Donald Wright, MD, MHS
Clinical Fellow of Biomedical Informatics and Data ScienceCards
About
Research
Publications
2026
Impact of an Ambient AI Scribe on Medical Student Objective Structured Clinical Examination Notes: Nonrandomized Clinical Trial
Talwalkar J, Wright D, Schwamm L, Leydon G, Shabanova V. Impact of an Ambient AI Scribe on Medical Student Objective Structured Clinical Examination Notes: Nonrandomized Clinical Trial. JMIR Medical Education 2026, 12: e88264. PMID: 42125891, PMCID: PMC13273210, DOI: 10.2196/88264.Peer-Reviewed Original ResearchThis study investigates the impact of an AI scribe on medical student clinical notes, showing little effect on note quality overall but potential benefits for lower-performing students.Ambient AI Scribes to Create Educational Feedback Notes for Medical Students: Randomized Trial
Talwalkar J, Chartash D, Zhang L, Makutonin M, Safranek C, Sidamon-Eristoff A, Schwamm L, Wright D. Ambient AI Scribes to Create Educational Feedback Notes for Medical Students: Randomized Trial. JMIR Medical Education 2026, 12: e89996. PMID: 42208058, PMCID: PMC13218648, DOI: 10.2196/89996.Peer-Reviewed Original ResearchConceptsIntervention groupTask loadMedical studentsLanguage modelNASA Task Load IndexDevelopment of clinical competenceFeedback notesArtificial intelligenceTask Load IndexFirst-year medical studentsSource transcriptsHuman-onlyCapture toolRandomized to controlDocumentation burdenClinical competenceNarrative feedbackUsabilityMedical educationFactual accuracyWritten feedbackNarrativesTaskInstructor effortVerbal exchangesAmbient AI Scribes to Create Educational Feedback Notes for Medical Students: A Randomized Trial.
Talwalkar JS, Chartash D, Zhang L, Makutonin M, Safranek CW, Sidamon-Eristoff AE, Schwamm LH, Wright DS. Ambient AI Scribes to Create Educational Feedback Notes for Medical Students: A Randomized Trial. JMIR Med Educ 2026 PMID: 42052923, DOI: 10.2196/89996.Peer-Reviewed Original ResearchThis study investigates how ambient AI scribes enhance written feedback quality for medical students, finding improved narrative detail without increasing instructor effort, despite usability challenges.High-Risk Medication Prescriptions Among Older Adults Discharged from the Emergency Department
Iscoe M, Sangal R, Hwang U, Fried T, Meeker D, Conner T, Gettel C, Follman S, Wright D, Venkatesh A. High-Risk Medication Prescriptions Among Older Adults Discharged from the Emergency Department. JAMA Internal Medicine 2026, 186: 483-486. PMID: 41661555, PMCID: PMC12887836, DOI: 10.1001/jamainternmed.2025.7883.Peer-Reviewed Original ResearchThis study investigates high-risk medication prescribing for older adults discharged from emergency departments, showing 6.5% receive potentially inappropriate medications, highlighting opportunities for safer practices.Correction: Real-World Evidence Synthesis of Digital Scribes Using Ambient Listening and Generative Artificial Intelligence for Clinician Documentation Workflows: Rapid Review
Kanaparthy N, Villuendas-Rey Y, Bakare T, Diao Z, Iscoe M, Loza A, Wright D, Safranek C, Faustino I, Brackett A, Melnick E, Taylor R. Correction: Real-World Evidence Synthesis of Digital Scribes Using Ambient Listening and Generative Artificial Intelligence for Clinician Documentation Workflows: Rapid Review. JMIR AI 2026, 5: e93250. PMID: 41824620, PMCID: PMC12986773, DOI: 10.2196/93250.Commentaries, Editorials and LettersSimulated evaluation of large language model stepwise diagnostic reasoning with real-world chest pain encounters and Bayesian networks
