Aline Pedroso, PhD
Associate Research ScientistAbout
Titles
Associate Research Scientist
Lead, Scientific Operations, Cardiovascular Data Science (CarDS) Lab
Biography
Dr. Aline Pedroso is an epidemiologist and is the Lead for Scientific Operations at the Cardiovascular Data Science (CarDS) Lab at the Yale School of Medicine. Her research focuses on large-scale studies on cardiovascular risk assessment, particularly in low-resource settings. She also works on studying existing and emerging practices and health policies and their effectiveness in improving patient outcomes. In addition, as the operations lead at the CarDS Lab, she is involved in the design and execution of multicenter studies that deploy digital health and artificial intelligence tools for improving the detection and prognostication of cardiovascular diseases. She manages a broad research portfolio at the CarDS Lab, working with a large interdisciplinary team of clinician-scientists and data scientists for the design of innovative health technologies, and manages partnerships with academic, pharmaceutical, and industry partners.
Last Updated on July 08, 2026.
Departments & Organizations
Education & Training
- Postdoctoral Research Associate
- Cardiovascular Data Science (CarDS) Lab (2024)
- PhD
- Federal University of Sao Joao del Rei, Health Sciences (2024)
- Postgraduate Associate
- Cardiovascular Data Science (CarDS) Lab (2023)
- MS
- Federal University of Sao Joal del Rei, Health Sciences (2019)
- BSc
- Federal University of Vales do Jequitinhonha e Mucuri, Pharmacy (2014)
Research
Publications
2026
Wearable Devices and Data Sharing in the US
Pedroso A, Dhingra L, Aminorroaya A, Khera R. Wearable Devices and Data Sharing in the US. JAMA Network Open 2026, 9: e2617733. PMID: 42268609, PMCID: PMC13254737, DOI: 10.1001/jamanetworkopen.2026.17733.Peer-Reviewed Original ResearchConceptsHealth Information National Trends SurveyPopulation-based surveyUS adultsWearable device useSociodemographic subgroupsCardiovascular diseaseCommunity-dwelling US adultsRisk factorsWearable useNational Trends SurveyDevice useHealth care toolCVD risk factorsSurvey studyUS adult populationPotential of wearable devicesWearable dataPersonal health informationDaily useSharing of personal health informationAssociated with greater willingnessSubgroups of ageData sharingWearable devicesTrends SurveyThe Evolving Utility of Artificial Intelligence-Based Tools for the Detection of Heart Failure and Cardiomyopathies: From Potential to Implementation
Croon P, Dhingra L, Pedroso A, Khera R. The Evolving Utility of Artificial Intelligence-Based Tools for the Detection of Heart Failure and Cardiomyopathies: From Potential to Implementation. Current Heart Failure Reports 2026, 23: 25. PMID: 42165933, DOI: 10.1007/s11897-026-00764-x.Peer-Reviewed Original ResearchConceptsImplementation of AIArtificial intelligence-based toolsLanguage modelElectronic health recordsWearable devicesWorkflow integrationReviewArtificial intelligenceClinician adoptionHealth recordsDetection of heart failureImplementationModel developmentInteroperabilityWearableDeploymentPractical frameworkIntelligenceDetectionWorkflowAIHeart failure careHeart failureOptimizationReal-world evidence for comparative safety of second-line antihyperglycemic agents in older adults with type 2 diabetes
Kim C, Bu F, Blacketer C, Ostropolets A, Duarte-Salles T, Viernes B, Falconer T, Pistillo A, Li J, Yin C, Van Zandt M, Nagy P, Nishimura A, Minty E, You S, Sawano M, Sawano S, Jeon J, Aminorroaya A, Dhingra L, Pedroso A, Thangaraj P, Dorr D, Pratt N, Man K, Lau W, Morales D, Khera R, Schuemie M, Ryan P, Hripcsak G, Krumholz H, Suchard M, Lu Y. Real-world evidence for comparative safety of second-line antihyperglycemic agents in older adults with type 2 diabetes. Nature Communications 2026 PMID: 41935054, DOI: 10.1038/s41467-026-71307-0.Peer-Reviewed Original ResearchGLP-1 receptor agonistsReceptor agonistsAntihyperglycemic agentsGLP-1SGLT2 inhibitorsClinical trialsComparative safetyRisk of diabetic ketoacidosisHigh riskHigher risk of diabetic ketoacidosisRisk of peripheral edemaMultinational cohort studyRisk of hypoglycemiaDPP-4 inhibitorsPropensity score adjustmentType 2 diabetesPeripheral edemaDiabetic ketoacidosisAdverse eventsCohort studyHazard ratioDPP-4Safety outcomesAgonistsReal-world evidence26-A-20737-ACC MULTIMODAL RETRIEVAL-AUGMENTED SYSTEM FOR INTEROPERABLE ASSESSMENT OF THROMBOEMBOLIC AND BLEEDING RISK IN ATRIAL FIBRILLATION
