2024
How Artificial Intelligence Will Transform Clinical Care, Research, and Trials for Inflammatory Bowel Disease
Silverman A, Shung D, Stidham R, Kochhar G, Iacucci M. How Artificial Intelligence Will Transform Clinical Care, Research, and Trials for Inflammatory Bowel Disease. Clinical Gastroenterology And Hepatology 2024 PMID: 38992406, DOI: 10.1016/j.cgh.2024.05.048.Peer-Reviewed Original ResearchInflammatory bowel diseaseBowel diseasePredicting response to therapyArtificial intelligenceResponse to therapyDisease Activity ScoreMulti-modal data sourcesDirections of AIBowel damageAI applicationsDiseaseClinical careTransform clinical careComputer-based methodologyDrug discoveryComplex diseasesCritical challengesData sourcesMetabolomicsEndoscopyTherapyValidation of an Electronic Health Record-Based Machine Learning Model Compared to 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 to Clinical Risk Scores for Gastrointestinal Bleeding. Gastroenterology 2024 PMID: 38971198, 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-riskOn the Wasserstein Median of Probability Measures
You K, Shung D, Giuffrè M. On the Wasserstein Median of Probability Measures. Journal Of Computational And Graphical Statistics 2024, 1-25. DOI: 10.1080/10618600.2024.2374580.Peer-Reviewed Original ResearchLetter: Shifting focus—From ChatGPT to specialised medical LLMs: Authors' reply
Giuffrè M, Kresevic S, You K, Dupont J, Huebner J, Grimshaw A, Shung D. Letter: Shifting focus—From ChatGPT to specialised medical LLMs: Authors' reply. Alimentary Pharmacology & Therapeutics 2024, 60: 417-418. PMID: 38884531, DOI: 10.1111/apt.18125.Peer-Reviewed Original ResearchSAT-338-YI Using retrieval augmented generation to increase large language models accuracy: a proof-of-concept pipeline on european hepatitis C virus (HCV) guidelines
Giuffrè M, Kresevic S, Croce’ S, Shung D. SAT-338-YI Using retrieval augmented generation to increase large language models accuracy: a proof-of-concept pipeline on european hepatitis C virus (HCV) guidelines. Journal Of Hepatology 2024, 80: s731. DOI: 10.1016/s0168-8278(24)02060-9.Peer-Reviewed Original ResearchOptimizing large language models in digestive disease: strategies and challenges to improve clinical outcomes
Giuffrè M, Kresevic S, Pugliese N, You K, Shung D. Optimizing large language models in digestive disease: strategies and challenges to improve clinical outcomes. Liver International 2024 PMID: 38819632, DOI: 10.1111/liv.15974.Peer-Reviewed Original ResearchSupervised fine-tuningHuman feedbackLanguage modelAccurate information retrievalInformation retrievalReinforcement learningDomain knowledgeText corpusNeural networkModel trainingAdaptive methodField of digestive diseasesFine-tuningWindow limitRetrievalIncreased accuracyAccuracyDigestive diseasesImprove healthcareDefinition of accuracyLearningIncrease patients' qualityClinical decision-makingSpecialized knowledgeDiverse sourcesSystematic review: The use of large language models as medical chatbots in digestive diseases
Giuffrè M, Kresevic S, You K, Dupont J, Huebner J, Grimshaw A, Shung D. Systematic review: The use of large language models as medical chatbots in digestive diseases. Alimentary Pharmacology & Therapeutics 2024, 60: 144-166. PMID: 38798194, DOI: 10.1111/apt.18058.Peer-Reviewed Original ResearchLanguage modelAdverse patient safety eventsPatient safety eventsClinical decision supportRisk of biasSystematic literature searchWeb of Science Core CollectionCombination of keywordsMedical chatbotTriage recommendationsHealthcare systemScience Core CollectionNecessary careSafety eventsOverburden healthcare systemsMedical adviceOvid MEDLINEMultiple specialtiesDecision supportOvid EmbaseCochrane LibrarySingle-study resultsGoogle ScholarLiterature searchGastroenterologyHuman-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 intuitionTrust1059 ENHANCING CLINICAL DECISION SUPPORT WITH LARGE LANGUAGE MODELS: A TAILORED PIPELINE FOR ACCURATE INTERPRETATION OF HEPATITIS C MANAGEMENT GUIDELINES