Safranek C, Socrates V, Wright D, Huang T, Alashi A, McCann K, Taylor R, Chartash D. Simulated evaluation of large language model stepwise diagnostic reasoning with real-world chest pain encounters and Bayesian networks. BMC Medical Informatics And Decision Making 2026, 26: 97. PMID: 41735989, PMCID: PMC13037032, DOI: 10.1186/s12911-026-03381-9.Peer-Reviewed Original ResearchConceptsBayesian networkRank biased overlapCategory constraintsIterative natureInformation-seeking behaviorInformation-seeking strategiesLanguage modelRobust simulation environmentClinical decision-support toolsSimulation evaluationSimulation environmentProbabilistic frameworkFalse alarmsProbabilistic modelEmergency departmentImage dataResource utilizationDiagnostic reasoningOptimal policyDecision-support toolNetworkDiagnostic decisionsQuery pathwayPhysician practice patternsChest painUsing generative artificial intelligence to standardize unstructured antigen profiles for the alloantibody exchange
McCann K, Wright D, Alvarez E, Sullivan J, Cantrell K, Hauser R. Using generative artificial intelligence to standardize unstructured antigen profiles for the alloantibody exchange. Transfusion 2026, 66: 481-490. PMID: 41481809, DOI: 10.1111/trf.70061.Peer-Reviewed Original Research
2025
AgentMD: Empowering language agents for risk prediction with large-scale clinical tool learning
Jin Q, Wang Z, Yang Y, Zhu Q, Wright D, Huang T, Khandekar N, Wan N, Ai X, Wilbur W, He Z, Taylor R, Chen Q, Lu Z. AgentMD: Empowering language agents for risk prediction with large-scale clinical tool learning. Nature Communications 2025, 16: 9377. PMID: 41130954, PMCID: PMC12549800, DOI: 10.1038/s41467-025-64430-x.Peer-Reviewed Original ResearchConceptsLanguage agentsHealthcare analyticsUnit testsTool learningTool buildersEmergency department notesDissemination challengesClinical calculatorsDiverse setRisk predictionIndividual patient careQuality checksUsabilityUsersPatient careMedical riskLearningCheckingAccuracyRisk managementClinical contextReal-World Evidence Synthesis of Digital Scribes Using Ambient Listening and Generative Artificial Intelligence for Clinician Documentation Workflows: Rapid Review
Kanaparthy N, Villuendas-Rey Y, Bakare T, Diao Z, Iscoe M, Loza A, Wright D, Safranek C, Faustino I, Brackett A, Melnick E, Taylor R. Real-World Evidence Synthesis of Digital Scribes Using Ambient Listening and Generative Artificial Intelligence for Clinician Documentation Workflows: Rapid Review. JMIR AI 2025, 4: e76743. PMID: 41071988, PMCID: PMC12513689, DOI: 10.2196/76743.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsYoung women’s experience of personal recovery following acute myocardial infarction: A qualitative study
Zhu C, Arakaki A, Pan A, Danvers K, Barbardo A, Wyatt J, Wright C, Wright D, Pilote L, Raparelli V, Monin J, Oettingen G, Dreyer R, Pavlo A. Young women’s experience of personal recovery following acute myocardial infarction: A qualitative study. PLOS ONE 2025, 20: e0298798. PMID: 40924702, PMCID: PMC12419669, DOI: 10.1371/journal.pone.0298798.Peer-Reviewed Original ResearchConceptsPersonal recovery frameworkAcute myocardial infarction survivorsYoung women's experiencesAcute myocardial infarctionPersonal recoveryWomen's experiencesAwareness of self-careExperience of acute myocardial infarctionRate of acute myocardial infarctionYoung womenYear post-AMIExperiences of young womenRecovery frameworkIn-depth interviewsSelf-CareMyocardial infarctionYoung women's perspectivesPsychosocial domainsSocial supportQualitative studyWomen's perspectivesSocial rolesPost-AMIPhenomenological approachStudy findings