Building Deep Learning Models to Predict Mortality in ICU Patients
This work aims to improve mortality prediction for ICU patients, which is critical for efficient treatment, but it is an incremental improvement on an existing problem.
This paper addresses mortality prediction in ICU patients using deep learning models on time series variables from electronic healthcare records. The models achieved strong performance across precision, recall, F1 score, and AUC on the MIMIC-III dataset.
Mortality prediction in intensive care units is considered one of the critical steps for efficiently treating patients in serious condition. As a result, various prediction models have been developed to address this problem based on modern electronic healthcare records. However, it becomes increasingly challenging to model such tasks as time series variables because some laboratory test results such as heart rate and blood pressure are sampled with inconsistent time frequencies. In this paper, we propose several deep learning models using the same features as the SAPS II score. To derive insight into the proposed model performance. Several experiments have been conducted based on the well known clinical dataset Medical Information Mart for Intensive Care III. The prediction results demonstrate the proposed model's capability in terms of precision, recall, F1 score, and area under the receiver operating characteristic curve.