Endocrine Therapy of Breast Cancer

Abstract

A recent controversy in the treatment of estrogen receptor positive (ER+) breast cancers is whether an aromatase inhibitor, e.g., letrozole (LET) or TAM should be given as first line endocrine therapy. Unfortunately, response rates are lower, and response durations are shorter, on crossover than when these agents are given as first line therapies, e.g., -40% of tumors show cross resistance to TAM or an aromatase inhibitor on crossover. Only 50% of ER+ tumors respond to endocrine therapy. Currently, we fail to predict endocrine responsiveness in about 66% of ER+/PgR- (progesterone receptor), 55% of ER-/PgR+, and 25% of ER+/PgR+ tumors. In this new Clinical Translational Research Award, we hypothesize that our analytical methods can extract expression profiles of breast tumors that define their responsiveness (sensitive vs. resistant) to endocrine therapy. These profiles, when combined with known predictive/prognostic factors, will support neural network and biostatistical classifiers or committee machines that predict each tumor's endocrine responsiveness. Our objectives are to array breast cancer cases, build classifiers of endocrine responsiveness (using microarray data), and validate these classifiers in independent data sets using mostly immunohistochemistry data (IHC). IHC will be done on cases with definitive outcomes data. In the long term, we will design custom arrays for use in clinical practice. Genes will be further studied using cellular and molecular methods, and their role as therapeutic targets explored.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2006
Accession Number
ADA463407

Entities

People

  • Robert Clarke

Organizations

  • Georgetown University

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Breast Cancer
  • Computational Science
  • Computer Science
  • Data Mining
  • Data Science
  • Data Sets
  • Databases
  • Dimensionality Reduction
  • Electrical Engineering
  • Information Science
  • Machine Learning
  • Medical Personnel
  • Neoplasms
  • Network Science
  • Neural Networks
  • Supervised Machine Learning

Fields of Study

  • Medicine

Readers

  • Breast cancer cell signaling and growth regulation.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks