Michael Kane, PhD, MA, MS
DownloadHi-Res Photo
Cards
Contact Info
About
Titles
Assistant Professor Adjunct of Biostatistics
Biography
Michael Kane is an Assistant Professor in Yale University's Biostatistics Department. He develops methods in statistical/machine learning in biomedicine to understand patient-level heterogeneity in clinical trials and to understand patterns of human mobility.
Appointments
Biostatistics
Assistant Professor AdjunctPrimary
Other Departments & Organizations
- Analytics Clinics
- Biostatistics
- Global Health Studies
- Yale School of Public Health
Education & Training
- PhD
- Yale University (2010)
- MA
- Yale University (2006)
- MS
- Rochester Institute of Technology, Electrical Engineering (2003)
- MS
- Rochester Institute of Technology (2003)
- BS
- Rochester Institute of Technology, Computer Engineering (2000)
Research
Overview
Michael Kane is an
associate research scientist at the Yale Center for Analytical Sciences. His
primary research interests are in the areas of high-performance statistical
computing as well as graphical models.
Michael Kane received his
M.S. from Rochester Institute of Technology and his M.A. and Ph.D. from Yale
University. He is the recipient of the John M. Chamber’s Statistical Software
Award for from the American Statistical Association.
Medical Subject Headings (MeSH)
Biostatistics; Computing Methodologies; Machine Learning; Mathematical Computing; Reproducibility of Results; Statistics
Research at a Glance
Yale Co-Authors
Frequent collaborators of Michael Kane's published research.
Publications Timeline
A big-picture view of Michael Kane's research output by year.
Research Interests
Research topics Michael Kane is interested in exploring.
Denise Esserman, PhD
Daniel Zelterman, PhD
David Ganz
Erich J Greene, PhD
Ondrej Blaha, PhD
Federico Costa, PhD
24Publications
2,267Citations
Machine Learning
Publications
2024
Assessing readiness to use electronic health record data for outcome ascertainment in clinical trials – A case study
Esserman D, Greene E, Latham N, Kane M, Lu C, Peduzzi P, Gill T, Ganz D. Assessing readiness to use electronic health record data for outcome ascertainment in clinical trials – A case study. Contemporary Clinical Trials 2024, 142: 107572. PMID: 38740298, DOI: 10.1016/j.cct.2024.107572.Peer-Reviewed Original ResearchConceptsElectronic health record dataElectronic health recordsOutcome ascertainmentDevelop Confidence in EldersElectronic health record platformsClinical sitesPrimary care practicesHealth record dataMulti-site trialMulti-site clinical trialCare practicesHealth recordsAssess readinessAcute clinical outcomesHealthcare systemRecord dataClinical trialsReduce injuriesData qualityData comprehensionChecklistStudy dataClinical trial sitesVariable data qualityAscertainmentA Bayesian platform trial design with hybrid control based on multisource exchangeability modelling
Wei W, Blaha O, Esserman D, Zelterman D, Kane M, Liu R, Lin J. A Bayesian platform trial design with hybrid control based on multisource exchangeability modelling. Statistics In Medicine 2024, 43: 2439-2451. PMID: 38594809, DOI: 10.1002/sim.10077.Peer-Reviewed Original ResearchValidation of a Rule-Based ICD-10-CM Algorithm to Detect Fall Injuries in Medicare Data
Ganz D, Esserman D, Latham N, Kane M, Min L, Gill T, Reuben D, Peduzzi P, Greene E. Validation of a Rule-Based ICD-10-CM Algorithm to Detect Fall Injuries in Medicare Data. The Journals Of Gerontology Series A 2024, 79: glae096. PMID: 38566617, PMCID: PMC11167485, DOI: 10.1093/gerona/glae096.Peer-Reviewed Original ResearchConceptsFee-for-serviceFall injuriesMedicare AdvantageMedicare dataTrial armsHealthcare systemDevelop Confidence in EldersArea under the receiver operating characteristic curveMedicare fee-for-serviceStratified resultsMedicareReduce injuriesMedical attentionObservational studyStrideReceiver operating characteristic curveCalendar monthMA dataInjuryData sourcesHealthcareArmReference standardTrialsWindow size
