{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Mohammed H"],"funding":["Zimmer Biomet","Syapse Inc","NIMHD NIH HHS","SGM Consulting LLC","National Institute on Minority Health and Health Disparities of the National Institutes of Health"],"pagination":["e0263897"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8939835"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["17(3)"],"pubmed_abstract":["<h4>Background</h4>Predictive models could help clinicians identify risk factors that cause adverse events after total knee arthroplasty (TKA), allowing for appropriate preoperative preventive interventions and allocation of resources.<h4>Methods</h4>The National Inpatient Sample datasets from 2010-2014 were used to build Logistic Regression (LR), Gradient Boosting Method (GBM), Random Forest (RF), and Artificial Neural Network (ANN) predictive models for three clinically relevant outcomes after TKA-disposition at discharge, any post-surgical complications, and blood transfusion. Model performance was evaluated using the Brier scores as calibration measures, and area under the ROC curve (AUC) and F1 scores as discrimination measures.<h4>Results</h4>GBM-based predictive models were observed"],"journal":["PloS one"],"pubmed_title":["Utilization of machine learning methods for predicting surgical outcomes after total knee arthroplasty."],"pmcid":["PMC8939835"],"funding_grant_id":["R01 MD013901","R01MD013901"],"pubmed_authors":["Memtsoudis S","Huang Y","Parks M","Ma Y","Mohammed H"],"additional_accession":[]},"is_claimable":false,"name":"Utilization of machine learning methods for predicting surgical outcomes after total knee arthroplasty.","description":"<h4>Background</h4>Predictive models could help clinicians identify risk factors that cause adverse events after total knee arthroplasty (TKA), allowing for appropriate preoperative preventive interventions and allocation of resources.<h4>Methods</h4>The National Inpatient Sample datasets from 2010-2014 were used to build Logistic Regression (LR), Gradient Boosting Method (GBM), Random Forest (RF), and Artificial Neural Network (ANN) predictive models for three clinically relevant outcomes after TKA-disposition at discharge, any post-surgical complications, and blood transfusion. Model performance was evaluated using the Brier scores as calibration measures, and area under the ROC curve (AUC) and F1 scores as discrimination measures.<h4>Results</h4>GBM-based predictive models were observed","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-21T16:45:24.531Z","creation":"2025-04-21T16:45:24.531Z"},"accession":"S-EPMC8939835","cross_references":{"pubmed":["35316270"],"doi":["10.1371/journal.pone.0263897"]}}