Researchers from Florida International University’s College of Business (FIU Business) have developed a machine learning (ML) algorithm that can diagnose stroke with 83 percent accuracy using hospital and social determinants of health data. This could lead to earlier stroke detection and better patient outcomes, especially among underserved communities. The findings were published in the January 2023 issue of The Journal of Medical Internet Research.

The ML algorithm was developed using emergency department and hospitalization records from Florida hospitals between 2012 and 2014, merged with social determinants of health data from the American Community Survey. The analysis included 143,203 hospital visits of unique patients, with stroke patients tending to be older, have more chronic conditions, and have Medicare as the primary payer.

Stroke is a common and dangerous misdiagnosed medical condition, with timely detection critical to effective management. Patients treated within an hour of the onset of symptoms have a greater chance of surviving and avoiding long-term brain damage. However, data indicates that certain groups, such as Blacks, Hispanics, women, older adults on Medicare, and residents of rural areas, are less likely to be diagnosed during this crucial window.

The ML algorithm helps better diagnose strokes by incorporating a wide range of variables to analyze and interpret complex patterns. As more data is added, the algorithm continues to learn and improve. If a hospital uses the algorithm, an automated, computer-assisted screening tool will quickly analyze all patient information and trigger a pop-up alert to alert the emergency department team if a patient is at high risk for stroke.

This type of technology is currently undergoing pilot testing in the emergency departments of several major healthcare systems. Current ML methods have focused on interpreting clinical notes and diagnostic imaging results, which may not be available when a patient arrives at a hospital, particularly in rural and underserved communities.

Min Chen, associate professor of information systems and business analytics at FIU Business and one of the researchers, said, “Our algorithm can incorporate a lot of variables to analyze and interpret complex patterns, which will allow emergency department care teams to make better and faster decisions.” Chen conducted the study with Professors Xuan Tan of Clara University and Rema Padman of Carnegie Mellon University.

Learn more in the press release here.

Subscribe to Our Newsletter

We keep your data private and share your data only with third parties that make this service possible. See our Privacy Policy for more information.