2025
Establishment and Validation of a Risk Prediction Model for Non-Suicidal Self-Injury Among Adolescents Based on Machine Learning Methods - Jiangsu Province, China, 2023.
Wang X, Wang Y, Tang J, Wang Y, Zhang R, Zhang X, Yang W, Du W, Wang F, Yang J. Establishment and Validation of a Risk Prediction Model for Non-Suicidal Self-Injury Among Adolescents Based on Machine Learning Methods - Jiangsu Province, China, 2023. China CDC Weekly 2025, 7: 952-958. PMID: 40671703, PMCID: PMC12259475, DOI: 10.46234/ccdcw2025.160.Peer-Reviewed Original ResearchRisk prediction modelNon-Suicidal Self-InjuryPublic health practiceMental health supportFamily environmentMental Well-BeingHistory of drinking alcoholPersonalized prevention strategiesPublic health concernHealth supportHealth practicesBehavioral interventionsEmotional symptomsPrevention strategiesDrinking alcoholSelf-injurySleep qualitySupportive family environmentPredictors of non-suicidal self-injuryHealth concernWell-beingComprehensive Behavioral InterventionJiangsu ProvinceAdolescentsConduct problemsTowards a dynamic model to estimate evolving risk of major bleeding after percutaneous coronary intervention
Hurley N, Desai N, Dhruva S, Khera R, Schulz W, Huang C, Curtis J, Masoudi F, Rumsfeld J, Negahban S, Krumholz H, Mortazavi B. Towards a dynamic model to estimate evolving risk of major bleeding after percutaneous coronary intervention. PLOS Digital Health 2025, 4: e0000906. PMID: 40560847, PMCID: PMC12193038, DOI: 10.1371/journal.pdig.0000906.Peer-Reviewed Original ResearchNational Cardiovascular Data RegistryPercutaneous coronary interventionPrescription of medicationsRisk predictionArea under the receiver operating characteristic curveRisk prediction modelTreatment decision makingIndividualized carePatient dischargeData registryRisk estimatesRisk modelPrimary outcomeIndex admissionRisk informationModerate riskCoronary interventionPercutaneous coronary intervention proceduresRisk factorsPatient characteristicsIn-hospital bleeding eventsHigh riskLow riskMedical historyRegistryDevelopment and Validation of Models to Estimate the Incident Risk of Cognitive Impairment and Atherosclerotic Cardiovascular Disease in Older Adults
Nanna M, Wojdyla D, Peterson E, Navar A, Williamson J, Colantonio L, Wang S, Jamil Y, Bertoni A, Nahid M, Damluji A, Goyal P, Chaudhry S, Gill T, Alexander K. Development and Validation of Models to Estimate the Incident Risk of Cognitive Impairment and Atherosclerotic Cardiovascular Disease in Older Adults. Journal Of The American Heart Association 2025, 14: e038949. PMID: 40401627, PMCID: PMC12229195, DOI: 10.1161/jaha.124.038949.Peer-Reviewed Original ResearchConceptsRisk of cognitive impairmentAtherosclerotic cardiovascular disease eventsAtherosclerotic cardiovascular diseaseRisk prediction modelCognitive impairmentOlder adultsMeasures of healthIncident cognitive impairmentOlder person's riskPooled Cohort EquationsCardiovascular diseaseRisk of deathCohort EquationsFramingham OffspringOlder personsExternal validationFunctional statusPersonal riskIncidence riskValidation cohortYoung adultsInternal validityFraminghamCohortTreatment decisionsImpacts of sample weighting on transferability of risk prediction models across EHR-Linked biobanks with different recruitment strategies
Salvatore M, Mondul A, Friese C, Hanauer D, Xu H, Pearce C, Mukherjee B. Impacts of sample weighting on transferability of risk prediction models across EHR-Linked biobanks with different recruitment strategies. Journal Of Biomedical Informatics 2025, 167: 104853. PMID: 40398830, DOI: 10.1016/j.jbi.2025.104853.Peer-Reviewed Original ResearchConceptsPS weightingRisk prediction modelOdds ratioArea under the receiver operating curveEHR-linked biobanksMichigan Genomics InitiativePhenotype risk scoreYears prior to diagnosisRisk score distributionCancer risk stratificationHigh-risk populationImprove risk predictionEHR dataPoststratification weightsRecruitment strategiesRisk stratificationCharlson Comorbidity IndexAlcohol consumptionRisk scoreBiobankRisk factorsRisk predictionUnderrepresented groupsComorbidity indexReceiver operating curveDoes inclusion of neighborhood variables improve clinical risk prediction for advanced prostate cancer in Black and White men?
