When it comes to big data, investigators aim for high statistical power: the more data points within a research question, the more likely they are to find patterns and associations that could provide insight about different diseases. Technology is advancing each day, capturing more and more information about human behavior, including medical histories, geographic locations, biometric data, lifestyle habits that can be combined in an astounding number of ways.
Ken Cheung in the Department of Biostatistics is an expert in artificial intelligence and machine learning, using his expertise to focus on the ever growing volume of information at our fingertips to develop new methods of real-time analysis and optimization.
Cheung has created analyticial methods to test and enhance the personal relevance of IntelliCare, a suite of smartphone apps designed to promote mental health. Each app is based on a clinically proven intervention for anxiety and depression. When users interact with an app, software using artifical intelligence algorithms learns from the user and recommends other apps within the suite that the user might also find userful.
Current Precision Prevention Work:
Cheung aims to enhance the software’s responsiveness by analyzing thousands of seconds of user-interaction data and rewriting the underlying code to leverage the accumulated knowledge of an entire population of users to personalize care. Personalized recommendations will maximize user engagement will enhance the effectiveness of these mental health practices. Cheung's prelimiary algorithm has increased meaningful user interactions by ten sessions per week aompared to earlier versions of the software, with his ultimate goal to have recommendations happen in real time.
These algorithms can be applied more broadly to mine big data for precise, effective interventions tailored to the individual.