AI Gone Astray: Technical Supplement
This addresses patient safety issues by highlighting performance degradation in medical AI models over time, though it is incremental as it supplements prior work.
The study investigated how time drift affects clinically deployed machine learning models for sepsis prediction, finding that an RNN model's performance degraded from 0.729 AUC to 0.525 AUC over a decade.
This study is a technical supplement to "AI gone astray: How subtle shifts in patient data send popular algorithms reeling, undermining patient safety." from STAT News, which investigates the effect of time drift on clinically deployed machine learning models. We use MIMIC-IV, a publicly available dataset, to train models that replicate commercial approaches by Dascena and Epic to predict the onset of sepsis, a deadly and yet treatable condition. We observe some of these models degrade overtime; most notably an RNN built on Epic features degrades from a 0.729 AUC to a 0.525 AUC over a decade, leading us to investigate technical and clinical drift as root causes of this performance drop.