Tagai E, Handorf E, Sorice K, Fang C, Deng M, Daly M, Reese A, Henry K, Ragin C, Lynch S. Does inclusion of neighborhood variables improve clinical risk prediction for advanced prostate cancer in Black and White men? Urologic Oncology Seminars And Original Investigations 2025, 43: 334.e17-334.e24. PMID: 40121103, PMCID: PMC12068980, DOI: 10.1016/j.urolonc.2025.02.021.Peer-Reviewed Original ResearchConceptsNeighborhood-level variablesProstate Cancer Prevention TrialNeighborhood variablesProtective service occupationsBlack menNeighborhood-level risk factorsWhite menNeighborhood-level povertyMedical oncology clinicUniversity Health SystemCancer Prevention TrialRisk prediction toolsLogistic regression modelsRisk prediction modelSocial environmental variablesPatients' medical recordsService occupationsHigh-grade PCaCurrent risk prediction modelsHealth systemPersistent disparitiesOncology clinicInsurance statusAssociated with ratesClinical risk predictionReporting of Fairness Metrics in Clinical Risk Prediction Models Used for Precision Health: Scoping Review
Rountree L, Lin Y, Liu C, Salvatore M, Admon A, Nallamothu B, Singh K, Basu A, Bu F, Mukherjee B. Reporting of Fairness Metrics in Clinical Risk Prediction Models Used for Precision Health: Scoping Review. Online Journal Of Public Health Informatics 2025, 17: e66598. PMID: 39962044, PMCID: PMC11966066, DOI: 10.2196/66598.Peer-Reviewed Original ResearchClinical risk prediction modelsRisk prediction modelFairness metricsSex-stratified modelsEthnicity dataPrecision healthClinical risk predictionSensitive featuresStudy populationCardiovascular diseaseRisk predictionEvaluate potential disparitiesTraining dataPotential disparitiesEmpirical evaluationPrediction modelPrimary preventionInformatics systemsHigh-impact publicationsCOVID-19Metrics usageStudy cohortGoogle ScholarImplementation frameworkCOVID-19 model
2024
Study protocol: Comparison of different risk prediction modelling approaches for COVID-19 related death using the OpenSAFELY platform
Collaborative T, Williamson E, Tazare J, Bhaskaran K, Walker A, McDonald H, Tomlinson L, Bacon S, Bates C, Curtis H, Forbes H, Minassian C, Morton C, Nightingale E, Mehrkar A, Evans D, Nicholson B, Leon D, Inglesby P, MacKenna B, Cockburn J, Davies N, Hulme W, Morley J, Douglas I, Rentsch C, Mathur R, Wong A, Schultze A, Croker R, Parry J, Hester F, Harper S, Perera R, Grieve R, Harrison D, Steyerberg E, Eggo R, Diaz-Ordaz K, Keogh R, Evans S, Smeeth L, Goldacre B. Study protocol: Comparison of different risk prediction modelling approaches for COVID-19 related death using the OpenSAFELY platform. Wellcome Open Research 2024, 5: 243. PMID: 39931522, PMCID: PMC11809169, DOI: 10.12688/wellcomeopenres.16353.2.Peer-Reviewed Original ResearchRisk prediction modelPrimary care electronic health records dataElectronic health record dataTime-varying measuresHealth record dataRisk of poor outcomesOpenSAFELY platformChronic disease settingsRestricted social contactDeath dataCOVID-19 related deathsWorld Health OrganizationCohort approachCOVID-19 deathsRecord dataCOVID-19Population of adult patientsHealth OrganizationRisk predictionOpenSAFELYSocial contactPerceived RiskPolicy changesRelated deathsAdult patientsAssociation between growth differentiation factor-15 and adverse outcomes among patients with heart failure: A systematic literature review
