You are here:
Vanderbilt Biostatistics Wiki
>
Main Web
>
Seminars
>
WednesdaySeminarSeries
>
RuiDuan20210908
(18 Aug 2021,
SimonVandekar
)
(raw view)
E
dit
A
ttach
%HEAD{ NAME="Rui Duan, !PhD" AFFILIATION="Harvard University" TITLE="Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach" IMAGELINK="https://cdn1.sph.harvard.edu/wp-content/uploads/sites/2577/2020/07/E7263E5B-C072-479E-BD28-647DFBD9B23F.jpeg" }% Precision medicine research has shown great promise to improve individual health and our understanding about how a person's genetics, environment, and lifestyle can help determine the best approach to prevent or treat disease. However, one serious challenge we are facing is the limited representation of minorities and disadvantaged populations in precision medicine research. Many studies have shown populations with low socioeconomic status as well as racial and ethnic minority groups tend to be underrepresented in biomedical research or biorepositories. To advance prediction medicine, it is crucial to improve the performance of statistical and machine learning models in underrepresented populations so as not to exacerbate health disparities. In this paper, we address the lack of representation and disparities in model performance through two strategies: (1) leverage the shared knowledge from diverse populations, and (2) integrate larger bodies of data from multiple healthcare organizations. More specifically, we develop transfer learning strategies to transfer the shared knowledge learned from diverse populations to an underrepresented population, so that comparable model performance can be reached with much less data. On the other hand, we propose federated learning methods to increase the sample sizes of underrepresented populations and the diversity of the data through multi-center collaborative research via a safe and efficient way. Our methods have solid theoretical foundations, and we demonstrate the feasibility and validity of our methods through numerical experiments and a real application to a multi-center study for constructing polygenic risk prediction models for Type II Diabetes. %TAIL{DATE="8 September 2021"}% <!-- * Set HEAD = <div class="w3-card-2" id="task" style="max-width:750px; margin-left: 0px;"> <header class="w3-container w3-blue" style="padding:40px"><h1>Biostatistics Weekly Seminar</h1><br><h2 style="color:white;">%TITLE%<br><br>%NAME%<br>%AFFILIATION%</h2></header><div class="w3-container" style="padding:40px"><IMG SRC=%IMAGELINK% align="left" id="mug"/> * Set TAIL = <br><h3>Zoom (Link to Follow)<br>%DATE%<br>1:30pm</h3></div></div><br>[[%TOPIC%Itinerary][Speaker Itinerary]] --> <style> .w3-card-2,.w3-example{box-shadow:0 2px 4px 0 rgba(0,0,0,0.16),0 2px 10px 0 rgba(0,0,0,0.12)!important} .w3-blue,.w3-hover-blue:hover{color:#fff!important;background-color:#2196F3!important} .w3-container{padding:0.01em 16px} .foswikiTopic {font-family: 'Open Sans', sans-serif;} /* Removes location hierarchy (usually written in grey text) */ .patternHomePath {display:none;} /* Removes bar with edit and attach buttons and location hierarchy */ .patternTop{display:none;} h1, h2, h3, h4, h5, h6{font-family: 'Montserrat','Open Sans', sans-serif;font-weight:700;} h1, h2, h3, h4, h5, h6{color:#bf1735;} h1:first-of-type{color:#2a3e6e;margin-bottom:25px;margin-top:5px;} .foswikiImage{margin-left:-9px;} img#mug{padding-right: 40px; padding-bottom:25px; height:250px;} </style>
E
dit
|
A
ttach
|
P
rint version
|
H
istory
: r2
<
r1
|
B
acklinks
|
V
iew topic
|
Edit
w
iki text
|
M
ore topic actions
Topic revision: r2 - 18 Aug 2021,
SimonVandekar
Main
Department Home Page
Biostatistics Graduate Program
Vanderbilt University Medical Center
Main Web
Main Web Home
Search
Recent Changes
Changes
Topic list
Biostatistics Webs
Archive
Main
Sandbox
System
Register
|
Log In
Copyright © 2013-2022 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki?
Send feedback