Minh Le, MD, PhD
he/him/his
Postdoctoral AssociateDownloadHi-Res Photo
Cards
Education
PhD
School of Medicine, Taipei Medical University, Medicine/Cardiology
School of Medicine, Taipei Medical University, Medicine/Cardiology
PGDip
Harvard Medical School, Clinical Research and Epidemiology
Harvard Medical School, Clinical Research and Epidemiology
MD
School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City (YDS), Medicine/Internal Medicine
School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City (YDS), Medicine/Internal Medicine
CarDS
About
Copy Link
Titles
Postdoctoral Associate
Biography
Minh Le, MD, PhD, is a physician-scientist in cardiovascular medicine. He currently serves as a postdoctoral associate under the mentorship of Dr. Rohan Khera - Associate Professor in Cardiovascular Medicine and Health Informatics in the Department of Internal Medicine, Section of Cardiovascular Medicine, at Yale University School of Medicine. He graduated from the School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City (YDS), Vietnam, in 2018 and completed his PhD in Medicine in Taiwan in 2026. His research focuses on large language models, computer vision, machine learning, and deep learning, with applications in cardiology and multimodal imaging, including ECG, ultrasound, CT, MRI, and DSA. He is particularly interested in developing clinically deployable AI systems that improve diagnosis, risk stratification, and clinical decision support.
He is a Harvard Medical School alumnus and completed the Clinical Trials and Epidemiology Program (GCSRT 2022). His capstone project focused on clinical trials in chronic hepatitis patients. During the program, he also worked on several cardiology projects, including STATA-based analyses of the Framingham cohort, genetics and bioinformatics studies, and training in grant and proposal writing.
Before joining Yale, Minh spearheaded collaborative AI projects with institutions including Harvard Medical School, Johns Hopkins, and Carnegie Mellon University. His work, which focuses on real-time imaging interpretation and cardiovascular phenotyping, has been published in JAMA, EClinicalMedicine, IEEE JBHI, IEEE-EMBS, ISBI, ICCV, MICCAI.
Outside of research, Minh enjoys photography, watching movies, and traveling.
Last Updated on January 23, 2026.
Departments & Organizations
Education & Training
- Postdoctoral Associate
- Yale School of Medicine
- PhD
- School of Medicine, Taipei Medical University, Medicine/Cardiology
- PGDip
- Harvard Medical School, Clinical Research and Epidemiology
- MD
- School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City (YDS), Medicine/Internal Medicine
Advanced Training & Certifications
- Global Clinical Scholars Research Training (GCSRT)
- Harvard Medical School (2022)
Research
Copy Link
Overview
Medical Research Interests
Cardiology; Internal Medicine
ORCID
0000-0002-7728-1539- View Lab Website
CarDS
Research at a Glance
Publications Timeline
A big-picture view of Minh Le's research output by year.
