Artificial intelligence methods are being utilized in radiology, cardiology and other medical specialty fields to quickly and accurately process large quantities of health data to improve the diagnostic and treatment power of health care teams. Compared to other medical specialty fields, primary care physicians deal with a very broad spectrum of illnesses, taking a person-centric approach to care, with fewer diagnostic instruments or tests available. The nature of primary care may pose unique challenges to the meaningful application of AI.
A comprehensive review of 405 studies led by researchers at Western University in Ontario shows that work on AI for primary care is at an early stage of maturity. The scoping review summarizes major trends in primary care AI.
"For the field to mature," the authors note, "value must be placed both on developing rigorous [AI] and on identifying potential impacts...on care delivery and longer-term health outcomes."
"Changing primary care is difficult when only one out of every seven of these papers includes a primary care author," says Winston Liaw, MD MPH and Ioannis A. Kakadiaris, PhD, in an accompanying editorial. "Without input from primary care, these teams may fail to grasp the context of primary care data collection, its role within the health system, and the forces shaping its evolution." Liaw and Kakadiaris lay out seven challenges that primary care AI teams must address in order to move AI forward.
Artificial Intelligence and Primary Care Research: A Scoping Review
Jacqueline K. Kueper, MSc, et al
Western University, Schulich School of Medicine & Dentistry, London, Ontario, Canada
Primary Care Artificial Intelligence: A Branch Hiding in Plain Sight
Winston Liaw, MD, MPH, et al
University of Houston College of Medicine, Department of Health Systems and Population Health Sciences, Houston, Texas