Machine learning analysis to identify the association between risk factors and onset of nosocomial diarrhea: a retrospective cohort study

Abstract

BackgroundAlthough several risk factors for nosocomial diarrhea have been identified, the detail of association between these factors and onset of nosocomial diarrhea, such as degree of importance or temporal pattern of influence, remains unclear. We aimed to determine the association between risk factors and onset of nosocomial diarrhea using machine learning algorithms.MethodsWe retrospectively collected data of patients with acute cerebral infarction. Seven variables, including age, sex, modified Rankin Scale (mRS) score, and number of days of antibiotics, tube feeding, proton pump inhibitors, and histamine 2-receptor antagonist use, were used in the analysis. We split the data into a training dataset and independant test dataset. Based on the training dataset, we developed a random forest, support vector machine (SVM), and radial basis function (RBF) network model. By calculating an area under the curve (AUC) of the receiver operating characteristic curve using 5-fold cross-validation, we performed feature selection and hyperparameter optimization in each model. According to their final performances, we selected the optimal model and also validated it in the independent test dataset. Based on the selected model, we visualized the variable importance and the association between each variable and the outcome using partial dependence plots.ResultsTwo-hundred and eighteen patients were included. In the cross-validation within the training dataset, the random forest model achieved an AUC of 0.944, which was higher than in the SVM and RBF network models. The random forest model also achieved an AUC of 0.832 in the independent test dataset. Tube feeding use days, mRS score, antibiotic use days, age and sex were strongly associated with the onset of nosocomial diarrhea, in this order. Tube feeding use had an inverse U-shaped association with the outcome. The mRS score and age had a convex downward and increasing association, while antibiotic use had a convex upward association with the outcome.ConclusionWe revealed the degree of importance and temporal pattern of the influence of several risk factors for nosocomial diarrhea, which could help clinicians manage nosocomial diarrhea.

Developing Action Plans Based on Machine Learning Analysis to Prevent Sick Leave in a Manufacturing Plant

“…Thereafter, we developed the final model using all data with 1:4 random undersampling. The association between important variables, which were determined by variable importance based on the Gini index, and the incidence of sick leave was visualized through partial dependence plots 19 . All analyses were conducted using R version 4.1.1.…”

“…Machine learning models can provide the relative importance of predictor variables and reveal nonlinear and nonmonotonic associations between the outcome and variables through partial dependence plots. 19 The variable importance can lead to prioritizing countermeasures to prevent sick leaves. In addition, the ability to reveal such nonlinear and nonmonotonic associations can waive the requirement for using a pre-determined cutoff.…”

“…These findings from the previous project led us to hypothesize that machine learning models are suitable for resolving these limitations. Machine learning models can provide the relative importance of predictor variables and reveal nonlinear and nonmonotonic associations between the outcome and variables through partial dependence plots 19 . The variable importance can lead to prioritizing countermeasures to prevent sick leaves.…”

A decision tree prediction model for a short-term outcome of delirium in patients with advanced cancer receiving pharmacological interventions: A secondary analysis of a multicenter and prospective observational study (Phase-R)

“…It has high interpretability because of its complete visualization of prediction rules. Although other machine learning models, such as random forest, can partially visualize influences of predictors (Kurisu et al, 2019; Roger et al, 2020; Tamune et al, 2020), this complete visualization is specific to a decision tree and enables clinicians to utilize the model without software.…”

Developing cardiometabolic risk classifiers for youth using handgrip strength, anthropometrics, and demographics: a machine learning approach leveraging National Health and Nutrition Examination Survey Data

“…Although studies have approached prediction problems using predetermined classi cation methods, inherent peculiarities around shared contexts (e.g., ecological and sociocultural) suggest it may be important to explore several models and identify the best performing ones for the speci c problem and dataset. Further, there are no theoretical methods to determine the sample size required to effectively train machine learning models [33]. These dataset attributes underlie variations in performances between different classi cation algorithms and methods.…”