Awardee Organization(s): University of Pennsylvania
Principal Investigator(s): Gary Weissman, MD, MSHP
Official Project Title: Advancing Diagnostic Excellence for Older Adults Through Collective Intelligence and Imitation Learning
AITC Partner: PennAITech
Website(s): https://www.med.upenn.edu

Diagnostic errors are common in the primary care setting and lead to direct patient harms, increased healthcare costs, and decrease patient satisfaction. Older adults are especially at risk for such diagnostic errors because of their higher comorbidity burden, medical complexity, increased rates of frailty and cognitive impairment, and decreased representation in clinical datasets and research studies. Artificial intelligence (AI) and machine learning (ML) methods have good face validity for offering clinical decision support (CDS) in this setting to promote diagnostic excellence. However, there is little data to suggest that any particular diagnostic CDS is transparent, reproducible, equitable, and effective at improving the diagnostic process. Therefore, our objective is to create a diagnostic CDS system for use in primary care clinics to facilitate the diagnostic process, present suggestions about important features of the history and exam to consider that are tailored to patient characteristics, and promote diagnostic excellence for older adults. This proposal overcomes existing limitations to training diagnostic CDS systems in primary care where there is a broad diagnostic scope and tremendous clinical uncertainty around training labels. To accomplish this, we will rely on imitation learning and collective intelligence to build AI/ML models that provide predicted suggestions into diagnosis and tests based on expected behaviors from peer clinicians caring for similar patients. These models will be trained using existing data from the electronic health record and deployed in a pilot study across diverse primary care clinics to assess their diagnostic accuracy and acceptability to clinicians, patients, and their caregivers.

View Resource