People with autism are prone to aggressive outbursts, which often happen unpredictably, and sometimes long after a trigger, severely limiting the liberties they can share with their families. In addition, communicating what is distressing them can often be difficult, making the timely and early intervention of their caregivers more challenging. If a caregiver can intervene early, they can help relax the individual, and maintain a safe environment.
The outbursts are a result of their resting stress levels being much higher compared to those of someone without autism. With this in mind, Northeastern behavioral scientist Matthew Goodwin and his team used the E4 and have created an algorithm that can predict these outbursts in people with autism by monitoring physiological indicators of stress. The researchers collected 87 hours of data from 20 children, tracking the physiological changes that occurred before, during, and after each episode.
By analyzing the changes in physiology that occurred around each episode, the algorithm developed by Goodwin and his team could predict an aggressive outburst a minute in advance with 84 percent accuracy. Even a minute's warning can be crucial in helping caregivers prevent an aggressive outburst, showing there is true potential in the use of wearables and AI to alert caregivers and help mitigate their emergence, occurrence, or impact.