Adejumo P, Thangaraj P, Dhingra L, Biswas D, Aminorroaya A, Shankar S, Pedroso A, Croon P, Khera R. 26-A-20737-ACC MULTIMODAL RETRIEVAL-AUGMENTED SYSTEM FOR INTEROPERABLE ASSESSMENT OF THROMBOEMBOLIC AND BLEEDING RISK IN ATRIAL FIBRILLATION. Journal Of The American College Of Cardiology 2026, 87: a95. DOI: 10.1016/j.jacc.2026.02.236.Peer-Reviewed Original Research26-A-16742-ACC PRIORITIZING ECHOCARDIOGRAPHY WITH AI-ENABLED ECG TO ACCELERATE STRUCTURAL HEART DISEASE DIAGNOSIS: FINDINGS FROM PROVAR+
Pedroso A, Dhingra L, Vinhal W, Shankar S, Reges R, Cardoso C, Da Silva Ribeiro I, Silva J, Silva L, De Mattos Paixao G, Brant L, Nascimento B, Sable C, Ribeiro A, Khera R. 26-A-16742-ACC PRIORITIZING ECHOCARDIOGRAPHY WITH AI-ENABLED ECG TO ACCELERATE STRUCTURAL HEART DISEASE DIAGNOSIS: FINDINGS FROM PROVAR+. Journal Of The American College Of Cardiology 2026, 87: a1188-a1189. DOI: 10.1016/j.jacc.2026.02.2922.Peer-Reviewed Original Research26-A-20902-ACC AI-ENHANCED ECG ENABLES HCM PHENOTYPE DETECTION IN INDIVIDUALS WITH A PATHOGENIC GENOTYPE
Croon P, Van Der Boon R, Shankar S, Dhingra L, Michels M, Zwetsloot P, De Boer R, Pedroso A, Bruining N, Khera R. 26-A-20902-ACC AI-ENHANCED ECG ENABLES HCM PHENOTYPE DETECTION IN INDIVIDUALS WITH A PATHOGENIC GENOTYPE. Journal Of The American College Of Cardiology 2026, 87: a779-a780. DOI: 10.1016/j.jacc.2026.02.2012.Peer-Reviewed Original Research26-A-16729-ACC GENERATIVE AI ADOPTION IN US HOSPITALS: NATIONAL PATTERNS AND VARIATION BY DIGITAL INFRASTRUCTURE AND CARDIOVASCULAR CARE PERFORMANCE
Pedroso A, Khera R. 26-A-16729-ACC GENERATIVE AI ADOPTION IN US HOSPITALS: NATIONAL PATTERNS AND VARIATION BY DIGITAL INFRASTRUCTURE AND CARDIOVASCULAR CARE PERFORMANCE. Journal Of The American College Of Cardiology 2026, 87: a1222. DOI: 10.1016/j.jacc.2026.02.3007.Peer-Reviewed Original ResearchWearable-Echo-FM: an ECG echo foundation model for 1-lead electrocardiography
Knight E, Oikonomou E, Aminorroaya A, Pedroso A, Khera R. Wearable-Echo-FM: an ECG echo foundation model for 1-lead electrocardiography. European Heart Journal - Digital Health 2026, 7: ztag049. PMID: 42077383, PMCID: PMC13131981, DOI: 10.1093/ehjdh/ztag049.Peer-Reviewed Original ResearchConvolutional neural networkArtificial intelligenceBaseline convolutional neural networkContrastive pre-trainingPortable devicesHeld-out test setText encoderNeural networkWearable electrocardiogramPre-trainingTraining setText reportsTest setWearableStructural heart diseaseLeft ventricular systolic dysfunctionEncodingDevicesIntelligenceNetworkLabelingSetsArtificial intelligence-enabled electrocardiography to triage echocardiography for structural heart disease diagnosis in a low-resource setting
Pedroso A, Nascimento B, Dhingra L, Shankar S, Vinhal W, Borges e Reges R, Cardoso C, Sable C, Ribeiro A, Khera R. Artificial intelligence-enabled electrocardiography to triage echocardiography for structural heart disease diagnosis in a low-resource setting. American Journal Of Preventive Cardiology 2026, 27: 101539. PMID: 42291046, PMCID: PMC13261225, DOI: 10.1016/j.ajpc.2026.101539.Peer-Reviewed Original ResearchPoint-of-care ultrasoundLow-resource settingsStructural heart diseaseMajor ECG abnormalityScreening cohortAI-ECGCardiovascular screening programHealth system impactTransthoracic echocardiographyECG abnormalitiesReferral workflowsIdentification of structural heart diseaseDiagnosis of structural heart diseaseComprehensive transthoracic echocardiographyReferral thresholdsScreening programScreened referencesReferral strategiesDecision-curve analysisIdentification of individualsPositive predictive valueStandard referralECG interpretationImaging cohortReferralArtificial Intelligence-enhanced Electrocardiography for Heart Failure Screening and Risk Stratification
Dhingra L, Croon P, Batinica B, Aminorroaya A, Pedroso A, Khera R. Artificial Intelligence-enhanced Electrocardiography for Heart Failure Screening and Risk Stratification. Current Heart Failure Reports 2026, 23: 10. PMID: 41838300, DOI: 10.1007/s11897-026-00748-x.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsRisk factor surveillancePublic health challengeHeart failure screeningHF risk assessmentHF screeningRoutine careCommunity programsHF riskHealth challengesECG testRisk scoreECG interpretationRisk stratificationConfirmatory imagingSymptom onsetRiskCost-effectiveClinical implementationProspective validationScreeningTherapy decisionsFunctional abnormalitiesCareRisk assessmentCohort
Academic Achievements & Community Involvement
News
News
- June 30, 2026
Wearables, Social Media, and What They Mean for the Doctor-Patient Relationship
- April 28, 2026
Choosing Safer Diabetes Medications for Older Adults
- January 23, 2025
New AI Tool Identifies Risk of Future Heart Failure
- November 05, 2024
Yale Researchers at American Heart Association Scientific Session 2024
Get In Touch
Contacts
Lab Number
Locations
CarDS Lab
Academic Office
195 Church Street, Fl 6th
New Haven, CT 06510