2025
Complete AI-Enabled Echocardiography Interpretation With Multitask Deep Learning
Holste G, Oikonomou E, Tokodi M, Kovács A, Wang Z, Khera R. Complete AI-Enabled Echocardiography Interpretation With Multitask Deep Learning. JAMA 2025, 334 PMID: 40549400, PMCID: PMC12186137, DOI: 10.1001/jama.2025.8731.Peer-Reviewed Original ResearchMultitask deep learningAI systemsDiagnostic classification tasksClassification taskDeep learningArtificial intelligenceArea under the receiver operating characteristic curveYale New Haven Health SystemTransthoracic echocardiography studyTransthoracic echocardiographyVentricular systolic dysfunctionParameter estimation taskSystolic dysfunctionDiagnosis tasksEchocardiographic videosRight ventricular systolic dysfunctionLeft ventricular ejection fractionAI predictionsEstimation taskVentricular ejection fractionSevere aortic stenosisManual reportingReceiver operating characteristic curveTaskClinical workflowPrediction of Lymph Node Metastasis in Non–Small Cell Lung Carcinoma Using Primary Tumor Somatic Mutation Data
Lee V, Moore N, Doyle J, Hicks D, Oh P, Bodofsky S, Hossain S, Patel A, Aneja S, Homer R, Park H. Prediction of Lymph Node Metastasis in Non–Small Cell Lung Carcinoma Using Primary Tumor Somatic Mutation Data. JCO Clinical Cancer Informatics 2025, 9: e2400303. PMID: 40446175, DOI: 10.1200/cci-24-00303.Peer-Reviewed Original ResearchConceptsNon-small cell lung cancerLymph node metastasisArea under the receiver operating characteristic curveNode metastasisTreatment strategiesNon-small cell lung carcinomaPrediction of lymph node metastasisSurvival analysisSNP dataLymph node metastasis statusAssociated with lymph node metastasisCell lung carcinomaCell lung cancerLymph node metastasis predictionReceiver operating characteristic curveDiagnostic methodsPersonalized treatment strategiesSingle-nucleotide polymorphism (SNPChi-square testMedian AUCLung carcinomaClinical outcomesNon-smallRisk stratificationLogistic regression modelsAutomated detection of interictal epileptiform discharges with few electroencephalographic channels
Alkofer M, Yang C, Ganglberger W, Beal J, Hegde M, Kang J, Yoo J, Gelfand M, Thio L, Kutluay E, Campbell Z, Schmitt S, Gleichgerrcht E, Waterhouse E, Lopez M, Eisenschenk S, Galanti M, Singh R, Wills K, Meulenbrugge E, Dlugos D, Dean B, Halford J, Goldenholz D, Jing J, Thomas R, Westover M. Automated detection of interictal epileptiform discharges with few electroencephalographic channels. Epilepsia 2025 PMID: 40317534, DOI: 10.1111/epi.18431.Peer-Reviewed Original ResearchArea under the receiver operating characteristic curveInterictal epileptiform dischargesMedian AUCEpileptiform dischargesFocal interictal epileptiform dischargesReceiver operating characteristic curveArea under the receiver operating characteristic curve valuesEpilepsy diagnosisDetection of interictal epileptiform dischargesClinically available productsDetecting interictal epileptiform dischargesClinically relevant metricsPatient populationPatientsCharacteristic curveDeep neural networksDiagnosisEpilepsyClinicNeural networkIED detectionElectroencephalographic channelsEEG setupElectroencephalographic samplesAutomated detectionPredicting Agitation Events in the Emergency Department Through Artificial Intelligence
Wong A, Sapre A, Wang K, Nath B, Shah D, Kumar A, Faustino I, Desai R, Hu Y, Robinson L, Meng C, Tong G, Bernstein S, Yonkers K, Melnick E, Dziura J, Taylor R. Predicting Agitation Events in the Emergency Department Through Artificial Intelligence. JAMA Network Open 2025, 8: e258927. PMID: 40332935, PMCID: PMC12059975, DOI: 10.1001/jamanetworkopen.2025.8927.Peer-Reviewed Original ResearchConceptsED visitsEmergency departmentAgitation eventsElectronic health record dataArea under the receiver operating characteristic curvePatient-centered careHealth service utilizationPrimary outcomeHealth record dataUrban health systemED visit dataMode of arrivalPrevention of agitationOutcome of agitationDiverse patient populationsRestraint ordersCross-sectional cohortService utilizationVital signsED sitesHealth systemMain OutcomesRestraint eventsRange of predicted probabilitiesVisit dataPerformance of the Charlson and Elixhauser Comorbidity Index Varies With the Type of Minimally Invasive Thoracic Surgery
