The traditional, manual screening process of hundreds to thousands of applications is not only a laborious undertaking, but can also have personal bias and variability among reviewers.
To mitigate those problems, AI technologies are conducting initial screenings at the Zucker School of Medicine at Hofstra University/Northwell in Hempstead, N.Y., and NYU Grossman School of Medicine in New York City, the AAMC reported Jan. 21.
Others are developing AI platforms to launch pilots within one to two years, including the University of Cincinnati College of Medicine and the George Washington (D.C.) University School of Medicine and Health Sciences.
The University of California San Diego’s medical school is having conversations about the technique. Last year, its admissions team had to whittle 5,000 applicants down to 180 accepted students.
To streamline this task, the San Diego-based school is working to create an AI system that detects traits. For example, rather than simply scanning for the term “service,” the tool would read an application and seek signals for qualities like conscientiousness.
Also, rather than spending 30 minutes per application, an AI platform can read an application within seconds and apply the same standards to each.
To achieve this, AI systems are trained with thousands of former applications, said Ioannis Koutroulis, MD, PhD, associate dean of MD admissions at the GW School of Medicine and Health Sciences.
“If I tell the system, ‘I want you to look for service, volunteer, work, public health,’ the system needs to learn how to identify those in the experiences section of the application,” Dr. Koutroulis told AAMC. “It takes [inputting] years of applications for the system to learn how to identify what you’re looking for.”