Javaheri A, Ozcan M, Moubarak L, Smoyer K, Rossulek M, Revkin J, Groarke J, Tarasenko L, Kosiborod M. Association between growth differentiation factor-15 and adverse outcomes among patients with heart failure: A systematic literature review. Heliyon 2024, 10: e35916. PMID: 39229539, PMCID: PMC11369438, DOI: 10.1016/j.heliyon.2024.e35916.Peer-Reviewed Original ResearchGDF-15 concentrationsGrowth differentiation factor 15Differentiation factor 15GDF-15Heart failureMultivariate analysisRenal functionComposite outcomeAdverse outcomesOptimal treatment regimensPredictors of mortalityCardiovascular-related mortalityCross-sectional studyPrognostic roleTreatment regimensClinical risk prediction modelsPoor outcomeRisk prediction modelExercise capacityEligibility criteriaPatientsPRISMA guidelinesMortalityNonfatal outcomesOutcomesFeasibility of In-Hospital Administration of a Tool to Predict Persistent Post-ICU Functional Impairment Among Older ICU Survivors A Pilot Study
Stevenson J, Murphy T, Tessier-Sherman B, Pisani M, Gill T, Ferrante L. Feasibility of In-Hospital Administration of a Tool to Predict Persistent Post-ICU Functional Impairment Among Older ICU Survivors A Pilot Study. CHEST Critical Care 2024, 2: 100093. PMID: 39822381, PMCID: PMC11737545, DOI: 10.1016/j.chstcc.2024.100093.Peer-Reviewed Original ResearchRisk prediction toolsICU survivorsIn-hospital administrationOlder adultsFunctional impairmentPilot studyIn-hospital mobilityOlder ICU survivorsDevelopment of risk prediction modelsHospital-related factorsIn-hospital factorsPresence of deliriumRisk prediction modelModel discriminationPersistent functional impairmentStatistical significanceHospital settingStudy designFeasibility thresholdDaily activitiesIncreased riskInternational Consensus ConferenceConsensus conferenceSurvivorsCritical illnessPredicting the Population Risk of Suicide Using Routinely Collected Health Administrative Data in Quebec, Canada: Model-Based Synthetic Estimation Study
Wang J, Kharrat F, Gariépy G, Gagné C, Pelletier J, Massamba V, Lévesque P, Mohammed M, Lesage A. Predicting the Population Risk of Suicide Using Routinely Collected Health Administrative Data in Quebec, Canada: Model-Based Synthetic Estimation Study. JMIR Public Health And Surveillance 2024, 10: e52773. PMID: 38941610, PMCID: PMC11245657, DOI: 10.2196/52773.Peer-Reviewed Original ResearchConceptsHealth administrative dataCommunity-level predictorsRisk prediction modelHealth care systemPopulation riskAdministrative dataHigh-risk regionsHealth systemCare systemIndividual's risk of suicideApplication of risk prediction modelsPopulation health planningHealth administrative databasesSignificant public health issueCase-control study designCommunity-level variablesRisk prediction toolsPublic health issueRisk of suicideSex-specific modelsProportion of suicidesIndividual-level predictorsAdministrative databasesHealth plansSuicide preventionAnalysis of Clinical Criteria for Discharge Among Patients Hospitalized for COVID-19: Development and Validation of a Risk Prediction Model