Kim A, Ding L, Udelsman B, Atay S, Wightman S, Harano T, Rosenberg G, Blasberg J, Boffa D, Kim A. Performance of the Charlson and Elixhauser Comorbidity Index Varies With the Type of Minimally Invasive Thoracic Surgery. World Journal Of Surgery 2025, 49: 1418-1431. PMID: 40261152, DOI: 10.1002/wjs.12599.Peer-Reviewed Original ResearchConceptsMinimally invasive pulmonary lobectomyMinimally invasive Ivor Lewis esophagectomyArea under the receiver operating characteristic curveThoracic surgeryPredicting mortalityMinimally invasive thoracic surgeryPredicting short-term outcomesUtilization Project National Readmission DatabasePredicting long-term outcomesInvasive thoracic surgeryIvor Lewis esophagectomyMultivariate logistic regression modelReceiver operating characteristic curveShort-term outcomesLong-term outcomesNational Readmission DatabasePulmonary lobectomyInternational Classification of DiseasesSurgery typeClinical prognosisLogistic regression modelsComorbidity indexNonroutine dischargeICD-10 codesSurgeryIdentification of Patients With Congestive Heart Failure From the Electronic Health Records of Two Hospitals: Retrospective Study
Sumsion D, Davis E, Fernandes M, Wei R, Milde R, Veltink J, Kong W, Xiong Y, Rao S, Westover T, Petersen L, Turley N, Singh A, Buss S, Mukerji S, Zafar S, Das S, Moura V, Ghanta M, Gupta A, Kim J, Stone K, Mignot E, Hwang D, Trotti L, Clifford G, Katwa U, Thomas R, Westover M, Sun H. Identification of Patients With Congestive Heart Failure From the Electronic Health Records of Two Hospitals: Retrospective Study. JMIR Medical Informatics 2025, 13: e64113. PMID: 40208662, PMCID: PMC12022513, DOI: 10.2196/64113.Peer-Reviewed Original ResearchConceptsElectronic health recordsNatural language processingICD codesHealth recordsMedical recordsArea under the receiver operating characteristic curveClinic visit notesGeneral hospital dataManual chart reviewLogistic regression modelsCause of hospital admissionDiagnosis of congestive heart failureVisit notesNatural language processing modelsAnalysis of medical recordsCongestive heart failureHospital dataHospital admissionLogistic regressionHospital sampleMachine learning modelsMedical Center dataOverall estimation errorRandom samplePrecision-recall curveInternational multispecialty expert physician preoperative identification of extranodal extension in patients with oropharyngeal cancer using computed tomography: Prospective blinded human inter‐observer performance evaluation
Sahin O, Kamel S, Wahid K, Dede C, Taku N, He R, Naser M, Sharafi C, Mäkitie A, Kann B, Kaski K, Sahlsten J, Jaskari J, Amit M, Chronowski G, Diaz E, Garden A, Goepfert R, Guenette J, Gunn G, Hirvonen J, Hoebers F, Hutcheson K, Guha‐Thakurta N, Johnson J, Kaya D, Khanpara S, Nyman K, Lai S, Lango M, Learned K, Lee A, Lewis C, Maniakas A, Moreno A, Myers J, Phan J, Pytynia K, Rosenthal D, Sandulache V, Schellingerhout D, Shah S, Sikora A, Mohamed A, Chen M, Fuller C, Group M. International multispecialty expert physician preoperative identification of extranodal extension in patients with oropharyngeal cancer using computed tomography: Prospective blinded human inter‐observer performance evaluation. Cancer 2025, 131: e35815. PMID: 40159431, PMCID: PMC12067423, DOI: 10.1002/cncr.35815.Peer-Reviewed Original ResearchConceptsPathologic