In our case, this power translates to preventive health. As I always say, if meticulously collected medical data is available, then it is only a matter of imagination the results derived from it.

I stumbled across a study in the prestigious Nature magazine that justifies my theory, that data collected with the help of health IT devices is the starting point of personalized, precision medicine.

In this study, based on an examination of 1002 healthy individuals, where healthy means “able to work,” researchers searched for digital phenotypes associated with stress. Physiological signals are a reliable indicator of it, but a large-scale validation is lacking. In this study subject were middle-aged, white collar workers, from technology oriented, finance and public companies. Researchers registered data for five consecutive days over the span of two years.

Subjects received two wearable devices from the scientists: a chest patch to measure the electrocardiogram and acceleration, a wristband to monitor skin conductance, skin temperature, and acceleration. In the study, they also collected smartphone sensor data: location, movement, SMS, call, mail logs, phone usage, audio, environmental sensors. The earlier small-scale study suggested that physiological responses to stress tend to be person-dependent.

Based on a data-driven approach, the study identified digital phenotypes characterized by self-reported poor health indicators and high depression, anxiety and stress scores that are associated with blunted physiological responses to stress.

The results of this study provide a baseline for large-scale ambulatory population monitoring to uncover blunted physiological responses to stress. Furthermore, these findings have important implications related to stress modeling strategies, indicating that stress detection models should be tailored to phenotypes by including multi-sensor data sources, as subjects with different physiological responses to stress, display different health statuses.

This study exemplifies how large-scale, data-driven analytics can be used to derive digital phenotypes and generate new insights into stress detection and disease interception in general. Continuous stress detection will form the basis to enable highly personalized, just-in-time interventions for preventive health — just the problems, here at NETIS are working on.

Author: Laszlo Varga