Explainable artificial intelligence model to predict acute critical illness from electronic health records

TLDR

Acute critical illness often follows deterioration of routine vitals, and while existing early warning scores rely on simple weighted metrics, AI models trained on EHR data show high predictive performance yet lack interpretability, hindering clinical adoption. The authors present an explainable AI early warning score (xAI‑EWS) system for early detection of acute critical illness. The xAI‑EWS system delivers predictions alongside explanations derived from EHR data to facilitate clinical translation. Traditional EWSs trade sensitivity for specificity, potentially causing adverse patient outcomes.

Abstract

Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as early warning scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on electronic health records (EHR) trained artificial intelligence (AI) systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. Here, we present an explainable AI early warning score (xAI-EWS) system for early detection of acute critical illness. xAI-EWS potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.