Machine learning techniques for mortality prediction in emergency departments: a systematic review

Abstract

ObjectivesThis systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs).DesignA systematic review was performed.SettingThe databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool.ParticipantsAdmitted patients to the ED.Main outcome measureIn-hospital mortality.ResultsFifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction.ConclusionThis review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.

Radiomics Modeling of Catastrophic Proximal Sesamoid Bone Fractures in Thoroughbred Racehorses Using μCT

“…Surprisingly, the log-regression models performed well when compared with more sophisticated ML approaches used in this study. As datasets increase in volume, variety, and velocity in the future, ML methods can offer computational efficiencies and offer decision support tools that are easy to understand and implement [ 29 ].…”

Identification of clinical factors related to prediction of alcohol use disorder from electronic health records using feature selection methods

“…In this study, the SML algorithms learn the classification rules from the selected features. The most commonly employed discriminatory SML algorithms in clinical decision support, i.e., support vector machine (SVM), k-nearest neighbors (KNN), and RF [ 40 , 41 ], were equipped to analyze all selected features and classify them into two classes, AUD-Positive and AUD-Negative. Since one of the aims of this study is to select features for prediction tasks, it is necessary not to focus on a linear classifier but to attempt to map the data to a higher dimensional space where the classification is more accurate.…”

Machine Learning Model-Based Simple Clinical Information to Predict Decreased Left Atrial Appendage Flow Velocity

“…In the current study, we built regression models using various ML algorithms, including the support vector machine (SVM) model, random forest (RF) model, and k-nearest neighbor (KNN) model because they are used widely in regression models [ 18 , 19 , 20 , 21 ]. All models were developed by R 15.6.…”