Early Prediction of Patient Mortality Based on Routine Laboratory Tests and Predictive Models in Critically Ill Patients

Abstract

We propose a method for quantitative analysis of predictive power of laboratory tests and early detection of mortality risk by usage of predictive models and feature selection techniques. Our method allows automatic feature selection, model selection, and evaluation of predictive models. Experimental evaluation was conducted on patients with renal failure admitted to ICUs (medical intensive care, surgical intensive care, cardiac, and cardiac surgery recovery units) at Boston's Beth Israel Deaconess Medical Center. Data are extracted from Multi parameter Intelligent Monitoring in Intensive Care III (MIMIC-III) database. We built and evaluated different single (e.g. Logistic regression) and ensemble (e.g. Random Forest) learning methods. Results revealed high predictive accuracy (area under the precision-recall curve (AUPRC) values >86%) from day four, with acceptable results on the second (>81%) and third day (>85%). Random forests seem to provide the best predictive accuracy. Feature selection techniques Gini and ReliefF scored best in most cases. Lactate, white blood cells, sodium, anion gap, chloride, bicarbonate, creatinine, urea nitrogen, potassium, glucose, INR, hemoglobin, phosphate, total bilirubin, and base excess were most predictive for hospital mortality. Ensemble learning methods are able to predict hospital mortality with high accuracy, based on laboratory tests and provide ranking in predictive priority.

An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application

“…Thus, remarkable studies have emerged for both RF and MIMIC databases. Poucke et al [6] concentrate on quantitative analysis of the predictive power of laboratory tests and early detection of mortality risk by using predictive models and feature selection techniques in the MIMIC-III database. RF and logistic regression were used on patients with renal failure admitted to ICUs at Boston's Beth Israel Deaconess Medical Center.…”

“…It is a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. Random forest (RF) has been used in biology and medicine, such as high-dimensional genetic or tissue microarray data and MIMIC-III [1][2][3][4][5][6]. It is specifically devised to operate quickly and efficiently over large datasets because of the simplification and it offers the highest prediction accuracy compared to other models in the setting of classification.…”

The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers

“…Machine learning prediction models were shown to accurately predict patient outcome in several clinical situations, such as cardiac and general surgeries[ 15 , 16 ], ICU admissions, initiation of dialysis [ 17 , 18 ], etc. The majority of described infection predicting models focused on estimating the aggregated risk.…”