Abstract
We report on the newly started project “SCH: Personalized Depression Treatment Supported by Mobile Sensor Analytics”. The current best practice guidelines for treating depression call for close monitoring of patients, and periodically adjusting treatment as needed. This project will advance personalized depression treatment by developing a system, DepWatch, that leverages mobile health technologies and machine learning tools. The objective of DepWatch is to assist clinicians with their decision making process in the management of depression. The project comprises two studies. Phase I collects sensory data and other data, e.g., clinical data, ecological momentary assessments (EMA), tolerability and safety data from 250 adult participants with unstable depression symptomatology initiating depression treatment. The data thus collected will be used to develop and validate assessment and prediction models, which will be incorporated into DepWatch system. In Phase II, three clinicians will use DepWatch to support their clinical decision making process. A total of 128 participants under treatment by the three participating clinicians will be recruited for the study. A number of new machine learning techniques will be developed.
Highlights
Depression is a complex, heterogeneous, severely debilitating and chronic illness
Similar to other fields of medicine, there has been a strong impetus in the field of psychiatry to personalize depression treatment, i.e., quickly identify the best treatment for a depressed individual while minimizing side effects in the clinical setting
Our study focuses on providing clinicians a decision support system that helps them to evaluate and adjust depression treatment, leveraging mobile sensor analytics
Summary
Depression is a complex, heterogeneous, severely debilitating and chronic illness. It affects more than 264 million people worldwide, contributing to significant number of deaths by suicide every year [1]. We further developed feature extraction techniques to extract behavioral features from the sensory data as correlates of depression symptomatology, and machine-learning models to predict self-report questionnaire scores and depression status (i.e., whether one is depressed or not) These techniques and prediction models were validated and refined in Phase II of the study. The self-reports and the passively collected sensory data will be used to develop, evaluate and cross validate machine learning models for assessing depressive symptoms and predicting patients’ response to treatment in the future e.g., in the two, four or six weeks after treatment initiation. We hypothesize that DepWatch system will be able to predict response/nonresponse to depression treatments by capturing change in behavioral patterns as it relates to changes in patient’s depression severity, which will be useful in clinicians’ decision making process This is a four-year project, currently in its first year. Our study focuses on providing clinicians a decision support system that helps them to evaluate and adjust depression treatment, leveraging mobile sensor analytics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
