I-Corps: Translation Potential of a Digital Phenotyping Tool to Improve Diagnostic Accuracy of Chronic Pain

This I-Corps project focuses on the development of a digital tool to better diagnose chronic pain, which affects over 100 million adults in the United States and contributes to an estimated $560–$635 billion annually in lost productivity and healthcare costs. Misdiagnosis or delayed treatment can lead to serious problems, including unnecessary reliance on opioid medications. Currently, doctors mostly depend on patient self-reports and their own judgment, but that doesn’t always give the full picture of the need for pain medications. Some patients struggle to communicate their pain, and important biological signals—like heart rate and hormone levels—often go unnoticed. This solution is an artificial intelligence system that can analyze multiple sources of information, including language, behavior, and biological data, to provide more accurate insights. By improving diagnosis, the technology aims to reduce ineffective treatments and contribute to a more scientific approach to managing chronic pain.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of a digital phenotyping platform that combines natural language processing, machine learning algorithms, and metabolic signal analysis to identify patterns in chronic pain expression. The system analyzes patient-generated language, behavioral patterns such as daily activity and self-management strategies, and physiological signals such as glucose variability to generate a multidimensional profile of the pain experience. This integrated approach advances current assessment methods by incorporating linguistic and biological dimensions often overlooked in conventional tools. The platform supports clinical decision making by providing real-time, individualized insights and has applications in electronic records integration, population-level analytics, and data-informed personalized care. This research contributes to the development of scalable, high-impact tools for improving diagnostic accuracy and system efficiency in pain management.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Award Number: 2521912
Principal Investigator: ShinYe Kim
Funds Obligated: $50,000
State: WI