JMIR Publications

ABSTRACT

Background:

The majority of adults in the US will be exposed to a potentially traumatic event, but only a handful will go on to develop impairing mental health conditions such as Post-traumatic Stress Disorder (PTSD).

Objective:

Identifying those at elevated risk shortly after trauma exposure is a clinical challenge. We aim to develop computational methods to more effectively identify at-risk patients, and thereby support better early interventions.

Methods:

We propose machine learning (ML) induction of models to automatically predict elevated PTSD symptoms in patients one month after a trauma, using self-reported symptoms from data collected via smartphones.

Results:

We show that an ensemble model accurately predicts elevated PTSD symptoms, with an AUC of 0.85, using a bag of SVM, Naïve Bayes, logistic regression, and random forest algorithms. Furthermore, we show that only 7 self-report items (features) are needed to obtain this AUC. Most importantly, we show that accurate predictions can be made after 10-20 days post trauma.

Conclusions:

These results suggest that simple smartphone-based patient surveys, coupled with automated analysis using ML-trained models, can identify those at risk for developing elevated PTSD symptoms and thus target them for early intervention.