Kresevic S, Giuffrè M, Shung D. 1059 ENHANCING CLINICAL DECISION SUPPORT WITH LARGE LANGUAGE MODELS: A TAILORED PIPELINE FOR ACCURATE INTERPRETATION OF HEPATITIS C MANAGEMENT GUIDELINES. Gastroenterology 2024, 166: s-1564. DOI: 10.1016/s0016-5085(24)04052-6.Peer-Reviewed Original ResearchTu2034 PERFORMANCE OF DIFFERENT COMPUTER-AIDED DETECTION (CADE) PLATFORMS COMPARED TO CONVENTIONAL COLONOSCOPY: A SYSTEMATIC REVIEW AND META-ANALYSIS
Soleymanjahi S, Huebner J, Elmansy L, Rajashekar N, Paracha R, Shung D. Tu2034 PERFORMANCE OF DIFFERENT COMPUTER-AIDED DETECTION (CADE) PLATFORMS COMPARED TO CONVENTIONAL COLONOSCOPY: A SYSTEMATIC REVIEW AND META-ANALYSIS. Gastroenterology 2024, 166: s-1501. DOI: 10.1016/s0016-5085(24)03891-5.Peer-Reviewed Original ResearchMo1066 LARGE LANGUAGE MODEL-BASED SIMULATED PATIENTS WITH UPPER GASTROINTESTINAL BLEEDING FOR MEDICAL EDUCATION – A PILOT STUDY WITH EMPATHGPT
Rajashekar N, Chan C, Laine L, Shung D. Mo1066 LARGE LANGUAGE MODEL-BASED SIMULATED PATIENTS WITH UPPER GASTROINTESTINAL BLEEDING FOR MEDICAL EDUCATION – A PILOT STUDY WITH EMPATHGPT. Gastroenterology 2024, 166: s-933. DOI: 10.1016/s0016-5085(24)02628-3.Peer-Reviewed Original ResearchSu1979 GUTGPT: NOVEL LARGE LANGUAGE MODEL PIPELINE OUTPERFORMS OTHER LARGE LANGUAGE MODELS IN ACCURACY AND SIMILARITY TO INTERNATIONAL EXPERTS FOR GUIDELINE RECOMMENDED MANAGEMENT OF PATIENTS WITH UPPER GASTROINTESTINAL BLEEDING
Giuffrè M, You K, Chung S, Kresevic S, Chan C, Saarinen T, Nakamura S, Laine L, Sung J, Garcia-Tsao G, Gralnek I, Barkun A, Sekhon J, Shung D. Su1979 GUTGPT: NOVEL LARGE LANGUAGE MODEL PIPELINE OUTPERFORMS OTHER LARGE LANGUAGE MODELS IN ACCURACY AND SIMILARITY TO INTERNATIONAL EXPERTS FOR GUIDELINE RECOMMENDED MANAGEMENT OF PATIENTS WITH UPPER GASTROINTESTINAL BLEEDING. Gastroenterology 2024, 166: s-889-s-890. DOI: 10.1016/s0016-5085(24)02528-9.Peer-Reviewed Original ResearchTu2010 PROVIDER TRUST TOWARDS ADOPTING REAL TIME ARTIFICIAL INTELLIGENCE IN COLONOSCOPY: A SYSTEMATIC REVIEW
Soleymanjahi S, Kolb J, Chung S, Foroutan F, Sultan S, Shung D. Tu2010 PROVIDER TRUST TOWARDS ADOPTING REAL TIME ARTIFICIAL INTELLIGENCE IN COLONOSCOPY: A SYSTEMATIC REVIEW. Gastroenterology 2024, 166: s-1490-s-1491. DOI: 10.1016/s0016-5085(24)03867-8.Peer-Reviewed Original ResearchThe Reply
Li D, Shung D. The Reply. The American Journal Of Medicine 2024, 137: e99. PMID: 38679450, DOI: 10.1016/j.amjmed.2024.01.017.Peer-Reviewed Original ResearchTu1649 SIMULATING THE PATIENT-PRACTITIONER RELATIONSHIP IN PATIENTS WITH IRRITABLE BOWEL SYNDROME WITH LARGE LANGUAGE MODELBASED TOOLS – A PROOF OF CONCEPT
Rajashekar N, Chan C, Deutsch J, Laine L, Shung D. Tu1649 SIMULATING THE PATIENT-PRACTITIONER RELATIONSHIP IN PATIENTS WITH IRRITABLE BOWEL SYNDROME WITH LARGE LANGUAGE MODELBASED TOOLS – A PROOF OF CONCEPT. Gastroenterology 2024, 166: s-1364. DOI: 10.1016/s0016-5085(24)03586-8.Peer-Reviewed Original ResearchTu2029 DOES COMPUTER-AIDED DETECTION (CADE) OFFER ANY ADVANTAGE TO CONVENTIONAL COLONOSCOPY: A COMPREHENSIVE COMPARISON OF EFFICACY AND SAFETY MEASURES?
