulatory measurement and another thermoregulatory measurement accordingly. A change in the absolute difference between a first thermoregulatory measurement and a second thermoregulatory measurement can change the overall recognizable pattern of the multiple thermoregulatory measurements. For example, a change in the absolute difference can cause the recognizable pattern to become more ordered or more disordered based on the change. Based on the orderliness of the recognizable pattern, the artificial intelligence can determine similarities and differences between the orderliness of the recognizable pattern of the multiple thermoregulatory measurements of the subject and the orderliness of at least one model recognizable pattern. The artificial intelligence can determine the probability that the orderliness of the recognizable pattern of the multiple thermoregulatory measurements of the subject is similar to the orderliness of at least one model recognizable pattern within a confidence level. For example, the closer the determined probability is to 1, the more the orderliness of the identifiable pattern of the subject's multiple thermoregulation measurement values ​​resembles a model identifiable pattern that implies a highly functional and / or efficient thermoregulation system, which can result in a higher thermoregulation elasticity score. For example, the closer the determined probability is to 0, the less the orderliness of the identifiable pattern of the subject's multiple thermoregulation measurement values ​​resembles a model identifiable pattern that implies a highly functional and / or efficient thermoregulation system. The less the orderliness of the identifiable pattern of the subject's multiple thermoregulation measurement values ​​resembles a model identifiable pattern that implies a highly functional and / or efficient thermoregulation system, the lower the functionality of the subject's thermoregulation system, which can result in a lower thermoregulation elasticity score.

[0344] Figure 23 An exemplary embodiment of multiple thermoregulatory elasticity scores for a subject over a time period defined as one month is shown. As shown, the chart shows a date and the subject's corresponding thermoregulatory elasticity score for that date. As further shown, the thermoregulatory elasticity score increases and decreases over a time period defined as one month. The greater the range and diversity of the thermoregulatory elasticity scores determined over that time period, the greater the variability in the subject's daily health status. This can be related to the cyclical nature of the subject's health status. The cyclical nature of the subject's health status can be associated with a more positive health status for the subject or a more negative health status for the subject.

[0345] Figure 24An exemplary embodiment of multiple thermoregulatory elasticity scores for a subject over a time period defined as one month is shown. As shown, the chart shows a date and the subject's corresponding thermoregulatory elasticity score for that date. As shown, the thermoregulatory elasticity score remains relatively constant over a time period defined as one month. The smaller the range and diversity of the thermoregulatory elasticity scores determined over that time period, the smaller the variation in the subject's daily health. As shown, the subject has a consistent, relatively high thermoregulatory elasticity score. In other words, a thermoregulatory elasticity score close to 1 can mean that the subject's daily health over that time period is generally good.

[0346] Figure 25 An exemplary embodiment of multiple thermoregulatory elasticity scores for a subject over a time period defined as one month is shown. As shown, the chart shows a date and the subject's corresponding thermoregulatory elasticity score for that date. As shown, the thermoregulatory elasticity score remains relatively constant over a time period defined as one month. The smaller the range and diversity of the thermoregulatory elasticity scores determined over that time period, the smaller the variation in the subject's daily health. As shown, the subject has a consistent, relatively low thermoregulatory elasticity score. In other words, the thermoregulatory elasticity score is closer to 0 than to 1, which may mean that the subject's daily health over that time period is generally poor.

[0347] Figure 26 An exemplary embodiment of multiple thermoregulatory elasticity scores for a subject over a time period defined as one month is shown. As shown, the chart shows a date and the subject's corresponding thermoregulatory elasticity score for that date. As shown, the thermoregulatory elasticity score remains relatively constant over a time period defined as one month. The smaller the range and diversity of the thermoregulatory elasticity scores determined over that time period, the smaller the variation in the subject's daily health. As shown, the subject has a consistent, relatively low thermoregulatory elasticity score. In other words, the thermoregulatory elasticity score is closer to 0 than to 1, which may mean that the subject's daily health over that time period is generally poor.

