Diagnostic Codes in AI Prediction Models and Label Leakage of Same-Admission Clinical Outcomes

This prognostic study of the MIMIC-IV database suggests that using ICD codes as features in same-admission prediction models may be a severe methodological flaw associated with inflated performance metrics, rendering models incapable of clinically useful predictions. The literature review found that the practice is common. Addressing this challenge is essential for advancing trustworthy artificial intelligence in health care.