JMIR Publications

ABSTRACT

Background:

Sensors embedded in smartphones allow for the passive momentary quantification of people’s states in the context of their daily lives in real-time. Such data could be useful for alleviating the burden from ecological momentary assessments and increase utility in clinical assessment. Despite existing research on utilizing passive sensor data to assess participants' moment-to-moment states and activity levels, only limited research has investigated temporally linking sensor assessment and self-reported assessment to further integrate the two methodologies.

Objective:

We investigated whether movement related sensor data, collected from the smartphone while participants were filling out the questionnaire, could predict future states of individuals’ work-related rumination, fatigue, mood, arousal, life engagement, and sleep quality.

Methods:

We trained personalized machine learning models on data from employees (N = 158) who participated in a three-week ecological momentary assessment study.

Results:

The results suggested that passive smartphone sensor data paired with personalized machine learning models can predict individuals’ future responses with a mean R² of approximately .31 and an R² = .18 or above in over 50% of participants. Accuracy was only slightly attenuated compared with earlier studies and ranged from 38.41% to 51.38%.

Conclusions:

Personalized machine learning models and temporally linked passive sensing data have the capability to predict a sizable proportion of variance in individuals’ daily self-reported states. Further research is needed to investigate factors that affect the accuracy and reliability of the prediction.