[0348] Figure 27 An exemplary embodiment of multiple thermoregulation measurements for three subjects over a period of time defined as one day is shown. As shown, the first subject is represented by red data points, the second subject is represented by yellow data points, and the third subject is represented by green data points. Figure 27 As shown in , the thermoregulatory elasticity score of a subject can vary during the day. Figure 27As further shown, although the thermoregulatory resilience score may vary, the trend, direction, or pattern of change in the thermoregulatory resilience score remains similar or consistent throughout the day. For example, a first subject may have a range of thermoregulatory resilience scores throughout the day, which may lead to an assessment to determine that the subject requires intervention or that health status is poor. Figure 27 As shown, for example, a first subject may have various thermoregulatory elasticity scores throughout the day, but the first subject generally remains within a first thermoregulatory elasticity score range. As shown, the first subject's first thermoregulatory elasticity score range is different from the second subject's second thermoregulatory elasticity score range, and the second subject's second thermoregulatory elasticity score range is different from the third subject's third thermoregulatory elasticity score range. This can allow the subject's thermoregulatory system to be correlated with a phenotype. In this way, any sensor that senses a biometric value can be used to assess the subject's thermoregulatory system. The first subject's thermoregulatory elasticity score can be related to a recognizable pattern associated with poor health. Similarly, as Figure 27 As shown, for example, a second subject may have various thermoregulatory resilience scores throughout the day, but the second subject generally remains within a second thermoregulatory resilience score range. The thermoregulatory resilience scores of the second subject may relate to a recognizable pattern associated with average health status. Similarly, as Figure 27 As shown, for example, a third subject may have various thermoregulatory resilience scores throughout the day, but the third subject generally remains within a third thermoregulatory resilience score range. The thermoregulatory resilience scores of the third subject may relate to a recognizable pattern associated with good health.

[0349] Figure 28 An exemplary embodiment of multiple thermoregulatory elasticity scores for multiple individuals is shown, plotted as a function of a combination of multiple thermoregulatory elasticity scores and multiple other biometric values. The combination can be considered a risk level. The graph can be used to identify subjects and / or assess the risk of a subject's health condition requiring treatment or intervention. Figure 28 As shown, most of the data points are within the thermoregulatory resilience score range of approximately -1000 to 2000. The lower the risk level, the higher the risk that the subject's health condition is considered to require treatment or intervention. Figure 28 It was further shown that by assessing a subject's risk in this manner, the probability of correctly assessing a subject's risk ranged from 5% to 25%, with an efficiency factor of 2.6.

[0350] Figure 29 Shows multiple thermoregulatory elasticity scores for multiple individuals (different from Figure 28An exemplary embodiment of a score (shown in FIG) is plotted as a function of a combination of multiple thermoregulatory elasticity scores and multiple other biometric values. The combination can be considered a risk level. The graph can be used to identify a subject and / or assess the risk that a subject's health condition requires treatment or intervention. Figure 29 As shown, at least one outlier has been removed, resulting in a majority of data points falling within the thermoregulatory resilience score range of approximately -500 to 1000. The lower the risk level, the higher the risk that the subject's health condition is considered to require treatment or intervention. Figure 29 As further shown, by assessing the risk of a subject in this manner, the probability of correctly assessing the risk of the subject ranges from 5% to 30%, with an efficiency factor of 4.43. Figure 29 As shown, by removing outliers from the dataset, the probability of correctly assessing the risk of a subject can be increased.

[0351] according to Figure 28 or Figure 29 As shown in the examples, the wearable devices disclosed herein can be used to provide precise information to a single individual to improve that individual's healthcare or optimize their lifestyle. Alternatively, multiple wearable devices can be distributed across a large group of people to gain operational efficiencies, even if the devices are not precise enough to guide care for a single individual. These embodiments address various key issues with the prior art. For example, there are restrictive established practices in the existing healthcare industry where large populations are involved and the incidence of high-cost events is low; there is little effort to intervene in these events because the cost of prediction exceeds the value of prevention; mitigation strategies are implemented at the group level (i.e., demographically stratified health guidance) rather than the individual level; and demand utility requires the ability to effectively segment the population to increase the chances of accurate prediction of events. This embodiment can produce excellent health and financial results, as described in the following illustrative cases:

[0352] Case 1: Serious medical event in a frail elderly person

[0353] Continuous monitoring by skilled medical professionals could prevent many elderly hospitalizations. Scaled skilled outpatient care is prohibitively expensive. IoT solutions improve the relative probability of predicting medical events and can be used to triage outpatient care resources. This triage capability multiplies the effective capacity of skilled nurses. Positive outcomes include reduced morbidity associated with aging and lower costs associated with hospitalizations.

[0354] Case 2: Health insurance for healthy young people

[0355] Young people require the least medical care unless they suffer a traumatic injury or unexpected illness. Demographic parameters determine insurance premiums. However, unknown physiological risk factors include the ability to effectively segment subgroups with varying risk and incentivize screening for the highest-risk groups, as well as the ability to identify stressful days when injuries are more likely and motivate customers to avoid unnecessary risk. The best outcomes include reduced morbidity associated with accidents and preventable illnesses, and lower costs for both insurers and consumers.

[0356] Case 3: Worker suffering from heat stroke

[0357] Working in hot environments is risky, especially in industries like agriculture and logistics. Most businesses adopt an all-or-nothing strategy: all workers work until the temperature exceeds a threshold, at which point everyone stops working. Identifying individuals most vulnerable to heat stroke allows for targeted work management. The benefits include less downtime and reduced injury costs.

