Search

EP-4125562-B1 - PREDICTING WELLNESS OF A USER WITH MONITORING FROM PORTABLE MONITORING DEVICES

EP4125562B1EP 4125562 B1EP4125562 B1EP 4125562B1EP-4125562-B1

Inventors

  • REZAI, ALI
  • FINOMORE, VICTOR
  • D'HAESE, Pierre
  • MARSH, CLAY

Dates

Publication Date
20260506
Application Date
20210329

Claims (9)

  1. A computer implemented method for monitoring a wellness of a user, the method comprising monitoring (202) a wellness-relevant parameter representing the user at a portable device 152,154) over a defined period to produce a time series for the wellness-relevant parameter; obtaining (204) a first set and a second set of one of cognitive assessment data and psychosocial assessment data for the user at respective first and second times in the defined period; and assigning (306) a value to the user via a predictive model representing a future value of the wellness-relevant parameter according to the time series for the wellness-relevant parameter, the first set of one of cognitive assessment data and psychosocial assessment data, and the second set of one of cognitive assessment data and psychosocial assessment data, wherein assigning the value to the user comprises: performing a wavelet decomposition on the time series for the wellness-relevant parameter to provide a set of wavelet coefficients as a two-dimensional array across time and either frequency or scale; and generating a center of mass of the two-dimensional array as a first representative value for time and a second representative value for either frequency or scale; wherein assigning the value representing the future value of the wellness-relevant parameter according to the time series for the wellness-relevant parameter, the first set of one of cognitive assessment data and psychosocial assessment data, and the second set of one of cognitive assessment data and psychosocial assessment data comprises assigning the value according to at least the first and second representative values, the first set of one of cognitive assessment data and psychosocial assessment data, and the second set of one of cognitive assessment data and psychosocial assessment.
  2. The method of claim 1, further compromising generating a weighted combination of at least a portion of the set of wavelet coefficients, wherein assigning the value according to at least the set of wavelet coefficients comprises assigning the value according to at least the weighted combination.
  3. The method of claim 1, further comprising: measuring an outcome associated with the user; comparing the measured outcome to the value assigned to the user via a predictive model; and changing a parameter associated with the predictive model according to the comparison of the measured outcome to the value assigned to the user via the predictive model.
  4. The method of claim 3, wherein changing the parameter associated with the predictive model according to the comparison of the measured outcome to the value assigned to the user via the predictive model comprises generating a reward for a reinforcement learning process based on a similarity of the measured outcome to the value assigned to the user and changing the parameter via the reinforcement learning process.
  5. The method of claim 4, wherein the parameter associated with the predictive model is a decision threshold used to assign the value to the user as a categorical value from a continuous index provided by the predictive model.
  6. The method of claim 1, wherein the wellness-relevant parameter is heart rate variability.
  7. A system comprising: a wearable device (152,154) that monitors a wellness-relevant parameter representing a user over a defined period to produce a time series for the monitored parameter; a portable device (160) that receives a first set and a second set of one of cognitive assessment data and psychosocial assessment data for the user at respective first and second times in the defined period; a feature extractor (122) that determines a set of features from the time series for the monitored parameter, the feature extractor performing a wavelet decomposition on the time series for the wellness-relevant parameter to provide a set of wavelet coefficients as a two-dimensional array across time and either frequency or scale and generating a center of mass of the two-dimensional array as a first representative value for time and a second representative value for either frequency or scale, the set of features including the first representative value and the second representative value; and a predictive model (124) that assigns a value representing a future value of the wellness-relevant parameter to the user according to the set of features, the first set of one of cognitive assessment data and psychosocial assessment data, and the second set of one of cognitive assessment data and psychosocial assessment data.
  8. The system of claim 7, wherein the first set and second set of one of cognitive assessment data and psychosocial assessment data are the first set and the second set of cognitive assessment data and the portable device includes a user interface that allows the user to interact with a cognitive assessment application at a base unit associated with the wearable device to provide the first set of cognitive assessment data and the second set of cognitive assessment data.
  9. The system of claim 7, wherein the predictive model is implemented as a recurrent neural network that produces an index representing the user and a reinforcement learning model that continuously refines a decision threshold used to assign the value to the user as a categorical parameter representing a wellness of the user.

Description

RELATED APPLICATIONS This application claims priority from each of U.S. Provisional Application No. 63/000,607, filed 27 March 2020 and U.S. Provisional Application No. 63/032,036, filed 29 May 2020. TECHNICAL FIELD This invention relates to a prediction of wellness of a user with monitoring from portable monitoring devices. BACKGROUND OF THE INVENTION Many disorders affecting the health and wellness of an individual can be difficult to detect in the early stages of the disorder, which is often the time in which intervention is most effective. For example, infectious diseases have incubation periods during which an individual can be contagious to others either without experiencing symptoms or while experiencing only relatively innocuous symptoms. Similarly, in many disorders, timely treatment can spare an individual the worst of the symptoms. Relevant prior art is disclosed in US 2016/022167, US 2019/239791, US 2014/163335, US 2019/113973 and US 2017/347906. SUMMARY In accordance with aspects of the present invention, methods and systems for monitoring wellness of a user are defined in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates a system for monitoring the wellness of a user in accordance with an aspect of the present invention;FIG. 2 is a schematic example of the system of FIG. 1 using a plurality of portable monitoring devices;FIG. 3 is a screenshot of a reaction time test from an example cognitive assessment application;FIG. 4 is a screenshot of an attention test from an example cognitive assessment application;FIGS. 5 and 6 are screenshots of a response inhibition test from an example cognitive assessment application;FIG. 7 is a screenshot of a working memory (1-back) test from an example cognitive assessment application;FIG. 8 is a screenshot of a working memory (2-back) test from an example cognitive assessment application;FIG. 9 illustrates example questions for a first survey that is completed in the morning for an example of the system used to predict the onset of symptoms from COVID-19;FIG. 10 illustrates example questions for a second survey that is completed in the evening for the example of FIG. 9;FIG. 11 illustrates a simplified example of a map of risk scores that could be generated for a target location;FIG. 12 illustrates graphs of several wellness-related parameters over a time period before an outbreak of an infectious disease;FIG. 13 illustrates graphs of the parameters of FIG. 12 during an outbreak;FIG. 14 illustrates a radar plot comparing average values for various wellness-relevant parameters for individuals infected with COVID-19 against the general population;FIG. 15 illustrates one example of a method for monitoring the wellness of a user;FIG. 16 illustrates another example for monitoring the wellness of a user; andFIG. 17 is a schematic block diagram illustrating an exemplary system of hardware components. DETAILED DESCRIPTION The term "wellness" as used herein in intended to refer to the mental, physical, cognitive, social, and emotional health of a user and should be construed to cover each of the health, function, balance, resilience, homeostasis, disease, and condition of the user. In various examples herein, the wellness of the user can relate to the readiness of the user to perform job-related functions, the susceptibility of the user to an infectious disease, the ability of the user to recover from an infectious disease, the exhibition of symptoms of an infectious disease by the user, the degree to which the user exhibits symptoms of an infectious disease, the ability to recover from an infectious disease, the effects of vaccines or other therapeutic substances on the user, including both efficacy and side effects, and the ability to avoid reinfection by a previously contracted infectious disease. A "wellness-relevant parameter" is a physiological, cognitive, sensory (e.g., smell, taste, vision, sweat, hearing, etc.), psychosocial, or behavioral parameter that is relevant to the wellness of a user. A "biological rhythm" is any chronobiological phenomenon that affects human beings, including but not limited to, circadian rhythms, ultradian rhythms, infradian rhythms, diurnal cycle, sleep/wake cycles, and patterns of life. A "portable monitoring device," as used herein, refers to a device that is worn by, carried by, or implanted within a user that incorporates either or both of an input device and user interface for receiving input from the user and sensors for monitoring either a wellness-relevant parameter or a parameter that can be used to calculate or estimate a wellness-relevant parameter. Examples include wearables, such as smartwatches, rings, and similar devices, mobile devices, such as smartphones, and tablets, and laptop or notebook computers. An "index", as used herein, is intended to cover composite statistics and Al findings derived from a series of observations and used as an indicator or measure. An index can be an ordinal, conti