biostudies-literaturePark JINCATS NIH HHS278-287https://www.ebi.ac.uk/biostudies/studies/S-EPMC8568050biostudies-literatureUnknown53(3)<h4>Purpose</h4>The aim of the study was to develop and validate machine learning models to predict the personalized risk for 30-day readmission with venous thromboembolism (VTE).<h4>Design</h4>This study was a retrospective, observational study.<h4>Methods</h4>We extracted and preprocessed the structured electronic health records (EHRs) from a single academic hospital. Then we developed and evaluated three prediction models using logistic regression, the balanced random forest model, and the multilayer perceptron.<h4>Results</h4>The study sample included 158,804 total admissions; VTE-positive cases accounted for 2,080 admissions from among 1,695 patients (1.31%). Based on the evaluation results, the balanced random forest model outperformed the other two risk prediction models.<h4>Conclusions</h4>This study delivered a high-performing, validated risk prediction tool using machine learning and EHRs to identify patients at high risk for VTE after discharge.<h4>Clinical relevance</h4>The risk prediction model developed in this study can potentially guide treatment decisions for discharged patients for better patient outcomes.Journal of nursing scholarship : an official publication of Sigma Theta Tau International Honor Society of NursingPersonalized Risk Prediction for 30-Day Readmissions With Venous Thromboembolism Using Machine Learning.PMC8568050UL1 TR001414Zheng KKim DPark JILee JAAmin AfalsePersonalized Risk Prediction for 30-Day Readmissions With Venous Thromboembolism Using Machine Learning.<h4>Purpose</h4>The aim of the study was to develop and validate machine learning models to predict the personalized risk for 30-day readmission with venous thromboembolism (VTE).<h4>Design</h4>This study was a retrospective, observational study.<h4>Methods</h4>We extracted and preprocessed the structured electronic health records (EHRs) from a single academic hospital. Then we developed and evaluated three prediction models using logistic regression, the balanced random forest model, and the multilayer perceptron.<h4>Results</h4>The study sample included 158,804 total admissions; VTE-positive cases accounted for 2,080 admissions from among 1,695 patients (1.31%). Based on the evaluation results, the balanced random forest model outperformed the other two risk prediction models.<h4>Conclusions</h4>This study delivered a high-performing, validated risk prediction tool using machine learning and EHRs to identify patients at high risk for VTE after discharge.<h4>Clinical relevance</h4>The risk prediction model developed in this study can potentially guide treatment decisions for discharged patients for better patient outcomes.2021-01-01T00:00:00Z2021 May2025-04-04T19:57:54.236Z2025-04-04T19:57:54.236ZS-EPMC85680503361768910.1111/jnu.12637