Claims

1. A system for identifying at least one identifiable characteristic associated with a health state of a subject, comprising: at least one sensor for measuring heat flux of the subject and generating a data stream therefrom, wherein the data stream comprises a plurality of heat flux measurements; and A processor is configured to receive the data stream and identify the at least one identifiable characteristic associated with the health state.

2. The system according to claim 1, wherein: The at least one sensor for measuring heat flux includes at least one sensor array for simultaneously measuring heat dissipation from the subject and an ambient temperature proximate to the subject.

3. The system according to claim 1, wherein: The plurality of heat flux measurements includes a plurality of heat dissipation measurements expressed as a function of ambient temperature. 4 . The system of claim 1 , further comprising at least one transition state corresponding to the at least one identifiable characteristic of the data stream.

5. The system according to claim 1, wherein: The at least one identifiable characteristic associated with the health state corresponds to a biological response.

6. The system according to claim 5, wherein: The at least one identifiable characteristic has a duration of less than one hour.

7. The system according to claim 5, wherein: The at least one identifiable characteristic has a duration of more than one hour.

8. The system according to claim 1, wherein: The at least one identifiable characteristic corresponds to a homeostatic state of the subject.

9. The system according to claim 1, wherein: The data stream also includes at least one operational quantification associated with the plurality of heat flux measurements.

10. The system according to claim 9, wherein: The at least one work quantification corresponds to energy expended by a user entering at least one transition state corresponding to the at least one identifiable characteristic of the data stream.

11. The system according to claim 10, wherein: The at least one work quantification also corresponds to energy expended by the subject between the first transition state and the second transition state.

12. The system according to claim 9, wherein: The at least one work quantification corresponds to movement of the subject.

13. The system of claim 1, further configured to identify at least one motif, wherein The at least one sequence comprises a plurality of heat flux measurements.

14. The system according to claim 13, wherein: There is at least one transition state between the first motif and the second motif.

15. The system of claim 1, further configured to identify at least one inharmony comprising a plurality of heat flux measurements that do not correspond to the at least one identifiable feature.

16. The system of claim 1, wherein: The one or more identifiable features are indicative of thermal regulation.

17. The system according to claim 16, wherein: The one or more identifiable features include one or more unique features, wherein the one or more unique features are at least one of: thermal range; and Hot trends.

18. The system according to claim 17, wherein: The one or more unique patterns are indicative of a health transition.

19. The system of claim 1, further configured to identify a difference between a first heat flux measurement in the plurality of heat flux measurements and a second heat flux measurement in the plurality of heat flux measurements.

20. The system of claim 4, wherein: The at least one transition state is indicative of a change in homeostasis in the subject.

21. The system of claim 1, wherein: The processor predicts a plurality of future heat flux measurements based on the identified at least one identifiable feature.

22. The system of claim 1, wherein: The processor predicts a future identifiable feature based on the identified at least one identifiable feature.

23. The system of claim 1, wherein: The processor determines that the subject is an outlier within a population based on the at least one identifiable characteristic.

24. The system of claim 23, wherein: The population includes one or more subjects having a health status substantially similar to the health status of the subject.

25. The system of claim 23, wherein: The population includes one or more subjects whose health transition is substantially similar to the subject's health report.

26. The system of claim 1, wherein: The processor generates a recommended countermeasure based on the at least one identifiable characteristic.

27. The system of claim 26, wherein: The recommended response measures include at least one of the following: Cold compress; rest; Participate in sports activities; Stop taking the medication; Start taking medication; Go indoors; Go outdoors; Increase hydration; reduced hydration; as well as Elevate one or more limbs.

28. The system of claim 1, wherein: The processor is configured to analyze the data stream.

29. A method of identifying at least one identifiable feature associated with a biological response, comprising: measuring heat flux in the subject; generating a data stream, wherein the data stream includes a plurality of heat flux measurements; as well as The at least one identifiable feature is identified from the data stream.

30. The method of claim 29, further comprising: An analysis of the at least one identifiable feature identified for a first subject is compared to an analysis of the at least one identifiable feature identified for a second subject.

31. A method of assessing thermoregulatory resilience in a subject and generating a recommendation for intervention for the subject based on the assessed thermoregulatory resilience, comprising: generating a thermoregulatory elasticity score for the subject over a predetermined time period, wherein the thermoregulatory elasticity score is based on a data stream comprising a plurality of thermoregulatory measurements of the subject; determining whether the need for intervention for the subject exceeds a predetermined urgency threshold; and A recommendation for intervention for the subject is generated.