Schnipper J, Oreper S, Hubbard C, Kurbegov D, Egloff S, Najafi N, Valdes G, Siddiqui Z, O.’Leary K, Horwitz L, Lee T, Auerbach A. Analysis of Clinical Criteria for Discharge Among Patients Hospitalized for COVID-19: Development and Validation of a Risk Prediction Model. Journal Of General Internal Medicine 2024, 39: 2649-2661. PMID: 38937368, PMCID: PMC11534938, DOI: 10.1007/s11606-024-08856-x.Peer-Reviewed Original ResearchTime of dischargeInternal validation setPost-discharge readmissionRisk factorsDays of dischargeRetrospective observational cohort studyIndependent risk factorReceiver operating characteristic curveObservational cohort studyReversible risk factorsAssociated with lower oddsPatients 7Lack of improvementRetrospective studyValidation setFollow-upCohort studyRisk prediction modelReadmission risk scoreAcademic centersPositive testPatientsRisk scoreCOVID-19 respiratory diseaseLower oddsIdentifying Veterans Who Benefit From Nirmatrelvir-Ritonavir: A Target Trial Emulation
Yan L, Bui D, Li Y, Rajeevan N, Rowneki M, Berry K, Argraves S, Huang Y, Hynes D, Cunningham F, Huang G, Aslan M, Ioannou G, Bajema K. Identifying Veterans Who Benefit From Nirmatrelvir-Ritonavir: A Target Trial Emulation. Clinical Infectious Diseases 2024, 79: 643-651. PMID: 38864601, DOI: 10.1093/cid/ciae202.Peer-Reviewed Original ResearchRisk quartileVeterans Health AdministrationLowest risk quartileHighest risk quartileTarget trial emulationRisk prediction modelUntreated veteransRisk of deathOlder veteransYounger veteransHealth AdministrationTrial emulationMeasure IncidenceNirmatrelvir-ritonavirVeteransHospitalUntreated participantsCOVID-19QuartileRiskSevere coronavirus disease 2019ParticipantsPersonsCoronavirus disease 2019Severe COVID-19[Prediction model related to 6-year risk of frailty in older adults aged 65 years or above in China].
Zhou J, Qi L, Wang J, Liu S, Shi W, Ye L, Zhang Z, Zhang Z, Meng X, Cui J, Chen C, Lyu Y, Shi X. [Prediction model related to 6-year risk of frailty in older adults aged 65 years or above in China]. Chinese Journal Of Epidemiology 2024, 45: 809-816. PMID: 38889980, DOI: 10.3760/cma.j.cn112338-20231205-00333.Peer-Reviewed Original ResearchConceptsDaily living scoresPredictors of frailtyArea under the receiver operating characteristic curveIncident frailtyOlder adultsLiving scoresChinese Longitudinal Healthy Longevity SurveyRisk thresholdSelf-rated healthChinese older adultsRisk of incident frailtyRisk of frailtyFree of frailtyPhysical examination variablesCox proportional hazards regression modelsProportional hazards regression modelsRisk prediction modelInstrumental activitiesHazards regression modelsLongevity SurveyFrailty incidenceFollow-up timeDecision-curve analysisOlder personsReceiver operating characteristic curveEstimating risk for pancreatic cancer among 9.4 million veterans in care.
