Selfies for Health Care

Presently, self-tracking applications are used to help patients with chronic illness management. For example, applications ask users to track mood through online diaries or snap photos of their food content in order to analyze patterns correlated to their chronic disease. Although these health care applications are on the market today, there still exists a fundamental challenge in motivating participants to consistently update and enter information. Therefore, the focus of this thesis is on reducing the fatigue from using these applications. Pulling from user social media data will almost completely eliminate the capture burden placed on participants, since users will only have to continue to use social media as they regularly do. Instead of analyzing manually inputted data, patterns can be found between social media data and chronic diseases. A Microsoft Research team found indicators in public user Twitter data associated with the onset of a depressive episode. They were able to create a predictor tool, predicting the onset of a depressive episode, with 70 percent accuracy. Using this research alongside expert feedback, our aim is to design an interface used by both clinician and patient that will provide them with a timeline marking spikes in Twitter indicators correlated to a patient’s depressive episode