Detecting self-harming activities with wearable devices

Abstract

In the United States, there are more than 35, 000 reported suicides with approximately 1, 800 of them being psychiatric inpatients. Staff perform intermittent or continuous observations in order to prevent such tragedies, but a study of 98 articles over time showed that 20% to 62% of suicides happened while inpatients were on an observation schedule. Reducing the instances of suicides of inpatients is a problem of critical importance to both patients and healthcare providers. In this paper, we introduce SHARE - A Self-Harm Activity Recognition Engine, which attempts to infer self-harming activities from sensing accelerometer data using smart devices worn on a subject's wrist. Preliminary classification accuracy of 80% was achieved using data acquired from 4 subjects performing a series of activities (both self-harming and not). The results, application, and proposed technology platform are discussed in-depth.