Prediction of in-hospital mortality ofClostriodiodes difficileinfection using critical care database: a big data-driven, machine learning approach

Abstract

Research objectivesClostriodiodes difficile infection (CDI) is a major cause of healthcare-associated diarrhoea with high mortality. There is a lack of validated predictors for severe outcomes in CDI. The aim of this study is to derive and validate a clinical prediction tool for CDI in-hospital mortality using a large critical care database.MethodologyThe demographics, clinical parameters, laboratory results and mortality of CDI were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. We subsequently trained three machine learning models: logistic regression (LR), random forest (RF) and gradient boosting machine (GBM) to predict in-hospital mortality. The individual performances of the models were compared against current severity scores (Clostridiodes difficile Associated Risk of Death Score (CARDS) and ATLAS (Age, Treatment with systemic antibiotics, leukocyte count, Albumin and Serum creatinine as a measure of renal function) by calculating area under receiver operating curve (AUROC). We identified factors associated with higher mortality risk in each model.Summary of resultsFrom 61 532 intensive care unit stays in the MIMIC-III database, there were 1315 CDI cases. The mortality rate for CDI in the study cohort was 18.33%. AUROC was 0.69 (95% CI, 0.60 to 0.76) for LR, 0.71 (95% CI, 0.62 to 0.77) for RF and 0.72 (95% CI, 0.64 to 0.78) for GBM, while previously AUROC was 0.57 (95% CI, 0.51 to 0.65) for CARDS and 0.63 (95% CI, 0.54 to 0.70) for ATLAS. Albumin, lactate and bicarbonate were significant mortality factors for all the models. Free calcium, potassium, white blood cell, urea, platelet and mean blood pressure were present in at least two of the three models.ConclusionOur machine learning derived CDI in-hospital mortality prediction model identified pertinent factors that can assist critical care clinicians in identifying patients at high risk of dying from CDI.

Machine Learning-Based Prediction Models for Clostridioides difficile Infection: A Systematic Review

“…In the study conducted by Ruzicika et al, which focused on predicting CDI recurrence and mortality, the XGBoost ML technique yielded AUROC scores of 0.65 and 0.69, which was similar to LR AUROC scores of 0.63 and 0.68 in the training data set ( 31 ). Similarly, in another study by Du et al, for predicting primary CDI, the AUROC for LR was 0.69, whereas random forest algorithm achieved AUROC of 0.71 and gradient boosting reached 0.72 ( 19 ). Additional information about the various ML models used, and their corresponding AUROC values can be found in Table 3 .…”

“…We identified a total of 1,290 unique citations by our search strategy and 195 after screening of full text. Eventually, a total of 12 studies ( 19 , 28 – 38 ) were included. There was near-perfect agreement between the 2 reviewers (S.M., R.T.) in the inclusion of studies (Cohen k: 0.977, 95% confidence interval: 0.81–1.00).…”

“…The advantage of using ML for risk prediction is the use of sets of variables, which could not be included in scoring systems developed by traditional statistics ( 19 , 20 ). This allows for detecting potential predictors that may have been missed with traditional modeling ( 19 , 20 ).…”

“…The advantage of using ML for risk prediction is the use of sets of variables, which could not be included in scoring systems developed by traditional statistics ( 19 , 20 ). This allows for detecting potential predictors that may have been missed with traditional modeling ( 19 , 20 ). Furthermore, the accuracy and reproducibility of these models can be validated using area under the receiver operating characteristic curve (AUROC) scores before being established into management protocols.…”