2021
Privacy-protecting, reliable response data discovery using COVID-19 patient observations
Kim J, Neumann L, Paul P, Day M, Aratow M, Bell D, Doctor J, Hinske L, Jiang X, Kim K, Matheny M, Meeker D, Pletcher M, Schilling L, SooHoo S, Xu H, Zheng K, Ohno-Machado L, Anderson D, Anderson N, Balacha C, Bath T, Baxter S, Becker-Pennrich A, Bernstam E, Carter W, Chau N, Choi Y, Covington S, DuVall S, El-Kareh R, Florian R, Follett R, Geisler B, Ghigi A, Gottlieb A, Hu Z, Ir D, Knight T, Koola J, Kuo T, Lee N, Mansmann U, Mou Z, Murphy R, Neumann L, Nguyen N, Niedermayer S, Park E, Perkins A, Post K, Rieder C, Scherer C, Soares A, Soysal E, Tep B, Toy B, Wang B, Wu Z, Zhou Y, Zucker R. Privacy-protecting, reliable response data discovery using COVID-19 patient observations. Journal Of The American Medical Informatics Association 2021, 28: 1765-1776. PMID: 34051088, PMCID: PMC8194878, DOI: 10.1093/jamia/ocab054.Peer-Reviewed Original Research
2019
Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm
Duan R, Boland M, Liu Z, Liu Y, Chang H, Xu H, Chu H, Schmid C, Forrest C, Holmes J, Schuemie M, Berlin J, Moore J, Chen Y. Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm. Journal Of The American Medical Informatics Association 2019, 27: 376-385. PMID: 31816040, PMCID: PMC7025371, DOI: 10.1093/jamia/ocz199.Peer-Reviewed Original Research
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 FactsHospitalInteractive medical word sense disambiguation through informed learning
Wang Y, Zheng K, Xu H, Mei Q. Interactive medical word sense disambiguation through informed learning. Journal Of The American Medical Informatics Association 2018, 25: 800-808. PMID: 29584896, PMCID: PMC6658868, DOI: 10.1093/jamia/ocy013.Peer-Reviewed Original Research
2017
An Empirical Study for Impacts of Measurement Errors on EHR based Association Studies.
Duan R, Cao M, Wu Y, Huang J, Denny J, Xu H, Chen Y. An Empirical Study for Impacts of Measurement Errors on EHR based Association Studies. AMIA Annual Symposium Proceedings 2017, 2016: 1764-1773. PMID: 28269935, PMCID: PMC5333313.Peer-Reviewed Original Research
2014
Determining molecular predictors of adverse drug reactions with causality analysis based on structure learning
Liu M, Cai R, Hu Y, Matheny M, Sun J, Hu J, Xu H. Determining molecular predictors of adverse drug reactions with causality analysis based on structure learning. Journal Of The American Medical Informatics Association 2014, 21: 245-251. PMID: 24334612, PMCID: PMC3932464, DOI: 10.1136/amiajnl-2013-002051.Peer-Reviewed Original Research
2013
Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy
Mani S, Chen Y, Li X, Arlinghaus L, Chakravarthy A, Abramson V, Bhave S, Levy M, Xu H, Yankeelov T. Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy. Journal Of The American Medical Informatics Association 2013, 20: 688-695. PMID: 23616206, PMCID: PMC3721158, DOI: 10.1136/amiajnl-2012-001332.Peer-Reviewed Original ResearchConceptsNeoadjuvant chemotherapyFeature selectionCycles of NACPredictive model buildingTime most patientsBreast cancer patientsImportant clinical problemCourse of therapyMachine learningDynamic contrast-enhanced MRIContrast-enhanced MRIQuantitative dynamic contrast-enhanced MRIMost patientsTreatment regimenCancer patientsClinical variablesTherapeutic responseBreast cancerPredictive modeling approachClinical problemData show promiseLogistic regressionPatientsMachineDiffusion-weighted MRI data
2012
Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs
Liu M, Wu Y, Chen Y, Sun J, Zhao Z, Chen X, Matheny M, Xu H. Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs. Journal Of The American Medical Informatics Association 2012, 19: e28-e35. PMID: 22718037, PMCID: PMC3392844, DOI: 10.1136/amiajnl-2011-000699.Peer-Reviewed Original ResearchConceptsAdverse drug reactionsPost-marketing phaseDrug reactionsSevere adverse drug reactionsImportant adverse drug reactionsWithdrawal of rofecoxibPotential adverse drug reactionsPost-marketing surveillanceADR predictionPatient morbidityClinical trialsMajor causeLarge-scale studiesDrugsMolecular pathwaysDrug developmentPhenotypic featuresSignificant improvementPhenotypic characteristicsEarly stages