Predicting physician departure with machine learning on EHR use patterns: A longitudinal cohort from a large multi-specialty ambulatory practice
Lopez K, Li H, Paek H, Williams B, Nath B, Melnick E, Loza A. Predicting physician departure with machine learning on EHR use patterns: A longitudinal cohort from a large multi-specialty ambulatory practice. PLOS ONE 2023, 18: e0280251. PMID: 36724149, PMCID: PMC9891518, DOI: 10.1371/journal.pone.0280251.Peer-Reviewed Original ResearchConceptsElectronic health recordsEHR use patternsHealthcare industryPhysician departureSHAP valuesHealth recordsPhysician characteristicsLongitudinal cohortPhysician ageRisk physiciansAmbulatory practiceTargeted interventionsAppropriate interventionsPhysiciansTop variablesDocumentation timePhysician turnoverPredictive modelHeavy burdenInterventionInboxPhysician demandMachineValidatingPatientsRacial and ethnic disparities in emergency department–initiated buprenorphine across five health care systems
Holland W, Li F, Nath B, Jeffery M, Stevens M, Melnick E, Dziura J, Khidir H, Skains R, D'Onofrio G, Soares W. Racial and ethnic disparities in emergency department–initiated buprenorphine across five health care systems. Academic Emergency Medicine 2023, 30: 709-720. PMID: 36660800, PMCID: PMC10467357, DOI: 10.1111/acem.14668.Peer-Reviewed Original ResearchConceptsOpioid use disorderCommunity emergency departmentsEmergency departmentDischarge diagnosisHealth care systemHispanic patientsBlack patientsHospital typeCare systemNon-Hispanic patientsOpioid overdose deathsClinical decision support systemOpioid withdrawalPrimary outcomeMedication treatmentBuprenorphine accessED treatmentTreatment accessOverdose deathsX-waiverBuprenorphinePatientsUse disordersEthnic disparitiesSecondary analysis