PPMF: A Patient-based Predictive Modeling Framework for Early ICU Mortality Prediction
This work addresses the challenge of early ICU mortality prediction for healthcare providers, offering an incremental improvement over existing methods.
The paper tackles early ICU mortality prediction by proposing a patient-based predictive modeling framework (PPMF) that captures dynamic patient changes, uses local approximation for classification, and updates feature weights with gradient descent, achieving significant performance improvements over severity score systems, aggregation-based classifiers, and baseline feature selection methods on MIMICIII data.
To date, developing a good model for early intensive care unit (ICU) mortality prediction is still challenging. This paper presents a patient based predictive modeling framework (PPMF) to improve the performance of ICU mortality prediction using data collected during the first 48 hours of ICU admission. PPMF consists of three main components verifying three related research hypotheses. The first component captures dynamic changes of patients status in the ICU using their time series data (e.g., vital signs and laboratory tests). The second component is a local approximation algorithm that classifies patients based on their similarities. The third component is a Gradient Decent wrapper that updates feature weights according to the classification feedback. Experiments using data from MIMICIII show that PPMF significantly outperforms: (1) the severity score systems, namely SASP III, APACHE IV, and MPM0III, (2) the aggregation based classifiers that utilize summarized time series, and (3) baseline feature selection methods.