extranodal extensionOropharyngeal cancerExtranodal extensionComputed tomographyClinician specialtyHPV-positive OPC patientsHuman papillomavirus (HPV)-positive oropharyngeal cancerHPV-positive oropharyngeal cancerReceiver operating characteristic curveArea under the receiver operating characteristic curveInter-observer variabilityOPC patientsNodal necrosisPrognostic factorsRadiological criteriaInterobserver agreementDiagnostic performanceBrier scoreCT imagesFleiss' kappaCharacteristic curvePredictive signLogistic regressionPatientsCancerAn interpretable deep-learning approach to detect biomarkers in anxious-depressed symptoms from prefrontal fNIRS signals during an autobiographical memory test
Zhang Y, Xu Y, Cheng Y, Zhao Y, Potenza M, Shi H. An interpretable deep-learning approach to detect biomarkers in anxious-depressed symptoms from prefrontal fNIRS signals during an autobiographical memory test. Asian Journal Of Psychiatry 2025, 107: 104451. PMID: 40158273, DOI: 10.1016/j.ajp.2025.104451.Peer-Reviewed Original ResearchAutobiographical Memory TestNon-anxious depressionFunctional near-infrared spectroscopyAnxious depressionMemory testDepressive symptomsAnxious-depressive symptomsNegative emotional valenceSevere mood disordersFrontal pole areasAD symptomsMood disordersEmotional valenceRight hemisphereNeuroimaging dataDiagnosed depressionSymptom groupsCognitive impairmentSymptom predictionHealthy controlsNear-infrared spectroscopyDepressionSymptomsRecall featuresArea under the receiver operating characteristic curveArtificial Intelligence-Enhanced Perfusion Scoring Improves the Diagnostic Accuracy of Myocardial Perfusion Imaging.
Miller R, Kavanagh P, Lemley M, Liang J, Sharir T, Einstein A, Fish M, Ruddy T, Kaufmann P, Sinusas A, Miller E, Bateman T, Dorbala S, Di Carli M, Hayes S, Friedman J, Berman D, Dey D, Slomka P. Artificial Intelligence-Enhanced Perfusion Scoring Improves the Diagnostic Accuracy of Myocardial Perfusion Imaging. Journal Of Nuclear Medicine 2025, 66: 648-653. PMID: 39978815, PMCID: PMC11960614, DOI: 10.2967/jnumed.124.268079.Peer-Reviewed Original ResearchObstructive coronary artery diseaseCoronary artery diseaseArea under the receiver operating characteristic curveMyocardial perfusion imagingPerfusion scoreDetection of obstructive coronary artery diseaseDiagnostic accuracy of myocardial perfusion imagingPerfusion imagingAccuracy of myocardial perfusion imagingInvasive coronary angiographyCohort of patientsHighest area under the receiver operating characteristic curveLeft main coronary arteryReceiver operating characteristic curveStress TPDDeep learningObstructive CADMedian ageCoronary angiographyArtificial intelligenceDiagnostic performanceDiagnostic accuracyArtery diseaseAI predictionsCoronary arteryComparative Performance of Machine Learning Models in Reducing Unnecessary Targeted Prostate Biopsies
Chen F, Esmaili R, Khajir G, Zeevi T, Gross M, Leapman M, Sprenkle P, Justice A, Arora S, Weinreb J, Spektor M, Huber S, Humphrey P, Levi A, Staib L, Venkataraman R, Martin D, Onofrey J. Comparative Performance of Machine Learning Models in Reducing Unnecessary Targeted Prostate Biopsies. European Urology Oncology 2025 PMID: 39924390, DOI: 10.1016/j.euo.2025.01.005.Peer-Reviewed Original ResearchProstate cancerPrediction of clinically significant prostate cancerClinical dataProstate-specific antigen levelClinically significant prostate cancerProstate magnetic resonance imagingSeverity of prostate cancerCombination of clinical featuresPrediction of csPCaSignificant prostate cancerProstate Imaging-ReportingCore needle biopsyRetrospective analysis of dataDecision curve analysisReducing unnecessary biopsiesProstate cancer diagnosisReceiver operating characteristic curveArea under the receiver operating characteristic curveFalse-negative rateMagnetic resonance imagingPersonalized risk assessmentAntigen levelsNeedle biopsyPatient ageUnnecessary biopsies