11Publications
1,562Citations
Publications
Featured Publications
Protective predictors of cardiovascular disease: an explainable AI approach
Le M, Kha H, Huynh H, Huynh P, Nguyen P, Nguyen D, Le T, Tran N, Bui Q, Pham H, Le H, Duong T, Le N, Vu L, Truong V, Nguyen T, Duong C, Le N. Protective predictors of cardiovascular disease: an explainable AI approach. Public Health 2025, 250: 106050. PMID: 41313957, DOI: 10.1016/j.puhe.2025.106050.Peer-Reviewed Original ResearchMeSH Keywords and ConceptsConceptsCardiovascular diseaseAbsence of diabetesCardiovascular disease careMental health stabilityYounger ageCross-sectional analysisNationally representative survey dataPredictor of cardiovascular diseaseEquitable preventionCardiovascular resilienceRepresentative survey dataHealth stabilitySocioeconomic advantageInsurance coverageRisk scoreHigher incomeDiverse populationsClinical risk scoreProtective factorsProtective predictorAdult recordsDiabetesSurvey dataBRFSSAgeOASIS-Net: An Obstetric Adversarial Semi-Supervised Image Segmentation Network for Cervical and Fetal Head Ultrasound Imaging
Le M, Le T, Nguyen T, Nguyen D, Nguyen H, Le N, Nguyen K, Kha H, Nguyen P, Le H, Huynh H, Ho D, Nguyen T, Nguyen Q, Xu M, Huynh P, Le N. OASIS-Net: An Obstetric Adversarial Semi-Supervised Image Segmentation Network for Cervical and Fetal Head Ultrasound Imaging. IEEE Journal Of Biomedical And Health Informatics 2025, PP: 1-10. PMID: 41370156, DOI: 10.1109/jbhi.2025.3631102.Peer-Reviewed Original ResearchCitationsConceptsSemi-supervised frameworkUltrasound segmentationImage segmentation networkPseudo-labelsConsistency lossSegmentation networkSpeckle noiseConfidence thresholdReal-time clinical useTraining modelLoss weightDiceHigh precisionCervical-lengthIntrapartum monitoringObstetric screeningUltrasound imagingAdversaryClinical useHigh-precision masksNetworkThe Return to Genetic Testing in Women’s Sport—Repeating History Without Evidence
Tran T, Marzouk S, Le M, Huy N. The Return to Genetic Testing in Women’s Sport—Repeating History Without Evidence. JAMA: The Journal Of The American Medical Association 2025, 334: 1795-1796. PMID: 41091502, DOI: 10.1001/jama.2025.18639.Peer-Reviewed Original ResearchCitationsAltmetricDeep Learning-Based Integrated System for Intraoperative Blood Loss Quantification in Surgical Sponges
Nguyen D, Le M, Le T, Charles-Okezie C, Diaz M, Sabet C, Dang H, Nguyen T, Nguyen H, Tran M, Le N, Muncey A, Huynh P. Deep Learning-Based Integrated System for Intraoperative Blood Loss Quantification in Surgical Sponges. IEEE Journal Of Biomedical And Health Informatics 2024, 29: 6342-6352. PMID: 40030353, DOI: 10.1109/jbhi.2024.3499852.Peer-Reviewed Original ResearchCitationsMeSH Keywords and ConceptsConceptsAdvanced hardware componentsAdvanced machine learning modelsMachine learning modelsResNet-18Detection accuracyClassification accuracyTraditional estimation techniquesProcessing imagesHardware componentsLearning modelsSurgical environmentReal-timeSystem robustnessClinical workflowAlgorithmEstimation techniquesBlood loss quantificationTraditional methodsComplex systemsAccuracyIntegrated systemSystem efficacyMass sensorSuccess rateDecision-making processAn in-depth review of AI-powered advancements in cancer drug discovery
Le M, Nguyen P, Nguyen T, Nguyen H, Tam D, Huynh H, Huynh P, Le N. An in-depth review of AI-powered advancements in cancer drug discovery. Biochimica Et Biophysica Acta (BBA) - Molecular Basis Of Disease 2025, 1871: 167680. PMID: 39837431, DOI: 10.1016/j.bbadis.2025.167680.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsCancer drug discoveryPersonalized treatment strategiesDrug discoveryEffective therapyDrug response predictionTreatment strategiesClinical trial optimizationLarge-scale genomic datasetsDrug discovery processTherapeutic target identificationCancer therapeuticsDrugCancerDrug designDrug developmentGenomic datasetsClinical and laboratory factors associated with coronavirus disease 2019 (Covid‐19): A systematic review and meta‐analysis