Wang L, Rahimi Larki N, Skanderson M, Tate J, Hauser R, Brandt C, Yang Y, Justice A. Estimating risk for pancreatic cancer among 9.4 million veterans in care. Journal Of Clinical Oncology 2024, 42: 10544-10544. DOI: 10.1200/jco.2024.42.16_suppl.10544.Peer-Reviewed Original ResearchVeterans Health AdministrationGeneral populationAlcohol useIntegrated health systemElectronic health recordsTen-year riskHistory of cancerLoss to follow-upFollow-upEvaluated model discriminationMedian baseline ageCox proportional hazards modelsRisk prediction modelHealth recordsProportional hazards modelHealth systemHealth AdministrationMultivariate Cox proportional hazards modelSmoking statusCharlson Comorbidity IndexBaseline ageClinical reasoningRange of risksHazards modelFinal predictorsDisease burden of cardiovascular conditions complicating pregnancy in Sri Lanka: a protocol
Hettiarachchi A, Lokunarangoda N, Agampodi T, Agampodi S. Disease burden of cardiovascular conditions complicating pregnancy in Sri Lanka: a protocol. F1000Research 2024, 10: 1028. PMID: 38504849, PMCID: PMC10948970, DOI: 10.12688/f1000research.52539.4.Peer-Reviewed Original ResearchCardiovascular diseasePeriod of amenorrhoeaBurden of CVDAdverse pregnancy outcomesEffects of CVDProspective cohort studyCardiovascular disease morbidityEvidence-based guidelinesRoutine clinical assessmentRisk prediction modelPostpartum morbidityPregnancy clinicWard admissionAntenatal careCohort studyPregnancy outcomesMaternal deathsMiddle-income countriesCVD burdenDisease morbidityEarly pregnancyFirst trimesterPregnant womenMaternal mortalityAppropriate referralDisease burden of cardiovascular conditions complicating pregnancy in Sri Lanka: a protocol
Hettiarachchi A, Lokunarangoda N, Agampodi T, Agampodi S. Disease burden of cardiovascular conditions complicating pregnancy in Sri Lanka: a protocol. F1000Research 2024, 10: 1028. DOI: 10.12688/f1000research.52539.4.Peer-Reviewed Original ResearchCardiovascular diseaseBurden of cardiovascular diseasePeriod of amenorrhoeaMedical Officer of Health (MOHCardiovascular disease morbidityCardiovascular disease burdenMiddle-income countriesEvidence-based guidelinesProspective cohort studyEffects of cardiovascular diseaseRisk prediction modelDisease complicating pregnancyAntenatal careMaternal mortalityPostpartum morbidityMaternal deathsPostpartum hemorrhageWard admissionTelephone interviewsConsultant cardiologistCohort studyDisease morbidityPregnancy clinicEligibility criteriaDisease burden
2023
Using Multi-Modal Electronic Health Record Data for the Development and Validation of Risk Prediction Models for Long COVID Using the Super Learner Algorithm
Jin W, Hao W, Shi X, Fritsche L, Salvatore M, Admon A, Friese C, Mukherjee B. Using Multi-Modal Electronic Health Record Data for the Development and Validation of Risk Prediction Models for Long COVID Using the Super Learner Algorithm. Journal Of Clinical Medicine 2023, 12: 7313. PMID: 38068365, PMCID: PMC10707399, DOI: 10.3390/jcm12237313.Peer-Reviewed Original ResearchComposite risk scoreRisk scoreElectronic health recordsAnalyses identified several factorsValidation of risk prediction modelsModerate discriminatory abilityRisk prediction modelPost-acute sequelae of COVID-19Health recordsCombined risk scorePost-AcuteIdentification of individualsPrevention effortsSuper Learner algorithmMedical recordsHealthcare challengesPublic healthMedical phenotypesCOVID-19Increased riskPredictive factorsCOVID-19 infectionRecord dataPost-acute sequelaeHigh riskLung Cancer Risk Prediction Models for Asian Ever-Smokers
