Deep-Learning Model for Mortality Prediction of ICU Patients with Paralytic Ileus

Abstract

Paralytic Ileus (PI) patients in the Intensive Care Unit (ICU) face a significant risk of death. Current predictive models for PI are often complex and rely on many variables, resulting in unreliable outcomes for such a serious health condition. Predicting mortality in ICU patients with PI is particularly challenging due to the vast amount of data and numerous features involved. To address this issue, a deep-learning predictive framework was developed using the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset, which includes data from 1017 ICU patients with PI. By employing SHAP (SHapley Additive exPlanations) analysis, we were able to narrow down the features to six distinct clinical lab items. The proposed framework, called DLMP (Deep Learning Model for Mortality Prediction of ICU Patients with PI), utilizes these six unique clinical lab items: Anion gap, Platelet, PTT, BUN, Total Bilirubin, and Bicarbonate, along with one demographic variable as inputs to a neural network consisting of only two neuron layers. DLMP achieved an outstanding prediction performance with an AUC score of 0.887, outperforming existing predictive models for ICU patients with PI. The DLMP framework significantly enhances the prediction of mortality for PI patients compared to traditional process mining and machine learning models. This model holds considerable potential for prognosis, enabling families to be better informed about the severity of a patient’s condition and to prepare accordingly. Furthermore, the model is valuable for research purposes and clinical trials.