Minh L, Abozaid A, Ha N, Le Quang L, Gad A, Tiwari R, Nhat‐Le T, Quyen D, AL‐Manaseer B, Kien N, Vuong N, Zayan A, Nhi L, Dila K, Varney J, Huy N. Clinical and laboratory factors associated with coronavirus disease 2019 (Covid‐19): A systematic review and meta‐analysis. Reviews In Medical Virology 2021, 31: e2288. PMID: 34472152, PMCID: PMC8646520, DOI: 10.1002/rmv.2288.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsCitationsAltmetricMeSH Keywords and ConceptsConceptsDeath groupBilateral ground-glass opacificationAcute respiratory distress syndromeSevere-criticallyGroup of non-survivorsRespiratory distress syndromeGround-glass opacificationMild-moderate groupMild-moderate symptomsNon-survivor groupSystematic reviewTreatment of COVID-19 patientsCOVID-19 patientsClinical presentationDistress syndromeComprehensive systematic reviewFollow-upSevere pneumoniaNon-survivorsRadiological imagingEvidence guidelinesPneumoniaSARS coronavirus 2Mortality rateMeta-analysisDengue hemophagocytic syndrome: A systematic review and meta‐analysis on epidemiology, clinical signs, outcomes, and risk factors
Giang H, Banno K, Minh L, Trinh L, Loc L, Eltobgy A, Tai L, Khan A, Tuan N, Reda Y, Samsom M, Nam N, Huy N, Hirayama K. Dengue hemophagocytic syndrome: A systematic review and meta‐analysis on epidemiology, clinical signs, outcomes, and risk factors. Reviews In Medical Virology 2018, 28: e2005. PMID: 30109914, DOI: 10.1002/rmv.2005.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsCitationsAltmetricMeSH Keywords and ConceptsConceptsHemophagocytic syndromeDevelopment of hemophagocytic syndromeLonger fever durationElevated serum ferritinHemophagocytic lymphohistiocytosis patientsBone marrow aspirateLactate dehydrogenase levelsClinical signsFever durationFrequency of clinical signsPersistent thrombocytopeniaHemophagocytic lymphohistiocytosisSerum ferritinCase fatality rateMarrow aspirationSevere dengueDehydrogenase levelsDengue classificationManual search of reference listsDengue hemorrhagic feverCo-InfectionRisk factorsThrombocytopeniaEpidemiological characteristicsRisk difference
2025
DeepGPT-DILI: Integrating Graph Convolutional Networks and Large Language Model Embeddings for Accurate Drug-Induced Liver Injury Prediction
Le M, Huynh U, Ong H, Huynh P, Dinh M, Huynh H, Kha H, Nguyen P, Huynh X, Vo A, Nguyen T, Nguyen T, Nguyen Q, Le N. DeepGPT-DILI: Integrating Graph Convolutional Networks and Large Language Model Embeddings for Accurate Drug-Induced Liver Injury Prediction. Lecture Notes In Computer Science 2025, 16146: 98-106. DOI: 10.1007/978-3-032-07502-4_12.ChaptersConceptsGraph convolutional networkLanguage model embeddingsRecurrent neural networkConvolutional networkNeural networkModel embeddingsNovel deep-learning methodDeep learning methodsMachine learning algorithmsMachine learning modelsGraph inputsLearning algorithmsExtraTrees classifierSMILES stringsLearning methodsLearning modelsGradient boostingPrincipal component analysisNetworkBonding topologyGraphARNNDrug-induced liver injury predictionExtraTreesEmbeddingAI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling.
Le M, Pham H, Nguyen H, Ong H, Kha H, Nguyen P, Nguyen T, Huynh H, Nguyen D, Nguyen T, Vo A, Nguyen T, Nguyen L, Tran T, Le N. AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling. Studies In Health Technology And Informatics 2025, 329: 563-567. PMID: 40775921, DOI: 10.3233/shti250903.Peer-Reviewed Original ResearchCitationsRadiomics in liver research: A paradigm shift in disease detection and staging
Le M, Kha H, Tran N, Nguyen P, Huynh H, Huynh P, Lam H, Le N. Radiomics in liver research: A paradigm shift in disease detection and staging. European Journal Of Radiology Artificial Intelligence 2025, 2: 100016. DOI: 10.1016/j.ejrai.2025.100016.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsCitationsAltmetricConcepts
News
Copy Link
Get In Touch
Copy Link
Locations
CarDS
Lab
100 Church Street South
New Haven, CT 06519