Sepsis Prediction and Vital Signs Ranking in Intensive Care Unit Patients
This work addresses sepsis prediction for ICU patients, offering a deployable model with strong performance, though it is incremental as it builds on existing methods with a novel ensemble approach.
The paper tackled sepsis detection and prediction in ICU patients using a neural network ensemble model, achieving AUC scores of 0.97, 0.96, and 0.91 for detecting sepsis, severe sepsis, and septic shock, respectively, and 0.90, 0.91, and 0.90 for predicting them four hours in advance.
We study multiple rule-based and machine learning (ML) models for sepsis detection. We report the first neural network detection and prediction results on three categories of sepsis. We have used the retrospective Medical Information Mart for Intensive Care (MIMIC)-III dataset, restricted to intensive care unit (ICU) patients. Features for prediction were created from only common vital sign measurements. We show significant improvement of AUC score using neural network based ensemble model compared to single ML and rule-based models. For the detection of sepsis, severe sepsis, and septic shock, our model achieves an AUC of 0.97, 0.96 and 0.91, respectively. Four hours before the positive hours, it predicts the same three categories with an AUC of 0.90, 0.91 and 0.90 respectively. Further, we ranked the features and found that using six vital signs consistently provides higher detection and prediction AUC for all the models tested. Our novel ensemble model achieves highest AUC in detecting and predicting sepsis, severe sepsis, and septic shock in the MIMIC-III ICU patients, and is amenable to deployment in hospital settings.