Assessment of a Deep Learning Model Based on Electronic Health Record Data to Forecast Clinical Outcomes in Patients With Rheumatoid Arthritis

Key Points

Question How accurately can artificial intelligence models prognosticate future patient outcomes for a complex disease, such as rheumatoid arthritis?

Findings  In this prognostic study of 820 patients with rheumatoid arthritis, a longitudinal deep learning model had strong performance in a test cohort of 116 patients, whereas baselines that used each patient’s most recent disease activity score had statistically random performance.

Meaning  The findings suggest that building accurate models to forecast complex disease outcomes using electronic health records is possible.

Prosegui la lettura su “Jama Network“