Personalized health experiments to optimize well-being and enable scientific discovery

Abstract

Nearly one quarter of US adults read patient-generated health information found on blogs, forums and social media; many say they use this information to influence everyday health decisions. Topics of discussion in online forums are often poorly-addressed by existing, high-quality clinical research, so patient's anecdotal experiences provide the only evidence. No method exists to help patients use this evidence to make decisions about their own care. My research aims to bridge the massive gap between clinical research and anecdotal evidence by putting the tools of science into the hands of patients. Specifically, I will enable patient communities to convert anecdotes into structured self-experiments that apply to their daily lives. A self-experiment, a sub-type of the single-subject (N-of-1) trial, can quantify the effectiveness of a lifestyle intervention on one patient. The patient's challenge is deciding which of many possible experiments to try given the information available. A recommender system will aggregate experimental outcomes and background information from many patients to recommend experiments for each individual. Unusual interventions that succeed over many trials become evidence to motivate future clinical research.