2024
Predicting positive Clostridioides difficile test results using large-scale longitudinal data of demographics and medication history
Pham A, El-Kareh R, Myers F, Ohno-Machado L, Kuo T. Predicting positive Clostridioides difficile test results using large-scale longitudinal data of demographics and medication history. Heliyon 2024, 11: e41350. PMID: 39958729, PMCID: PMC11825254, DOI: 10.1016/j.heliyon.2024.e41350.Peer-Reviewed Original ResearchArea under the receiver operating characteristic curveMedical historyClostridioides difficile</i> infectionMonths of medical historyPatient's chancesData of demographicsReceiver operating characteristic curveLogistic regression modelsHealth patientsModerate sample sizesPregnant womenHealthcare institutionsClostridioides difficile</i>Antibiotic useOdds ratioNegative casesLarge-scale longitudinal dataFinancial incentivesPositive testLogistic regressionPatientsIncreased susceptibilityCharacteristic curveRegression modelsSignificant covariatesDiagnostic performance of neural network algorithms in skull fracture detection on CT scans: a systematic review and meta-analysis
Sharifi G, Hajibeygi R, Zamani S, Easa A, Bahrami A, Eshraghi R, Moafi M, Ebrahimi M, Fathi M, Mirjafari A, Chan J, Dixe de Oliveira Santo I, Anar M, Rezaei O, Tu L. Diagnostic performance of neural network algorithms in skull fracture detection on CT scans: a systematic review and meta-analysis. Emergency Radiology 2024, 32: 97-111. PMID: 39680295, DOI: 10.1007/s10140-024-02300-7.Peer-Reviewed Original ResearchConceptsConvolutional neural networkArea under the receiver operating characteristic curveConvolutional neural network modelCT scanSkull fractureComputed tomographyDeep learningProspective clinical trialMeta-analysisReceiver operating characteristic curvePublication biasSkull fracture detectionSystematic reviewNeural network algorithmDetecting skull fracturesImprove diagnosis accuracyDiagnostic hurdlesShortage of radiologistsAutomated diagnostic toolTransfer learningDiagnostic performanceDiagnostic accuracyClinical trialsModel architectureNeural networkConstruction and performance of a clinical prediction rule for ureteral stone without the use of race or ethnicity: A new STONE score
Moore C, Gross C, Hart L, Molinaro A, Rhodes D, Singh D, Baloescu C. Construction and performance of a clinical prediction rule for ureteral stone without the use of race or ethnicity: A new STONE score. Journal Of The American College Of Emergency Physicians Open 2024, 5: e13324. PMID: 39524039, PMCID: PMC11543628, DOI: 10.1002/emp2.13324.Peer-Reviewed Original ResearchClinical prediction ruleArea under the receiver operating characteristic curveSTONE scoreMultivariate logistic regressionUreteral stonesComputed tomographyPrediction ruleUncomplicated renal colicKidney stonesReceiver operating characteristic curveLogistic regressionNon-black raceDiagnosis of kidney stonesGross hematuriaMicroscopic hematuriaRenal colicPotential adverse effectsDiagnostic accuracyHematuriaClinical algorithmMale genderProspective dataClinical accuracyRetrospective dataCharacteristic curveNatural Language Processing of Clinical Documentation to Assess Functional Status in Patients With Heart Failure
