I-Corps: Translation Potential of a Diagnostic Solution to Assess Cognitive Decline

The broader impact of this I-Corps project is based on the development of advanced dementia assessment tools designed to enhance the efficiency of clinical trial patient recruitment and screening processes, thereby accelerating dementia drug development. These tools will enable more precise patient recruitment and reduce screening durations that can currently extend up to 2-years.

These advances could lead to a reduction in both the time and cost associated with developing new dementia therapies. This project aims to provide a scalable, robust assistive tool that enables healthcare professionals to assess cognitive health with greater accuracy. Primary care physicians and other healthcare providers can utilize this tool to efficiently and confidently evaluate patients' cognitive status across three major stages and ten etiologies of dementia.

By addressing the challenges posed by the shortage of neurological healthcare professionals, the tool facilitates earlier diagnosis and intervention, allowing for more tailored and effective care based on the specific type and stage of dementia.

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. The solution is based on the development of a deep learning framework that underpins leading large language models to provide comprehensive probability assessments across various stages of cognitive decline, including normal cognition, mild cognitive impairment, and dementia, as well as across 10 major etiologies, such as Alzheimer's, vascular, and Lewy body diseases.

The model leverages a wide range of routine standard-of-care data, including demographic information, patient medical history, neurological tests, images, and genetic data. Beyond its cutting-edge predictive capabilities, this technology incorporates explainable results, enhancing transparency and allowing for the identification of key features influencing each prediction on an individual basis.

The solution's diagnostic accuracy meets or exceeds that of experienced clinicians, representing a significant advancement in medical artificial intelligence applications.

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.