H
Harry B. Burke
Researcher at Uniformed Services University of the Health Sciences
Publications - 62
Citations - 2575
Harry B. Burke is an academic researcher from Uniformed Services University of the Health Sciences. The author has contributed to research in topics: Medicine & MEDLINE. The author has an hindex of 23, co-authored 56 publications receiving 2351 citations. Previous affiliations of Harry B. Burke include New York Medical College & George Washington University.
Papers
More filters
Journal ArticleDOI
Human prostate cancer risk factors.
David G. Bostwick,Harry B. Burke,Daniel Djakiew,Susan Y. Euling,Shuk-Mei Ho,Joseph R. Landolph,Howard Morrison,Babasaheb Sonawane,Tiffany Shifflett,David J. Waters,David J. Waters,Barry G. Timms +11 more
TL;DR: The authors conclude that most of the data regarding risk relies, of necessity, on epidemiologic studies, but animal and cell culture models offer promise in confirming some important findings.
Journal ArticleDOI
Artificial neural networks improve the accuracy of cancer survival prediction
Harry B. Burke,Philip H. Goodman,David B. Rosen,Donald E. Henson,John N. Weinstein,Frank E. Harrell,Jeffrey R. Marks,David P. Winchester,David G. Bostwick +8 more
TL;DR: This study compares the prediction accuracy of the TNM staging system with that of artificial neural network statistical models.
Journal ArticleDOI
Artificial neural networks applied to survival prediction in breast cancer.
TL;DR: An artificial neural network is very accurate in the 5-, 10- and 15-year breast-cancer-specific survival prediction and the good predictive performance of a network trained without information on nodal status demonstrate that neural networks can be important tools for cancer survival prediction.
Journal ArticleDOI
Criteria for prognostic factors and for an enhanced prognostic system
Harry B. Burke,Donald E. Henson +1 more
TL;DR: The criteria for selecting a prognostic system that includes TNM and new prognostic factors is suggested and is easy for physicians to use, provides predictions for all types of cancer, and provides the most accurate relapse and survival predictions at diagnosis.