Soleymanjahi S, Huebner J, Elmansy L, Rajashekar N, Paracha R, Shung D. Tu2029 DOES COMPUTER-AIDED DETECTION (CADE) OFFER ANY ADVANTAGE TO CONVENTIONAL COLONOSCOPY: A COMPREHENSIVE COMPARISON OF EFFICACY AND SAFETY MEASURES? Gastroenterology 2024, 166: s-1499. DOI: 10.1016/s0016-5085(24)03886-1.Peer-Reviewed Original Research407 IMPACT OF ARTIFICIAL INTELLIGENCE SYSTEMS FOR UPPER GASTROINTESTINAL BLEEDING ON CLINICIAN TRUST AND LEARNING USING LARGE LANGUAGE MODELS: A RANDOMIZED PILOT SIMULATION STUDY
Chung S, Rajashekar N, Pu Y, Shin Y, Giuffrè M, Chan C, You K, Saarinen T, Hsiao A, Sekhon J, Wong A, Evans L, McCall T, Kizilcec R, Laine L, Shung D. 407 IMPACT OF ARTIFICIAL INTELLIGENCE SYSTEMS FOR UPPER GASTROINTESTINAL BLEEDING ON CLINICIAN TRUST AND LEARNING USING LARGE LANGUAGE MODELS: A RANDOMIZED PILOT SIMULATION STUDY. Gastroenterology 2024, 166: s-95-s-96. DOI: 10.1016/s0016-5085(24)00715-7.Peer-Reviewed Original ResearchPredicting response to non-selective beta-blockers with liver–spleen stiffness and heart rate in patients with liver cirrhosis and high-risk varices
Giuffrè M, Dupont J, Visintin A, Masutti F, Monica F, You K, Shung D, Crocè L. Predicting response to non-selective beta-blockers with liver–spleen stiffness and heart rate in patients with liver cirrhosis and high-risk varices. Hepatology International 2024, 1-12. PMID: 38664292, DOI: 10.1007/s12072-024-10649-7.Peer-Reviewed Original ResearchHigh-risk varicesHepatic venous pressure gradientLiver stiffnessLiver cirrhosisSpleen stiffnessVariceal gradeHeart rateCohort of cirrhotic patientsNon-selective beta-blockersPercentual decreaseAssessed therapeutic responseMultivariate modelVenous pressure gradientCut-off valueOptimal cut-offAssociated with better predictionNSBB treatmentPrimary prophylaxisHemorrhagic episodesCirrhotic patientsTherapeutic responseBeta-blockersNSBBTreatment initiationProspective studyOptimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework
Kresevic S, Giuffrè M, Ajcevic M, Accardo A, Crocè L, Shung D. Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. Npj Digital Medicine 2024, 7: 102. PMID: 38654102, PMCID: PMC11039454, DOI: 10.1038/s41746-024-01091-y.Peer-Reviewed Original ResearchClinical decision support systemsFew-shot learningLanguage modelImprove clinical decision support systemsDecision support systemText similarity scoresText similarityAblation studiesImprove overall accuracyGeneration accuracyRight informationAccurate outputSupport systemTransform healthcareIncreasing levels of complexityHospital workflowOverall accuracyRight providerTurbo modelLearning strategiesLevel of complexityLearningRetrievalCorpus of textsAccuracyReview article: Upper gastrointestinal bleeding – review of current evidence and implications for management
Shung D, Laine L. Review article: Upper gastrointestinal bleeding – review of current evidence and implications for management. Alimentary Pharmacology & Therapeutics 2024, 59: 1062-1081. PMID: 38517201, DOI: 10.1111/apt.17949.Peer-Reviewed Original ResearchUpper gastrointestinal bleedingManagement of upper gastrointestinal bleedingAcute upper gastrointestinal bleedingPeptic ulcer diseaseOver-the-scope clipPre-endoscopicVariceal bleedingManagement of acute upper gastrointestinal bleedingTreated with prophylactic antibioticsTransjugular intrahepatic portosystemic shuntUpper gastrointestinal bleeding patientsRed blood cell transfusion policyPre-endoscopic managementHigh-risk stigmataSeverity of bleedingEarly enteral feedingHigh-risk patientsMeta-analysisIntrahepatic portosystemic shuntProton pump inhibitorsEvidence-based updateOver-the-scopeHospital-based carePhase of careRandom-effects method