Thomas Durant, MD
Associate Professor of Laboratory MedicineCards
About
Titles
Associate Professor of Laboratory Medicine
Medical Director, Chemical Pathology, Laboratory Medicine; Medical Director, Laboratory Informatics, Laboratory Medicine; Associate Director, ACGME Chemical Pathology Fellowship, Laboratory Medicine; Medical Director, Immunology, Laboratory Medicine
Biography
Dr. Thomas Durant is an Associate Professor of Laboratory Medicine and Biomedical Informatics and Data Science at the Yale School of Medicine. He is the Medical Director of Chemical Pathology, Clinical Immunology, and Laboratory Informatics at Yale-New Haven Hospital and the Associate Director for the ACGME Chemical Pathology Fellowship. Dr. Durant's research embodies a practical approach, concentrating on quality care initiatives, laboratory outcomes, statistics, machine learning, and artificial intelligence applications in pathology and clinical laboratory medicine. His primary research interests lie in clinical informatics and the innovative use of data management technology to extract valuable insights into laboratory quality and overall operations for enhanced patient care. Among his ongoing projects are investigations into stream processing of interface data for automated sample identification for subsequent biobanking, as well as machine learning endeavors such as the utilization of 'very deep' convolutional neural networks for the automated classification of digital images obtained in clinical laboratories, graph neural networks, and quantum machine learning.
Appointments
Laboratory Medicine
Associate Professor on TermPrimaryBiomedical Informatics & Data Science
Associate Professor on TermSecondary
Other Departments & Organizations
Education & Training
- Winchester Clinical Microbiology Fellow
- Yale-New Haven Hospital (2019)
- Resident
- Yale-New Haven Hospital (2018)
- Chief Resident
- Yale-New Haven Hospital (2018)
- MD
- University of Connecticut, School of Medicine (2015)
- MA
- Quinnipiac University, Physical Therapy
- BA
- Quinnipiac University, Health Sciences (2008)
Research
Publications
Featured Publications
A primer for quantum computing and its applications to healthcare and biomedical research
Durant T, Knight E, Nelson B, Dudgeon S, Lee S, Walliman D, Young H, Ohno-Machado L, Schulz W. A primer for quantum computing and its applications to healthcare and biomedical research. Journal Of The American Medical Informatics Association 2024, 31: 1774-1784. PMID: 38934288, PMCID: PMC11258415, DOI: 10.1093/jamia/ocae149.Peer-Reviewed Original ResearchApplications of Digital Microscopy and Densely Connected Convolutional Neural Networks for Automated Quantification of Babesia-Infected Erythrocytes
Durant TJS, Dudgeon SN, McPadden J, Simpson A, Price N, Schulz WL, Torres R, Olson EM. Applications of Digital Microscopy and Densely Connected Convolutional Neural Networks for Automated Quantification of Babesia-Infected Erythrocytes. Clinical Chemistry 2021, 68: 218-229. PMID: 34969114, PMCID: PMC12928752, DOI: 10.1093/clinchem/hvab237.Peer-Reviewed Original ResearchVery Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes
Durant T, Olson EM, Schulz WL, Torres R. Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes. Clinical Chemistry 2017, 63: 1847-1855. PMID: 28877918, DOI: 10.1373/clinchem.2017.276345.Peer-Reviewed Original ResearchConceptsConvolutional neural networkNeural networkDeep convolutional neural networkDense shortcut connectionsNeural network designSlow manual processSignificant labor costsClassification of erythrocytesWeb applicationCapable machinesUnseen dataShortcut connectionsManual processEnsemble model predictionsDigital imagesPrecision metricsArchitectural considerationsNetwork designAutomated profilingClassification frequencyMisclassification errorPractical performanceFinal databaseHarmonic meanNetwork
2026
Intraoperative tissue aspirate testing: A single-center experience and evaluation of criteria for parathyroid tissue confirmation
