A novel health risk model based on intraday physical activity time series collected by smartphones
This work addresses health risk assessment for smartphone users by enabling transferable predictions across devices and populations, though it is incremental as it builds on existing domain adaptation and deep learning methods.
The authors tackled the problem of predicting health risks from smartphone motion data by developing a model using adversarial domain adaptation and a ResNet, which produced a risk score predictive of lifespan and healthspan, with performance validated in a smaller cohort.
We compiled a demo application and collected a motion database of more than 10,000 smartphone users to produce a health risk model trained on physical activity streams. We turned to adversarial domain adaptation and employed the UK Biobank dataset of motion data, augmented by a rich set of clinical information as the source domain to train the model using a deep residual convolutional neuron network (ResNet). The model risk score is a biomarker of ageing, since it was predictive of lifespan and healthspan (as defined by the onset of specified diseases), and was elevated in groups associated with life-shortening lifestyles, such as smoking. We ascertained the target domain performance in a smaller cohort of the mobile application that included users who were willing to share answers to a short questionnaire related to their disease and smoking status. We thus conclude that the proposed pipeline combining deep convolutional and Domain Adversarial neuron networks (DANN) is a powerful tool for disease risk and lifestyle-associated hazard assessment from mobile motion sensors that are transferable across devices and populations.