32. The method according to claim 31, wherein The predetermined time period is at least two days.

33. The method according to claim 31, wherein The predetermined time period is at least one day.

34. The method according to claim 31, wherein The predetermined time period is approximately one day.

35. The method of claim 31 , wherein: The predetermined time period is less than one day.

36. The method of claim 31, wherein The predetermined time period is approximately 8 hours.

37. The method of claim 31, wherein The thermoregulatory elasticity score is the homeostatic robustness of the subject's thermoregulatory system.

38. The method of claim 37, wherein: The homeostatic robustness of the subject is based on the resilience of the thermoregulatory system during transition phases.

39. The method according to claim 38, wherein The subject's ability to regulate the thermoregulatory system is based on the subject's health status.

40. The method of claim 38, wherein The transition phase includes a plurality of thermoregulatory measurements that are inconsistent with the plurality of thermoregulatory measurements constituting a normal state of the thermoregulatory system of the subject.

41. The method according to claim 40, wherein The transition phase lasts for an extended period of time that is longer than a predetermined period of time.

42. The method of claim 31 , further comprising: The healthcare practitioner is alerted that the recommendation has been generated.

43. The method of claim 40, wherein: The non-extended time period of the transition phase is indicative of an elastic thermoregulatory system of the subject.

44. The method of claim 41, wherein The extended period of the transition phase is indicative of an inelastic thermoregulatory system of the subject.

45. The method of claim 43, wherein The generated thermoregulatory elasticity score is greater than a predetermined threshold.

46. ​​The method of claim 44, wherein The generated thermoregulatory elasticity score is less than a predetermined threshold.

47. The method of claim 31 , wherein: The thermoregulatory elasticity score is below a predetermined threshold value for a predetermined duration.

48. The method of claim 47, further comprising: Alerts the healthcare practitioner that a recommendation has been generated.

49. The method of claim 31, wherein The thermoregulatory resilience score is associated with one or more interventions.

50. The method of claim 31 , further comprising: Changes in the plurality of thermoregulatory measurements of the subject are analyzed to determine characteristics of the changes.

51. The method of claim 50, wherein: The plurality of thermoregulatory measurements of the subject include a plurality of heat flux measurements.

52. The method of claim 50, wherein: The changes are characterized by a pattern.

53. A method for identifying a subject in urgent need of intervention, comprising: measuring a plurality of thermoregulatory measurements of the subject; generating a data stream over a time period, wherein the data stream includes a plurality of thermoregulatory measurements; generating a score for the time period based on the data stream; Identifying whether the subject is in urgent need of intervention; and Send alerts related to urgent intervention needs.

54. The method of claim 53, wherein: The score is less than a predetermined score.

55. The method of claim 54, wherein The score indicates that the subject's thermoregulatory system is inelastic.

56. An alarm system configured to generate an alarm to intervene in the health of a subject, comprising: at least one sensor for generating a plurality of thermoregulatory measurements of the subject; a communication component for generating a data stream of thermoregulation measurements, wherein the data stream includes a plurality of thermoregulation measurements within a predetermined time period; as well as A processor is configured to receive the data stream and generate a score associated with the predetermined time period based on the measured elasticity of thermoregulation of the subject.

57. An alarm system according to claim 56, wherein In case the score is greater than a predetermined score threshold, the score is a resiliency score.

58. The alarm system of claim 56, further comprising an alarm configured to alert a user to intervene with the subject if the score is less than a predetermined score threshold.

59. An alarm system according to claim 58, wherein The score is an inelasticity score, indicating that the subject's thermoregulatory system is inelastic.

60. A method of identifying a subject requiring intervention and alerting another person regarding the need for intervention, comprising: measuring a plurality of thermoregulatory measurements of the subject; generating a data stream over a time period, wherein the data stream includes a plurality of thermoregulatory measurements; generating a score for the time period based on the data stream; grouping the score and a plurality of other biometric values ​​into a data set; identifying whether the subject requires intervention based at least in part on the score; and An alert is sent regarding the need for intervention.

61. The method of claim 60, wherein: The plurality of other biometric values ​​includes at least one of: Heart rate; blood pressure; or Skin temperature.

62. The method of claim 60, wherein: Identify whether the need for intervention is urgent.

63. The method of claim 60, wherein: The primary basis for determining whether the subject is in urgent need of intervention is the score.

64. A method for identifying a patient at risk for health problems, comprising: measuring a plurality of thermoregulatory measurements of the subject; generating a data stream over a time period, wherein the data stream includes a plurality of thermoregulatory measurements; generating a score for the time period based on the data stream; grouping the score and a plurality of other biometric values ​​into a data set; and Identify whether the subject has a health risk.

65. The method of claim 64, wherein Identifying whether the subject has a health risk is used to determine at least one of the following: the subject's health insurance risk; or The heat stroke threshold of the subject.

Images