Breast Cancer Research and Treatment

, Volume 129, Issue 2, pp 451–458

Artificial neural network analysis of circulating tumor cells in metastatic breast cancer patients

Authors

    • Department of HematopathologyThe University of Texas MD Anderson Cancer Center
    • Department of Endocrinology and Molecular and Clinical OncologyUniversity of Naples Federico II
  • Mario Giuliano
    • Breast Center, Baylor College of Medicine
    • Department of Endocrinology and Molecular and Clinical OncologyUniversity of Naples Federico II
  • Michelino De Laurentiis
    • Department of Breast OncologyNational Cancer Institute “Fondazione Pascale”
  • Antonio Eleuteri
    • Department of Medical Physics and Clinical EngineeringRoyal Liverpool University Hospital
  • Francesco Iorio
    • Department of Mathematics and InformaticsUniversity of Salerno
  • Roberto Tagliaferri
    • Department of Mathematics and InformaticsUniversity of Salerno
  • Gabriel N. Hortobagyi
    • Department of Breast Medical OncologyThe University of Texas MD Anderson Cancer Center
  • Lajos Pusztai
    • Department of Breast Medical OncologyThe University of Texas MD Anderson Cancer Center
  • Sabino De Placido
    • Department of Endocrinology and Molecular and Clinical OncologyUniversity of Naples Federico II
  • Kenneth Hess
    • Department of BiostatisticsThe University of Texas MD Anderson Cancer Center
  • Massimo Cristofanilli
    • Department of Medical OncologyFox Chase Cancer Center
  • James M. Reuben
    • Department of HematopathologyThe University of Texas MD Anderson Cancer Center
Clinical trial

DOI: 10.1007/s10549-011-1645-5

Cite this article as:
Giordano, A., Giuliano, M., De Laurentiis, M. et al. Breast Cancer Res Treat (2011) 129: 451. doi:10.1007/s10549-011-1645-5

Abstract

A cut-off of 5 circulating tumor cells (CTCs) per 7.5 ml of blood in metastatic breast cancer (MBC) patients is highly predictive of outcome. We analyzed the relationship between CTCs as a continuous variable and overall survival in immunohistochemically defined primary tumor molecular subtypes using an artificial neural network (ANN) prognostic tool to determine the shape of the relationship between risk of death and CTC count and to predict individual survival. We analyzed a training dataset of 311 of 517 (60%) consecutive MBC patients who had been treated at MD Anderson Cancer Center from September 2004 to 2009 and who had undergone pre-therapy CTC counts (CellSearch®). Age; estrogen, progesterone receptor, and HER2 status; visceral metastasis; metastatic disease sites; therapy type and line; and CTCs as a continuous value were evaluated using ANN. A model with parameter estimates obtained from the training data was tested in a validation set of the remaining 206 (40%) patients. The model estimates were accurate, with good discrimination and calibration. Risk of death, as estimated by ANN, linearly increased with increasing CTC count in all molecular tumor subtypes but was higher in ER+ and triple-negative MBC than in HER2+. The probabilities of survival for the four subtypes with 0 CTC were as follows: ER+/HER2− 0.947, ER+/HER2+ 0.959, ER−/HER2+ 0.902, and ER-/HER2− 0.875. For patients with 200 CTCs, they were ER+/HER2− 0.439, ER+/HER2+ 0.621, ER−/HER2+ 0.307, ER−/HER2− 0.130. In this large study, ANN revealed a linear increase of risk of death in MBC patients with increasing CTC counts in all tumor subtypes. CTCs’ prognostic effect was less evident in HER2+ MBC patients treated with targeted therapy. This study may support the concept that the number of CTCs, along with the biologic characteristics, needs to be carefully taken into account in future analysis.

Keywords

Circulating tumor cellsMetastatic breast cancerArtificial neural networkHER2Prognosis

Copyright information

© Springer Science+Business Media, LLC. 2011