Background Consumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized. Objective We aimed to derive high-resolution digital phenotypes from observational wearable recordings and to examine their associations with modifiable and inherent markers of cardiometabolic disease risk. Methods We introduced a principled framework to extract interpretable high-resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes the handling of data irregularities; encodes contextual information regarding the underlying physiological state at any given time; and generates a set of 66 minimally redundant features across active, sedentary, and sleep states. We applied our approach to a multimodal data set, from the SingHEART study (NCT02791152), which comprises heart rate and step count time series from wearables, clinical screening profiles, and whole genome sequences from 692 healthy volunteers. We used machine learning to model nonlinear relationships between the high-resolution phenotypes on the one hand and clinical or genomic risk markers for blood pressure, lipid, weight and sugar abnormalities on the other. For each risk type, we performed model comparisons based on Brier scores to assess the predictive value of high-resolution features over and beyond typical baselines. We also qualitatively characterized the wearable phenotypes for participants who had actualized clinical events. Results We found that the high-resolution features have higher predictive value than typical baselines for clinical markers of cardiometabolic disease risk: the best models based on high-resolution features had 17.9% and 7.36% improvement in Brier score over baselines based on age and gender and resting heart rate, respectively (P<.001 in each case). Furthermore, heart rate dynamics from different activity states contain distinct information (maximum absolute correlation coefficient of 0.15). Heart rate dynamics in sedentary states are most predictive of lipid abnormalities and obesity, whereas patterns in active states are most predictive of blood pressure abnormalities (P<.001). Moreover, in comparison with standard measures, higher resolution patterns in wearable heart rate recordings are better able to represent subtle physiological dynamics related to genomic risk for cardiometabolic disease (improvement of 11.9%-22.0% in Brier scores; P<.001). Finally, illustrative case studies reveal connections between these high-resolution phenotypes and actualized clinical events, even for borderline profiles lacking apparent cardiometabolic risk markers. Conclusions High-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management.

BackgroundConsumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized.ObjectiveWe aimed to (i) derive high resolution digital phenotypes from observational wearable recordings, (ii) characterize their ability to predict modifiable markers of cardiometabolic disease, and (iii) study their connections with genetic predispositions for cardiometabolic disease and with lifestyle factors.MethodsWe introduce a principled framework to extract interpretable high resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes handling of data irregularities, encodes contextual information about underlying physiological state at any given time, and generates a set of 66 minimally redundant features across active, sedentary and sleep states. We applied our approach on a multimodal dataset, from the SingHEART study (NCT02791152), that comprises of heart rate and step count time series from wearables, clinical screening profiles, whole genome sequences and lifestyle survey responses from 692 healthy volunteers. We employed machine learning to model non-linear relationships between the high resolution phenotypes and clinical risk markers for blood pressure, lipid and weight abnormalities. For each risk type, we performed model comparisons based on Brier Skill Scores (BSS) to assess predictive value of the high resolution features over and beyond typical baselines. We then examined associations between the wearable-derived features, polygenic risk for cardiometabolic disease, and lifestyle habits and health perceptions.ResultsCompared to typical summary statistic measures like resting heart rate, we find that the high-resolution features collectively have greater predictive value for modifiable clinical markers associated with cardiometabolic disease risk (average improvement in Brier Skill Score=52.3%, P<.001). Further, we show that heart rate dynamics from different activity states contain distinct information about type of cardiometabolic risk, with dynamics in sedentary states being most predictive of lipid abnormalities and patterns in active states being most predictive of blood pressure abnormalities (P<.001). Finally, our results reveal that subtle heart rate dynamics in wearable recordings serve as physiological correlates of genetic predisposition for cardiometabolic disease, lifestyle habits and health perceptions.ConclusionsHigh resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance prediction of cardiometabolic disease risk, and could enable more proactive and personalized health management.Trial RegistrationClinicalTrials.govNCT02791152; https://clinicaltrials.gov/ct2/show/NCT02791152