Roar Articles

Machine Learning Can Help Turn Wearable Data into Scientific Discovery

Research conducted by:

Zita Oravecz, Associate Professor of Human Development and Family Studies and ICDS Co-Hire, Tim Brick, Assistant Professor of Human Development and Family Studies and ICDS Co-Hire


machine learning psychology wearables

Research Summary:

Smartphone sensors and health and fitness monitors can ease the collection of physiological data for scientists. They can also help researchers gather real-time information about psychological states from participants. A team of researchers used machine learning approaches to use that physiological data to offer hints at the participant’s psychological states. The researchers hope this could lead to new ways to identify important psychological states – for example, moments when a person recovering from an addiction is feeling temptation – without the need for often burdensome active assessments.

How Roar played a role in this research:

"The ICDS infrastructure was instrumental in terms of processing the high intensity data and running the machine learning algorithms featured in the paper." - Zita Oravecz

Publication Details

Article Title:

Individualized Modeling to Distinguish Between High and Low Arousal States Using Physiological Data

Published In:

Journal of Healthcare Informatics Research


With wearable, relatively unobtrusive health monitors and smartphone sensors, it is increasingly easy to collect continuously streaming physiological data in a passive mode without placing much burden on participants. At the same time, smartphones provide the ability to survey participants to provide “ground-truth” reporting on psychological states, although this comes at an increased cost in participant burden. In this paper, we examined how analytical approaches from the field of machine learning could allow us to distill the collected physiological data into actionable decision rules about each individual’s psychological state, with the eventual goal of identifying important psychological states (e.g., risk moments) without the need for ongoing burdensome active assessment (e.g., self-report). As a first step towards this goal, we compared two methods: (1) a k-nearest neighbor classifier that uses dynamic time warping distance, and (2) a random forests classifier to predict low and high states of affective arousal states based on features extracted using the tsfresh python package. Then, we compared random-forest-based predictive models tailored for the individual with individual-general models. Results showed that the individual-specific model outperformed the general one. Our results support the feasibility of using passively collected wearable data to predict psychological states, suggesting that by relying on both types of data, the active collection can be reduced or eliminated.

View article on publisher's website

Related Articles