Adejumo P, Thangaraj P, Dhingra L, Aminorroaya A, Zhou X, Brandt C, Xu H, Krumholz H, Khera R. Natural Language Processing of Clinical Documentation to Assess Functional Status in Patients With Heart Failure. JAMA Network Open 2024, 7: e2443925. PMID: 39509128, PMCID: PMC11544492, DOI: 10.1001/jamanetworkopen.2024.43925.Peer-Reviewed Original ResearchConceptsFunctional status assessmentArea under the receiver operating characteristic curveClinical documentationElectronic health record dataHF symptomsOptimal care deliveryHealth record dataAssess functional statusStatus assessmentClinical trial participationProcessing of clinical documentsFunctional status groupCare deliveryOutpatient careMain OutcomesMedical notesTrial participantsNew York Heart AssociationFunctional statusQuality improvementRecord dataHeart failureClinical notesDiagnostic studiesStatus groupsInternational multi-institutional external validation of preoperative risk scores for 30-day in-hospital mortality in paediatric patients
Tangel V, Hoeks S, Stolker R, Brown S, Pryor K, de Graaff J, Committee M, Pace N, Domino K, Muehlschlegel J, Kheterpal S, Vaughan M, Mathis M, Jiang S, Obembe S, Freundlich R, Schonberger R, Kim D. International multi-institutional external validation of preoperative risk scores for 30-day in-hospital mortality in paediatric patients. British Journal Of Anaesthesia 2024, 133: 1222-1233. PMID: 39477712, DOI: 10.1016/j.bja.2024.09.003.Peer-Reviewed Original ResearchConceptsSurgical risk scoresPediatric risk assessmentArea under the receiver operating characteristic curveIn-hospital mortalityRisk scoreMulticenter Perioperative Outcomes GroupPreoperative risk scoreDecision curve analysisReceiver operating characteristic curvePhysical status scoreExternal validationAssess model discriminationRisk prediction scoreASA physical status scoreClinical decision-makingPaediatric patientsLow probability of mortalityDutch hospitalsOutcome groupPatient-specific risk scoresPrimary outcomeClustering of casesCurve analysisStatus scoreCharacteristic curveDevelopment of a prediction model for 30-day COVID-19 hospitalization and death in a national cohort of Veterans Health Administration patients–March 2022—April 2023
Bui D, Bajema K, Huang Y, Yan L, Li Y, Rajeevan N, Berry K, Rowneki M, Argraves S, Hynes D, Huang G, Aslan M, Ioannou G. Development of a prediction model for 30-day COVID-19 hospitalization and death in a national cohort of Veterans Health Administration patients–March 2022—April 2023. PLOS ONE 2024, 19: e0307235. PMID: 39365775, PMCID: PMC11451987, DOI: 10.1371/journal.pone.0307235.Peer-Reviewed Original ResearchConceptsVeterans Health AdministrationCOVID-19 hospitalizationArea under the receiver operating characteristic curveComprehensive electronic health recordNational cohortElectronic health recordsAll-cause mortalityNational cohort of patientsFull modelHealth recordsHealth AdministrationReceipt of COVID-19 vaccineMortality riskEpidemiology of COVID-19COVID-19High-risk patientsBrier scoreCohort of patientsAnti-SARS-CoV-2 treatmentCOVID-19 vaccineReceiver operating characteristic curveCalibration interceptHospitalAntiviral treatmentAvailability of effective vaccinesLarge-Scale Proteomics in Early Pregnancy and Hypertensive Disorders of Pregnancy
Greenland P, Segal M, McNeil R, Parker C, Pemberton V, Grobman W, Silver R, Simhan H, Saade G, Ganz P, Mehta P, Catov J, Merz C, Varagic J, Khan S, Parry S, Reddy U, Mercer B, Wapner R, Haas D. Large-Scale Proteomics in Early Pregnancy and Hypertensive Disorders of Pregnancy. JAMA Cardiology 2024, 9: 791-799. PMID: 38958943, PMCID: PMC11223045, DOI: 10.1001/jamacardio.2024.1621.Peer-Reviewed Original ResearchArea under the receiver operating characteristic curveCase-control studyHypertensive disordersEarly pregnancyClinical dataSmall-for-gestational-age infantsPrediction of hypertensive disordersSmall-for-gestational-ageHypertensive disorders of pregnancyPrediction of HDPDisorders of pregnancyNested case-control studyPlasma samplesMulticenter observational studyStored plasma samplesReceiver operating characteristic curveBody mass indexGestational hypertensionNon-Hispanic blacksPreterm birthFetal sexFirst-trimesterNon-Hispanic whitesPregnancy outcomesMaternal raceDeep-Transfer-Learning–Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer
