2022
Exploring the clinical and genetic associations of adult weight trajectories using electronic health records in a racially diverse biobank: a phenome-wide and polygenic risk study
Xu J, Johnson JS, Signer R, Consortium E, Birgegård A, Jordan J, Kennedy MA, Landén M, Maguire SL, Martin NG, Mortensen PB, Petersen LV, Thornton LM, Bulik CM, Huckins LM. Exploring the clinical and genetic associations of adult weight trajectories using electronic health records in a racially diverse biobank: a phenome-wide and polygenic risk study. The Lancet Digital Health 2022, 4: e604-e614. PMID: 35780037, PMCID: PMC9612590, DOI: 10.1016/s2589-7500(22)00099-1.Peer-Reviewed Original ResearchMeSH KeywordsAdultBiological Specimen BanksBody-Weight TrajectoryElectronic Health RecordsGenome-Wide Association StudyHumansMultifactorial InheritanceConceptsElectronic health recordsPolygenic risk scoresWeight trajectoriesDepression polygenic risk scoresObesity polygenic risk scoresHealth recordsWeight changeUK BiobankIndividual health statusLower disease riskGenetic associationPatient populationUS National InstitutesWeight managementStable weightRisk scoreHealthy populationHealth statusAnorexia nervosaBioMe BiobankDisease riskDisorder diagnosisMental healthWeight lossPhenome-wide association study
2020
Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation
Vaid A, Somani S, Russak A, De Freitas J, Chaudhry F, Paranjpe I, Johnson K, Lee S, Miotto R, Richter F, Zhao S, Beckmann N, Naik N, Kia A, Timsina P, Lala A, Paranjpe M, Golden E, Danieletto M, Singh M, Meyer D, O'Reilly P, Huckins L, Kovatch P, Finkelstein J, Freeman R, Argulian E, Kasarskis A, Percha B, Aberg J, Bagiella E, Horowitz C, Murphy B, Nestler E, Schadt E, Cho J, Cordon-Cardo C, Fuster V, Charney D, Reich D, Bottinger E, Levin M, Narula J, Fayad Z, Just A, Charney A, Nadkarni G, Glicksberg B. Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation. Journal Of Medical Internet Research 2020, 22: e24018. PMID: 33027032, PMCID: PMC7652593, DOI: 10.2196/24018.Peer-Reviewed Original ResearchMeSH KeywordsAcute Kidney InjuryAdolescentAdultAgedAged, 80 and overBetacoronavirusCohort StudiesCoronavirus InfectionsCOVID-19Electronic Health RecordsFemaleHospital MortalityHospitalizationHospitalsHumansMachine LearningMaleMiddle AgedNew York CityPandemicsPneumonia, ViralPrognosisRisk AssessmentROC CurveSARS-CoV-2Young AdultConceptsElectronic health recordsNew York CityYork CityMount Sinai Health SystemSinai Health SystemMortality predictionAdmitted to hospitalAt-risk patientsHealth recordsHealth systemEHR dataIn-hospital mortalityEarly identification of high-risk patientsCOVID-19Identification of high-risk patientsMultiple hospitalsStudy populationPatient characteristicsSingle hospitalHospitalArea under the receiver operating characteristic curveEarly identificationPredicting mortalityCohort of patientsCOVID-19 pandemicImplicit bias of encoded variables: frameworks for addressing structured bias in EHR–GWAS data
Dueñas H, Seah C, Johnson J, Huckins L. Implicit bias of encoded variables: frameworks for addressing structured bias in EHR–GWAS data. Human Molecular Genetics 2020, 29: r33-r41. PMID: 32879975, PMCID: PMC7530523, DOI: 10.1093/hmg/ddaa192.Peer-Reviewed Original ResearchMeSH KeywordsComputational BiologyDiseaseElectronic Health RecordsGenome-Wide Association StudyHumansPhenotypePolymorphism, Single NucleotidePrejudiceConceptsElectronic health recordsUse of electronic health recordsElectronic health record dataElectronic health record analysisGenome-wide association studiesHealth recordsPhenotype definitionAssociation studiesMedical recordsClinical decisionsPhenotypic characterizationPhenotypic analysisClinically useful insightsPotential biasPresentation of diseaseDegree of biasHomogeneous cohortClinicPhenotypeScalable mannerRecordsCohortBias