Jasjeet Sekhon
Eugene Meyer Professor of Political Science and Professor of Statistics and Data ScienceCards
About
Research
Publications
2025
Usability and adoption in a randomized trial of GutGPT a GenAI tool for gastrointestinal bleeding
Chung S, Giuffrè M, Rajashekar N, Pu Y, Shin Y, Kresevic S, Chan C, Nakamura-Sakai S, You K, Saarinen T, Hsiao A, Wong A, Evans L, McCall T, Kizilcec R, Sekhon J, Laine L, Shung D. Usability and adoption in a randomized trial of GutGPT a GenAI tool for gastrointestinal bleeding. Npj Digital Medicine 2025, 8: 527. PMID: 40825997, PMCID: PMC12361555, DOI: 10.1038/s41746-025-01896-5.Peer-Reviewed Original ResearchClinical decision support systemsUnified Theory of AcceptanceReal-world integrationTheory of AcceptanceDecision support systemUnified theoryUse of technologyGenerative AIEffort expectancyDecision accuracySupport systemBehavioral intentionUsabilityDashboardRandomized trialsAdoptionUTAUTUGIB managementUsersClinical traineesSecondary measuresPatient outcomesPrimary outcomeUnifiedGastrointestinal bleeding managementUncovering memorization effect in the presence of spurious correlations
You C, Dai H, Min Y, Sekhon J, Joshi S, Duncan J. Uncovering memorization effect in the presence of spurious correlations. Nature Communications 2025, 16: 5424. PMID: 40593835, PMCID: PMC12216586, DOI: 10.1038/s41467-025-61531-5.Peer-Reviewed Original ResearchExpert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology
Giuffrè M, You K, Pang Z, Kresevic S, Chung S, Chen R, Ko Y, Chan C, Saarinen T, Ajcevic M, Crocè L, Garcia-Tsao G, Gralnek I, Sung J, Barkun A, Laine L, Sekhon J, Stadie B, Shung D. Expert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology. Npj Digital Medicine 2025, 8: 242. PMID: 40319106, PMCID: PMC12049514, DOI: 10.1038/s41746-025-01589-z.Peer-Reviewed Original ResearchReward modelSimilarity-based rankingZero-shot baselineSupervised fine-tuningRejection samplingLanguage modelSimilarity metricModel safetyHuman performanceFine-tuningHuman gradingExpert verificationTime-consumingDecision-makingMedical decision-makingMedical questionsEVALAccuracyLanguageDatasetMetricsAssess accuracyRewardVerificationSetsNonparametric identification is not enough, but randomized controlled trials are
Aronow P, Robins J, Saarinen T, Sävje F, Sekhon J. Nonparametric identification is not enough, but randomized controlled trials are. Observational Studies 2025, 11: 3-16. PMID: 40487083, PMCID: PMC12139723, DOI: 10.1353/obs.2025.a956837.Peer-Reviewed Original ResearchPropensity score functionResults of RobinsValid confidence intervalsAverage treatment effectParametric rateScoring functionContinuous confoundersNonparametric identificationUnconfoundedness assumptionBinary outcomesStatistical estimationObservational settingPropensity scoreAssumptionsEstimationConfidence intervalsPropensityRobinTreatment effectsFunctionInferenceRejoinder: Nonparametric identification is not enough, but randomized controlled trials are.
Aronow P, Robins J, Saarinen T, Sävje F, Sekhon J. Rejoinder: Nonparametric identification is not enough, but randomized controlled trials are. Observational Studies 2025, 11: 85-90. PMID: 40487084, PMCID: PMC12139717, DOI: 10.1353/obs.2025.a956844.Peer-Reviewed Original ResearchRoot-nPropensity score functionRoot-n rateConditional expectation functionFinite-sampleContinuous covariatesNonparametric identificationExpectation functionUntestable assumptionsRandomized experimentScoring functionPotential outcomesEstimated averageSample sizeEstimationPropensity scoreConfidence intervalsPropensityAssumptionsCovariatesFunctionUniformityRemarks
2024
Validation of an Electronic Health Record–Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding
Shung D, Chan C, You K, Nakamura S, Saarinen T, Zheng N, Simonov M, Li D, Tsay C, Kawamura Y, Shen M, Hsiao A, Sekhon J, Laine L. Validation of an Electronic Health Record–Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding. Gastroenterology 2024, 167: 1198-1212. PMID: 38971198, PMCID: PMC11493512, DOI: 10.1053/j.gastro.2024.06.030.Peer-Reviewed Original ResearchElectronic health recordsGlasgow-Blatchford scoreEmergency departmentVery-low-risk patientsRisk scoreOakland scoreMachine learning modelsStructured data fieldsClinical risk scoreGastrointestinal bleedingAll-Cause MortalityHealth recordsLearning modelsManual data entrySecondary analysisRisk stratification scoresAssess proportionRed blood-cell transfusionPrimary outcomeProportion of patientsData entryOvert gastrointestinal bleedingPrimary analysisReceiver-operating-characteristic curveVery-low-riskCalibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations
You C, Min Y, Dai W, Sekhon J, Staib L, Duncan J. Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations. 2015 IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2024, 00: 26140-26150. PMID: 39640960, PMCID: PMC11620289, DOI: 10.1109/cvpr52733.2024.02470.Peer-Reviewed Original ResearchDiverse downstream tasksVision-language modelsPre-trained modelsRepresentation of samplesContrastive learningDownstream tasksFeature reweightingTraining dataFeature patternsModel generalizationGroup annotationsPain pointsGroup labelsAnnotationRobustnessClassifierClipsFeaturesDeepDeploymentBenchmarksTime-intensiveCodeTaskLearningHuman-Algorithmic Interaction Using a Large Language Model-Augmented Artificial Intelligence Clinical Decision Support System
Rajashekar N, Shin Y, Pu Y, Chung S, You K, Giuffre M, Chan C, Saarinen T, Hsiao A, Sekhon J, Wong A, Evans L, Kizilcec R, Laine L, Mccall T, Shung D. Human-Algorithmic Interaction Using a Large Language Model-Augmented Artificial Intelligence Clinical Decision Support System. 2024, 1-20. DOI: 10.1145/3613904.3642024.Peer-Reviewed Original ResearchClinical decision support systemsHuman-computer interactionDecision support systemArtificial intelligenceAI-CDSSIntelligent clinical decision support systemSupport systemIntegration of artificial intelligenceHuman-algorithm interactionsEase-of-useLanguage modelHuman algorithmAI systemsSocio-technological challengesHealth-care providersMedical student participationQualitative themesClinical simulationClinical expertiseUpper gastrointestinal bleedingUsabilityBorderline decisionsLanguageClinical intuitionTrust
2023
Same Root Different Leaves: Time Series and Cross‐Sectional Methods in Panel Data
Shen D, Ding P, Sekhon J, Yu B. Same Root Different Leaves: Time Series and Cross‐Sectional Methods in Panel Data. Econometrica 2023, 91: 2125-2154. DOI: 10.3982/ecta21248.Peer-Reviewed Original Research
2022
Linear Aggregation in Tree-Based Estimators
Künzel S, Saarinen T, Liu E, Sekhon J. Linear Aggregation in Tree-Based Estimators. Journal Of Computational And Graphical Statistics 2022, 31: 917-934. DOI: 10.1080/10618600.2022.2026780.Peer-Reviewed Original Research