Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 397 - Personalized Medicine with Large-Scale Data: Beyond Machine Learning
Type: Invited
Date/Time: Thursday, August 12, 2021 : 2:00 PM to 3:50 PM
Sponsor: ENAR
Abstract #316622
Title: Personalized Medicine with Large-Scale Data: Beyond Machine Learning
Author(s): Ross Laverne Prentice*
Companies: Fred Hutchinson Cancer Research Center
Keywords: hazard rate models; failure time data; health benefits and risks; menopausal hormones; randomized clinical trials; regression
Abstract:

Ross Prentice Fred Hutchinson Cancer Research Center and University of Washington Seattle WA

TIMING ISSUES AND THE RELATIONSHIP OF MENOPAUSAL HORMONE USE TO VARIOUS HEALTH RISKS AND BENEFITS Randomized controlled trials have a central role in producing reliable information on the health benefits and risks of medical and public health interventions. While large observational databases, possibly with high-dimensional measures on individual study subjects, may contribute to overall findings in the context of such trials, they are unlikely to yield the crucial and nuanced findings that often emerge from randomized group comparisons in clinical trials. Randomized, placebo-controlled trials of estrogens and of estrogens plus progestins in relation to the primary coronary heart disease and breast cancer primary outcomes, as a component of the Women's Health Initiative studies among postmenopausal US women, will illustrate the discovery of important hormone therapy influences on health which were not evident from a related extensive observational study literature.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program