Yang J, Wen W, Zahed H, Zheng W, Lan Q, Abe S, Rahman M, Islam M, Saito E, Gupta P, Tamakoshi A, Koh W, Gao Y, Sakata R, Tsuji I, Malekzadeh R, Sugawara Y, Kim J, Ito H, Nagata C, You S, Park S, Yuan J, Shin M, Kweon S, Yi S, Pednekar M, Kimura T, Cai H, Lu Y, Etemadi A, Kanemura S, Wada K, Chen C, Shin A, Wang R, Ahn Y, Shin M, Ohrr H, Sheikh M, Blechter B, Ahsan H, Boffetta P, Chia K, Matsuo K, Qiao Y, Rothman N, Inoue M, Kang D, Robbins H, Shu X. Lung Cancer Risk Prediction Models for Asian Ever-Smokers. Journal Of Thoracic Oncology 2023, 19: 451-464. PMID: 37944700, PMCID: PMC11126207, DOI: 10.1016/j.jtho.2023.11.002.Peer-Reviewed Original ResearchLow-intensity smokersLong-term quittersLung cancer riskRisk prediction modelProspective cohortCancer riskPopulation-based prospective cohortLung cancer risk prediction modelsLung cancer prediction modelsCancer risk prediction modelsRisk-based screeningRisk assessment toolEver smokersPooled analysisCancer prediction modelAsian cohortSmokersHighest AUCWestern populationsAsian populationsCohortGood calibrationQuittersAssessment toolRiskRecent advances and controversial issues in the optimal management of asymptomatic carotid stenosis
Paraskevas K, Brown M, Lal B, Myrcha P, Lyden S, Schneider P, Poredos P, Mikhailidis D, Secemsky E, Musialek P, Mansilha A, Parikh S, Silvestrini M, Lavie C, Dardik A, Blecha M, Liapis C, Zeebregts C, Nederkoorn P, Poredos P, Gurevich V, Jawien A, Lanza G, Gray W, Gupta A, Svetlikov A, Fernandes E Fernandes J, Nicolaides A, White C, Meschia J, Cronenwett J, Schermerhorn M, AbuRahma A. Recent advances and controversial issues in the optimal management of asymptomatic carotid stenosis. Journal Of Vascular Surgery 2023, 79: 695-703. PMID: 37939746, DOI: 10.1016/j.jvs.2023.11.004.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsBest medical treatmentTranscarotid artery revascularizationAsymptomatic carotid stenosisCarotid revascularization proceduresRevascularization proceduresCarotid endarterectomyCarotid stenosisPatient subgroupsRisk prediction modelCognitive dysfunctionOptimal managementStroke risk prediction modelManagement of patientsSpecific patient subgroupsDuplex ultrasound examinationTreatment of patientsIndividual patient preferencesPubMed/PubMed CentralIndividual patient needsCarotid plaque ulcerationMagnetic resonance angiography scansArtery revascularizationSilent infarctsStroke riskCerebrovascular reserveA framework for assessing interactions for risk stratification models: the example of ovarian cancer
Phung M, Lee A, McLean K, Anton-Culver H, Bandera E, Carney M, Chang-Claude J, Cramer D, Doherty J, Fortner R, Goodman M, Harris H, Jensen A, Modugno F, Moysich K, Pharoah P, Qin B, Terry K, Titus L, Webb P, Wu A, Zeinomar N, Ziogas A, Berchuck A, Cho K, Hanley G, Meza R, Mukherjee B, Pike M, Pearce C, Trabert B. A framework for assessing interactions for risk stratification models: the example of ovarian cancer. Journal Of The National Cancer Institute 2023, 115: 1420-1426. PMID: 37436712, PMCID: PMC10637032, DOI: 10.1093/jnci/djad137.Peer-Reviewed Original ResearchConceptsFamily history of ovarian cancerOvarian Cancer Association ConsortiumHistory of ovarian cancerFirst-degree family historyMenopausal statusRisk stratification modelCase-control studyRisk prediction modelOvarian cancerDisease riskAccurate risk stratification modelsStratification modelRisk/protective factorsDepot medroxyprogesterone acetate useProtective factorsFactor analysisRiskComprehensive analysis of interactionsCancerAcetate useUnequivocal riskStatusBreastfeedingAnalysis of interactionsPairwise interactions
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply