Digital Health: Tracking Physiomes and Activity Using Wearable Biosensors Reveals Useful Health-Related Information

Abstract

A new wave of portable biosensors allows frequent measurement of health-related physiology. We investigated the use of these devices to monitor human physiological changes during various activities and their role in managing health and diagnosing and analyzing disease. By recording over 250,000 daily measurements for up to 43 individuals, we found personalized circadian differences in physiological parameters, replicating previous physiological findings. Interestingly, we found striking changes in particular environments, such as airline flights (decreased peripheral capillary oxygen saturation [SpO2] and increased radiation exposure). These events are associated with physiological macro-phenotypes such as fatigue, providing a strong association between reduced pressure/oxygen and fatigue on high-altitude flights. Importantly, we combined biosensor information with frequent medical measurements and made two important observations: First, wearable devices were useful in identification of early signs of Lyme disease and inflammatory responses; we used this information to develop a personalized, activity-based normalization framework to identify abnormal physiological signals from longitudinal data for facile disease detection. Second, wearables distinguish physiological differences between insulin-sensitive and -resistant individuals. Overall, these results indicate that portable biosensors provide useful information for monitoring personal activities and physiology and are likely to play an important role in managing health and enabling affordable health care access to groups traditionally limited by socioeconomic class or remote geography.

Fig 1. Overview of the project and summary of the devices.

(A) Wearable devices used in this study. The different colors for the human figures indicate the specific studies in which each individual participated (i.e., red participated in all five studies, grey in two studies [Physiology/Activity and Insulin Sensitivity], blue in three studies [Physiology/Activity, Insulin Sensitivity, and Inflammation], orange and yellow in two studies [Physiology/Activity and Airflights], and green and pink in one study [Inflammation] and purple in one study [Airflights]). (B) The period during which the devices were used. The number of data points available for Participant #1 and others is indicated to the right. (C) The specific parameters measured by the different devices. The devices used to measure these parameters were represented by the color of the lines (MOVES: magenta; Basis: dark blue; Scanadu Scout: light green; iHealth-finger: brown; Masimo: orange; RadTarge: red; Withings: dark green). Dashed line indicates devices used frequently for discrete measurements; solid lines indicate devices that provide continuous measurement.

Fig 2. Circadian and diurnal patterns in physiological parameters.

Participant #1 hourly summaries in (A) sleep, (B) HRs, (C) skin temperature, and (D) steps as measured using the Basis Peak device over 71 nontravel d. (E) Summaries of 43-person cohort for daily HR and skin temperature from all data and (F) differences in resting (fewer than five steps) nighttime and daytime HRs (Note: one person did not have nighttime measurements and is not included) and skin temperature. (G) Daily activity plots for 43 individuals. Based on number of peaks in the curves, four general patterns of activity behavior are evident. The plots in Fig 2G were aligned according to the first increase in activity.

Fig 3. Physiological and activity profiles for 43 individuals.

(A) The relationship between the average number of steps per day and resting HR (n = 43) and (B) average steps per minute and change in body mass index (BMI; n = 20) over the course of approximately 1 y was analyzed. Average resting HRs (C) were calculated by gender (see Material and Methods; n = 38).

Fig 4. SpO₂ measurements during flight.

(A) Example of a flight with continuous SpO₂ measurements (blue) taken using a Masimo finger device. Altitude recorded using FlightAware (green). (B) Heat map showing distribution of SpO₂ measurements recorded using a forehead Scanadu device at different flight stages: before takeoff, ascending, cruising, descending, and on ground post flight. (C) SpO₂ levels recorded using iHealth-finger device during 2-h automobile ride over a mountain. Average measurements and standard error measured over a 15-min window (Blue). Altitude recorded from sign markers or town elevations and/or using DraftLogic website. (D) Distribution of SpO₂ measurements taken from 18 individuals at cruising altitude (blue) versus on ground (green). (E) Distribution of SpO₂ measurements after the participant reported feeling alert (red) or tired (cyan). (Upper panel) Measurements from nonflying days. (Lower panel) Measurements from flying days. The significance of the difference between the two distributions was assessed by two-sample Kolmogorov–Smirnov test. (F) Scatterplot of response time and SpO₂ level recorded during one flight. The data recorded during another flight are shown in S5D Fig. The response time was derived from the psychomotor vigilance test to objectively quantify the fatigue of the participant. Self-reported tired and alert states are labeled by cyan triangles and red dots, respectively. (G) (Upper panel) Example of a flight with continuous SpO₂ measurements (blue) taken using a Masimo finger device. Altitude recorded using FlightAware (green). Note the increase in SpO₂ level towards the end of the flight. (Lower panel) Sleepiness recorded by Basis device. Magenta and cyan colors represent sleep and awake status, respectively. (H) A scatterplot of duration of time and the increase of SpO₂ in the last quarter. All data points were collected at altitudes higher than 35,000 feet. (I) Empirical cumulative distribution function plot of SpO₂ levels >7 h after takeoff (red) versus <2 h after takeoff (blue). All the data points were recorded at altitudes higher than 35,000 feet (p < 1e-307; two-sample Kolmogorov–Smirnov test).

Fig 5. Elevated physiological measurements during infections.

(A) Plot of fraction of outlying skin temperatures and HRs for all 679 d of Participant #1. Note all outlying time points correspond to periods when elevated high-sensitivity C-reactive protein (hs-CRP) measurements and/or illness were noted. The period harboring Lyme disease is expanded in panel B. (C) Decreased SpO₂ measurements during the flight and subsequent period when aberrant physiological measurements were first noted; boxplot shows SpO₂ distribution on Day 470 flight (blue) relative to similar length flights (green). The significance of this difference was assessed by two-sided Wilcoxon rank sum test. (D, E) CRP measurements are plotted against the proportion of daily HR measurements that were more than two SDs above the mean for Participant #58 (Pearson correlation coefficient = 0.90, p = 1.066e-05) (D) and Participant #59 (Pearson correlation coefficient = 0.966, p = 0.1653) (E). The timelines for the illness progression, CRP measurements, and Basis monitoring period captured in the figure are indicated for Participant #58 (two different illnesses separated by a period of ~11 mo) (Lower panel of D) and Participant #59 (Lower panel of E). (F) 679-d monitoring period of Participant #1. Left: normalized HR in minute resolution. Zoomed in at each illness period. Right: elevated CRP periods; G-H. Normalized HR at sick periods in minute resolution for Participant #58 (G) and Participant #59 (H). Red peak: Abnormal periods indicated by the peak caller. Red vertical line: CRP larger than 10; Green vertical line: CRP larger than three but smaller than ten. Yellow line: CRP smaller than three.

Fig 6. HR differences in IR and sensitivity.

Fit plots (A–D) of the linear regression models showing the associations between daytime (C), nighttime (D), delta (daytime minus nighttime) HR (A), and average daily steps (B) with SSPG levels. Higher SSPG levels indicate increased IR. An increase in delta HR and daytime HR is associated with a higher SSPG level, whereas an increase in average number of steps taken a day is associated with a lower SSPG level. There was no association with nighttime HR. Contour fit plot (E) and 3-D plot (F) of the multivariate regression demonstrating that delta HR and average daily steps each have an independent inverse association with SSPG. Parameter estimates were obtained using restricted maximum likelihood estimation with a robust variance estimator to account for unequal variances.

Fig 7. Exposure to radiation in daily life.

Bar plot (upper panel: bars in blue) showing the amount of radiation that Participant #1 exposed to over a 25-d time window. Bar plot (lower panel: bars in magenta) showing the time that Participant #1 spent in airplane flights over the same time period. The maximum cruising altitude of each flight was labeled in the zoomed view of the bar plots. Asterisk represents the amount of radiation monitored during the airport carry-on luggage check (range 0.027 to 0.031 mRem). Other events that resulted in relatively high radiation are also labeled in the figure.