2023
A compressed large language model embedding dataset of ICD 10 CM descriptions
Kane M, King C, Esserman D, Latham N, Greene E, Ganz D. A compressed large language model embedding dataset of ICD 10 CM descriptions. BMC Bioinformatics 2023, 24: 482. PMID: 38105180, PMCID: PMC10726612, DOI: 10.1186/s12859-023-05597-2.Peer-Reviewed Original ResearchCitations
2022
Regression methods for the appearances of extremes in climate data
Yu C, Blaha O, Kane M, Wei W, Esserman D, Zelterman D. Regression methods for the appearances of extremes in climate data. Environmetrics 2022, 33 DOI: 10.1002/env.2764.Peer-Reviewed Original ResearchCitationsAltmetricConceptsBayesian local exchangeability design for phase II basket trials
Liu Y, Kane M, Esserman D, Blaha O, Zelterman D, Wei W. Bayesian local exchangeability design for phase II basket trials. Statistics In Medicine 2022, 41: 4367-4384. PMID: 35777367, PMCID: PMC10279458, DOI: 10.1002/sim.9514.Peer-Reviewed Original ResearchCitationsBayesian basket trial design with false-discovery rate control.
Zabor EC, Kane MJ, Roychoudhury S, Nie L, Hobbs BP. Bayesian basket trial design with false-discovery rate control. Clinical Trials (London, England) 2022, 19: 297-306. PMID: 35128970, DOI: 10.1177/17407745211073624.Peer-Reviewed Original Research
2021
Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach
Li X, Kane M, Zhang Y, Sun W, Song Y, Dong S, Lin Q, Zhu Q, Jiang F, Zhao H. Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach. Journal Of Medical Internet Research 2021, 23: e18403. PMID: 34647895, PMCID: PMC8554674, DOI: 10.2196/18403.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsRhythm formationPDMS-2Motor developmentCircadian rhythm analysisPeabody Developmental Motor Scales-Second EditionFisher testChildhood motor developmentEarly childhood motor developmentWearable device dataHealthy infantsRhythm analysisClinical studiesLinear regression analysisGross motorMonthsTime pointsAge 6Bonferroni correctionEarly childhoodRhythm developmentRegression analysisOne dayAssociationDaily rhythmsActiwatch dataUnified exact design with early stopping rules for single arm clinical trials with multiple endpoints
Wei W, Esserman D, Kane M, Zelterman D. Unified exact design with early stopping rules for single arm clinical trials with multiple endpoints. Statistical Methods In Medical Research 2021, 30: 1575-1588. PMID: 34159859, PMCID: PMC8959087, DOI: 10.1177/09622802211013062.Peer-Reviewed Original ResearchCitations
2020
Two‐stage randomized trial design for testing treatment, preference, and self‐selection effects for count outcomes
Shi Y, Cameron B, Gu X, Kane M, Peduzzi P, Esserman DA. Two‐stage randomized trial design for testing treatment, preference, and self‐selection effects for count outcomes. Statistics In Medicine 2020, 39: 3653-3683. PMID: 32875582, DOI: 10.1002/sim.8686.Peer-Reviewed Original ResearchCitationsMeSH Keywords and ConceptsConceptsTrial designPatient preferencesPatient-centered treatment strategiesTreatment effectsTraditional clinical trial designClinical trial designEnd of lifeUse of antimicrobialsTreatment strategiesHealthcare providersPatient psychologyTesting treatmentsTwo-stage designOutcomesParticular treatmentTreatmentBinary outcomesCount outcomesTrials
Links & Media
News
- April 04, 2024
Molecular Subtypes of Advanced Kidney Cancer Matter for Treatment Response
- October 05, 2018
Cancer death disparities linked to poverty, lifestyle factors nationwide
- September 10, 2014
More health symptoms reported near ‘fracking’ natural gas extraction
- August 13, 2011Source: Barron's
Hitting the Switch on New Circuit Breakers
Get In Touch
Contacts
Locations
300 George Street
Academic Office
Ste Suite 555
New Haven, CT 06511