JMIR Publications

ABSTRACT

Background:

Inhibitory control, or inhibition, is one of the humans' core executive functions. It contributes to our attention, performance, physical and mental wellbeing. Our inhibitory control is modulated by a variety of factors and therefore fluctuates over time. Being able to continuously and unobtrusively assess our inhibitory control will allow systems that help manage and support our wellbeing.

Objective:

The objective of our study was to investigate whether we can assess individuals' inhibitory control using an unobtrusive and scalable approach to identify digital markers that are predictive of changes in inhibitory control.

Methods:

We developed InhibiSense, an app that passively collects users' phone usage and sensor data to track their behaviors and cognition. Participants were asked to use the InhibiSense and wear a heart rate monitor (Polar H10) for 4 weeks. We used generalized estimating equation models fitted with features extracted from participants' sensor data to predict their stop signal reaction time, an objective metric used to measure an individual's inhibitory control, and identify the predictive digital markers.

Results:

A total of 12 participants completed the study, and we collected in total 2,189 responses of their ecological momentary assessment and stop signal task. Some of the top predictive sensor features we identified for inhibitory control include the standard deviation of a person's acceleration (p=0.021), whether they were in an outdoor and recreational environment (p=0.011), the number of phone use sessions (p=0.005), and the number of incoming calls (p<0.001).

Conclusions:

We identified several phone sensor based markers that are predictive of changes in inhibitory control. We discussed some potential applications of the system and how intervention technologies can be designed to help manage our inhibitory control.