2018
A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set
Rasmy L, Wu Y, Wang N, Geng X, Zheng W, Wang F, Wu H, Xu H, Zhi D. A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set. Journal Of Biomedical Informatics 2018, 84: 11-16. PMID: 29908902, PMCID: PMC6076336, DOI: 10.1016/j.jbi.2018.06.011.Peer-Reviewed Original ResearchConceptsRecurrent neural networkOnset riskCapability of RNNCerner Health FactsHeterogeneous EHR dataHeart failure patientsData setsElectronic health record dataDeep learning modelsDifferent patient populationsNeural network-based predictive modelDifferent patient groupsHealth record dataEHR data setsPredictive modelingSmall data setsFailure patientsPatient groupPatient populationReduction of AUCNeural networkRNN modelRETAIN modelHealth FactsHospital
2017
Evaluating the role of race and medication in protection of uterine fibroids by type 2 diabetes exposure
Velez Edwards D, Hartmann K, Wellons M, Shah A, Xu H, Edwards T. Evaluating the role of race and medication in protection of uterine fibroids by type 2 diabetes exposure. BMC Women's Health 2017, 17: 28. PMID: 28399866, PMCID: PMC5387248, DOI: 10.1186/s12905-017-0386-y.Peer-Reviewed Original ResearchMeSH KeywordsAdultAgedBlack PeopleCase-Control StudiesCohort StudiesDiabetes Mellitus, Type 2FemaleHumansLeiomyomaMiddle AgedOdds RatioUnited StatesWhite PeopleConceptsT2D medicationsUF riskAnnual healthcare costsElectronic medical record algorithmCase-control studyLarge clinical populationFurther mechanistic researchBackgroundUterine fibroidsT2D diagnosisDiabetes exposureMedication typeDiabetes presenceInsulin usersUterine fibroidsInsulin treatmentProtective associationStratified analysisClinical cohortConclusionsThese dataProtective effectLarge cohortCase-control statusHealthcare costsT2DMedications