Learning Individualized Cardiovascular Responses from Large-scale Wearable Sensors Data
This work addresses cardiovascular health monitoring for individuals using wearable data, but it is incremental as it applies a known neural network method to a new large-scale dataset.
The authors tackled the problem of modeling cardiovascular responses to physical activity and sleep from wearable sensor data, using an attentional convolutional neural network on a cohort of 80,000 people, and demonstrated that their method outperformed baselines in predicting heart rate and variables like age and BMI.
We consider the problem of modeling cardiovascular responses to physical activity and sleep changes captured by wearable sensors in free living conditions. We use an attentional convolutional neural network to learn parsimonious signatures of individual cardiovascular response from data recorded at the minute level resolution over several months on a cohort of 80k people. We demonstrate internal validity by showing that signatures generated on an individual's 2017 data generalize to predict minute-level heart rate from physical activity and sleep for the same individual in 2018, outperforming several time-series forecasting baselines. We also show external validity demonstrating that signatures outperform plain resting heart rate (RHR) in predicting variables associated with cardiovascular functions, such as age and Body Mass Index (BMI). We believe that the computed cardiovascular signatures have utility in monitoring cardiovascular health over time, including detecting abnormalities and quantifying recovery from acute events.