BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251105T025413EST-0869dzDvkU@132.216.98.100
DTSTAMP:20251105T075413Z
DESCRIPTION:Steffen Ventz\, PhD\n\nAssistant Professor of Biostatistics | D
 ivision of Biostatistics\n\nSchool of Public Health | University of Minnes
 ota\n\nWhere: Hybrid Event | 2001 9IÖÆ×÷³§Ãâ·Ñ College\, Room 1140\; Zoom\n\nAbs
 tract\n\nBiomedical technologies enable the use of omics information for p
 rognostic purposes\, to quantify the risk of diseases or to predict respon
 se to treatments. Risk stratification in oncology often utilizes a set of 
 biomarkers to predict cancer progression or death within a time period. Th
 e number of covariates can often exceed the sample size\, which makes the 
 identification of relevant genomic features for risk prediction and the de
 velopment of accurate models challenging. In this talk I introduce a stati
 stical procedure that integrates datasets from multiple biomedical studies
  to predict patients’ survival\, based on individual clinical and genomic 
 profiles. The procedure accounts for potential differences in the relation
  between predictors and outcomes across studies\, due to distinct patient 
 populations\, treatments\, and technologies to measure outcomes and biomar
 kers. These differences are modeled explicitly with study-specific paramet
 ers. We use hierarchical regularization to shrink study-specific parameter
 s towards each other and to borrow information across studies. The estimat
 ion of the study-specific parameters utilizes a similarity matrix\, which 
 summarizes differences and similarities of the relations between covariate
 s and outcomes across studies. We illustrate the method in simulation stud
 ies and using a collection of gene expression datasets in ovarian cancer. 
 We show that the proposed model increases the accuracy of survival predict
 ions compared to alternative meta-analytic methods.\n\nSpeaker Bio\n\nWebs
 ite: https://steffen-ventz.github.io/\n\n\n	\n	 \n
DTSTART:20230315T193000Z
DTEND:20230315T203000Z
SUMMARY:Integration of survival data from multiple studies
URL:/epi-biostat-occh/channels/event/integration-survi
 val-data-multiple-studies-346597
END:VEVENT
END:VCALENDAR