DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning

TL;DR

DeepSOFA introduces an interpretable deep learning model that continuously assesses ICU patient severity using streaming data, significantly improving mortality prediction accuracy over traditional static methods.

Contribution

This work presents a novel, interpretable deep learning framework for real-time illness severity assessment that outperforms existing static scoring systems like SOFA.

Findings

DeepSOFA achieved a mean AUC of 0.90 in mortality prediction.

It significantly outperformed baseline SOFA models with AUCs of 0.79 and 0.85.

The model effectively identifies patients needing urgent interventions.

Abstract

Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time-sensitive individual physiological patterns, a critical task in the intensive care unit. We propose a novel acuity score framework (DeepSOFA) that leverages temporal measurements and interpretable deep learning models to assess illness severity at any point during an ICU stay. We compare DeepSOFA with SOFA (Sequential Organ Failure Assessment) baseline models using the same model inputs and find that at any point during an ICU admission, DeepSOFA yields significantly more accurate predictions of in-hospital mortality. A DeepSOFA model developed in a public database and validated in a single institutional cohort had a mean AUC for the entire ICU stay of 0.90 (95% CI 0.90-0.91) compared with baseline SOFA models with mean AUC 0.79 (95% CI 0.79-0.80) and 0.85 (95% CI 0.85-0.86). Deep models are well-suited to identify ICU patients in need of life-saving interventions prior to the occurrence of an unexpected adverse event and inform shared decision-making processes among patients, providers, and families regarding goals of care and optimal resource utilization.