Kodger J, Merchant N, El-Khoury J, Ogilvie J, Ramirez A, Durant T. Intraoperative tissue aspirate testing: A single-center experience and evaluation of criteria for parathyroid tissue confirmation. Clinica Chimica Acta 2026, 588: 120981. PMID: 41876081, DOI: 10.1016/j.cca.2026.120981.Peer-Reviewed Original ResearchParathyroid tissueBiochemical cureParathyroid hormoneDiagnostic performanceIntraoperative measurement of parathyroid hormoneIntraoperative measurementsMeasurement of parathyroid hormoneBiochemical cure ratesRemoval of parathyroid tissueSingle-center experienceParathyroid hormone measurementTissue confirmationPrimary hyperparathyroidismAdenoma casesHistopathological diagnosisSerum calciumPTH ratioCure rateDiagnostic accuracyAdjunctive techniquesPatientsExcised tissueClinical practiceParathyroidectomySix-monthsQuantum Machine Learning and Data Re-Uploading: Evaluation on Benchmark and Laboratory Medicine Data Sets
Durant TJS, Lee SJ, Dudgeon SN, Knight E, Nelson B, Young HP, Ohno-Machado L, Schulz WL. Quantum Machine Learning and Data Re-Uploading: Evaluation on Benchmark and Laboratory Medicine Data Sets. Clinical Chemistry 2026, hvaf192. DOI: 10.1093/clinchem/hvaf192.Peer-Reviewed Original ResearchQuantum Machine Learning and Data Re-Uploading: Evaluation on Benchmark and Laboratory Medicine Data Sets
Durant T, Lee S, Dudgeon S, Knight E, Nelson B, Young H, Ohno-Machado L, Schulz W. Quantum Machine Learning and Data Re-Uploading: Evaluation on Benchmark and Laboratory Medicine Data Sets. Clinical Chemistry 2026, 72: 451-460. PMID: 41728802, DOI: 10.1093/clinchem/hvaf192.Peer-Reviewed Original ResearchQuantum machine learningReal-world healthcare dataMachine learningClassification performanceML algorithmsQuantum machine learning methodsComparison of classification performanceData setsBenchmark data setsLow-dimensional dataClassical machine learningInput dimensionalityRe-uploadingF1 scoreF-scoreClassic algorithmConfiguration parametersAlgorithmAlgorithm developmentLinear algorithmQuantum hardwareImpact of optimismQuantum machinesBaseline comparisonLearningValidating CALIPER pediatric reference intervals in a U.S. population using retrospective outpatient data and RefineR
Kodger J, Durant T, Yurtsever N, El-Khoury J. Validating CALIPER pediatric reference intervals in a U.S. population using retrospective outpatient data and RefineR. Clinica Chimica Acta 2026, 584: 120846. PMID: 41565092, DOI: 10.1016/j.cca.2026.120846.Peer-Reviewed Original ResearchThis study investigates the applicability of CALIPER pediatric reference intervals in a diverse U.S. population, showing RefineR provides more accurate and practical results than CLSI guidelines.
2025
Reevaluating the Threshold for Low Total Testosterone
Arun A, Durant T, El-Khoury J, Krumholz H. Reevaluating the Threshold for Low Total Testosterone. Clinical Chemistry 2025, 71: 609-611. PMID: 40238540, DOI: 10.1093/clinchem/hvaf025.Peer-Reviewed Original ResearchAutomated Quality Assurance Rules for Liquid Chromatography–Mass Spectrometry Testing in a Clinical Laboratory
Cassella-Mclane G, McGowan M, Kodger J, Durant T. Automated Quality Assurance Rules for Liquid Chromatography–Mass Spectrometry Testing in a Clinical Laboratory. Clinics In Laboratory Medicine 2025, 45: 221-232. PMID: 40348434, DOI: 10.1016/j.cll.2025.01.006.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsConceptsCollege of American PathologistsClinical Laboratory Improvement AmendmentsClinical benefit to patientsTherapeutic drug monitoringBenefits to patientsDrug monitoringLiquid chromatography-tandem mass spectrometryClinical laboratoriesLC-MS/MSChromatography-tandem mass spectrometryAmerican PathologistsDietary monitoringClinicData reviewBiochemical geneticsSpectrometry testCLSIMass spectrometryPatientsReviewEndocrinology
2024
Prospective and External Validation of an Ensemble Learning Approach to Sensitively Detect Intravenous Fluid Contamination in Basic Metabolic Panels
Spies N, Militello L, Farnsworth C, El-Khoury J, Durant T, Zaydman M. Prospective and External Validation of an Ensemble Learning Approach to Sensitively Detect Intravenous Fluid Contamination in Basic Metabolic Panels. Clinical Chemistry 2024, 71: 296-306. PMID: 39545815, DOI: 10.1093/clinchem/hvae168.Peer-Reviewed Original ResearchSHapley Additive exPlanationsLearning approachDetection of contamination eventsUnsupervised learning approachLearning-based methodsMachine learning-based methodsEnsemble learning approachMachine learning pipelineEnsemble learningLearning pipelineMatthews correlation coefficientAlgorithmic fairnessReal worldSHapley Additive exPlanations valuesCurrent workflowsClinical workflowWorkflowOperational burdenBasic metabolic panelIntravenous (IVPipelineInternal validation setValidation setFlagging ratesPerformance assessment
Teaching & Mentoring
News
News
Get In Touch
Contacts
Laboratory Medicine
55 Park Street
New Haven, CT 06510
United States