Comparative Effectiveness of Machine Learning Approaches for Predicting Gastrointestinal Bleeds in Patients Receiving Antithrombotic Treatment
Herrin J, Abraham NS, Yao X, Noseworthy PA, Inselman J, Shah ND, Ngufor C. Comparative Effectiveness of Machine Learning Approaches for Predicting Gastrointestinal Bleeds in Patients Receiving Antithrombotic Treatment. JAMA Network Open 2021, 4: e2110703. PMID: 34019087, PMCID: PMC8140376, DOI: 10.1001/jamanetworkopen.2021.10703.Peer-Reviewed Original ResearchMeSH KeywordsAdolescentAdultAgedAged, 80 and overAnticoagulantsAntifibrinolytic AgentsAtrial FibrillationClinical Decision-MakingCohort StudiesCross-Sectional StudiesFemaleFibrinolytic AgentsGastrointestinal HemorrhageHumansMachine LearningMaleMiddle AgedMyocardial IschemiaPredictive Value of TestsRetrospective StudiesRisk AssessmentThienopyridinesUnited StatesVenous ThromboembolismYoung AdultConceptsGastrointestinal bleedingIschemic heart diseaseCross-sectional studyThienopyridine antiplatelet agentAntithrombotic treatmentVenous thromboembolismAntiplatelet agentsRandom survival forestStudy cohortAtrial fibrillationValidation cohortHeart diseaseHAS-BLED risk scoreRetrospective cross-sectional studyCox proportional hazards regressionHAS-BLED scorePrior GI bleedPatients 18 yearsCohort of patientsEntire study cohortProportional hazards regressionOptumLabs Data WarehouseMedicare Advantage enrolleesPositive predictive valueRisk prediction model