Kim S, Kim S, Kim E, Cecchini M, Park M, Choi J, Kim S, Hwang H, Kang C, Choi H, Shin S, Kang J, Lee C. Deep-Transfer-Learning–Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer. JCO Clinical Cancer Informatics 2024, 8: e2400021. PMID: 39151114, DOI: 10.1200/cci.24.00021.Peer-Reviewed Original ResearchConceptsArea under the receiver operating characteristic curveSurvival of patientsCT reportsPancreatic cancerNatural language processingC-indexPredicting survivalOverall survival of patientsTertiary hospitalPredicting 1-year survivalPredicting survival of patientsImproved C-indexSurvival informationPancreatic cancer survivalReceiver operating characteristic curveInternal test data setNLP modelsComputed tomography reportsLanguage processingKorean tertiary hospitalOverall survivalConsecutive patientsActual survivalConcordance indexPatientsElevated myocardial extracellular volume fraction is associated with the development of conduction pathway defects following transcatheter aortic valve replacement
Feroze R, Kang P, Dallan L, Akula N, Galo J, Yoon S, Ukaigwe A, Filby S, Baeza C, Pelletier M, Rushing G, Rajagopalan S, Al‐Kindi S, Rashid I, Attizzani G. Elevated myocardial extracellular volume fraction is associated with the development of conduction pathway defects following transcatheter aortic valve replacement. Catheterization And Cardiovascular Interventions 2024, 104: 1119-1128. PMID: 38952304, DOI: 10.1002/ccd.31136.Peer-Reviewed Original ResearchMeSH KeywordsAction PotentialsAgedAged, 80 and overAortic ValveAortic Valve StenosisArea Under CurveAtrioventricular BlockBundle-Branch BlockCardiac Pacing, ArtificialFemaleFibrosisHeart Conduction SystemHumansMagnetic Resonance Imaging, CineMaleMyocardiumPacemaker, ArtificialPredictive Value of TestsRetrospective StudiesRisk AssessmentRisk FactorsROC CurveTime FactorsTranscatheter Aortic Valve ReplacementTreatment OutcomeConceptsTranscatheter aortic valve replacementCardiac magnetic resonance imagingLate gadolinium enhancementRight bundle branch blockArea under the receiver operating characteristic curveAortic valve replacementReceiver operating curveMyocardial fibrosisPost-TAVRConduction defectsBundle branch blockAssociations of myocardial fibrosisExtracellular volumeConduction diseaseValve replacementGadolinium enhancementPermanent pacemakerConduction abnormalitiesConduction deficitsHeart blockBranch blockRisk of heart blockSeptal late gadolinium enhancementMyocardial extracellular volume fractionBaseline conduction diseaseLeveraging machine learning to develop a postoperative predictive model for postoperative urinary retention following lumbar spine surgery
Malnik S, Porche K, Mehkri Y, Yue S, Maciel C, Lucke-Wold B, Robicsek S, Decker M, Busl K. Leveraging machine learning to develop a postoperative predictive model for postoperative urinary retention following lumbar spine surgery. Frontiers In Neurology 2024, 15: 1386802. PMID: 38988605, PMCID: PMC11233696, DOI: 10.3389/fneur.2024.1386802.Peer-Reviewed Original ResearchPostoperative urinary retentionLumbar spine surgerySpine surgeryUrinary retentionPatient demographicsIncidence of postoperative urinary retentionRetrospective observational cohort studyTertiary academic medical centerIndwelling catheter placementIncreased patient morbidityReceiver operating characteristic curveArea under the receiver operating characteristic curveObservational cohort studyAcademic medical centerBody mass indexPostoperative prediction modelLogistic regression modelsIntraoperative variablesIntraoperative factorsCatheter placementAnesthesia variablesPatient morbidityMass indexSurgical proceduresCohort study
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply