A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients

Michelino De Laurentiis, Sabino De Placido, Angelo R. Bianco, Gary M. Clark, Peter M. Ravdin

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Tumor-node-matastasis (TNM) staging is the standard system for the estimation of prognosis of breast cancer patients. However, this system does not exploit information yielded by markers of the biological aggressiveness of breast cancer and is clearly unsatisfactory for optimal-treatment decision-making and for patient counseling. We have developed a prognostic model, based on a few routinely evaluated prognostic variables, that produces quantitative estimates for risk of relapse of individual breast cancer patients. We used data concerning 2441 of 2990 consecutive breast cancer patients to develop an artificial neural network (ANN) for the prediction of the probability of relapse over 5 years. The prognostic variables used were: patient age, tumor size, number of axillary metastases, estrogen and progesterone receptor levels, S-phase fraction, and tumor ploidy. Performances of the model were evaluated in terms of discrimination ability and quantitative precision. Predictions were validated on an independent series of 310 patients from an institution in another country. The ANN discriminated patients according to their risk of relapse better than the TNM classification (P = 0.0015). The quantitative precision of the model's estimates was accurate and was confirmed on the series from the second institution. The 5-year relapse risk yielded by the model varied greatly within the same TNM class, particularly for patients with four or more nodal metastases. The model discriminates prognosis better than the TNM classification and is able to identify patients with strikingly different risks of relapse within each TNM class.

Original languageEnglish
Pages (from-to)4133-4139
Number of pages7
JournalClinical Cancer Research
Volume5
Issue number12
Publication statusPublished - Dec 1999

Fingerprint

Breast Neoplasms
Recurrence
Neoplasms
Neoplasm Metastasis
Aptitude
Ploidies
Progesterone Receptors
S Phase
Estrogen Receptors
Counseling
Decision Making
Biomarkers

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients. / De Laurentiis, Michelino; De Placido, Sabino; Bianco, Angelo R.; Clark, Gary M.; Ravdin, Peter M.

In: Clinical Cancer Research, Vol. 5, No. 12, 12.1999, p. 4133-4139.

Research output: Contribution to journalArticle

De Laurentiis, Michelino ; De Placido, Sabino ; Bianco, Angelo R. ; Clark, Gary M. ; Ravdin, Peter M. / A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients. In: Clinical Cancer Research. 1999 ; Vol. 5, No. 12. pp. 4133-4139.
@article{c12e5d213fe44e1aa01b94a2810a65f0,
title = "A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients",
abstract = "Tumor-node-matastasis (TNM) staging is the standard system for the estimation of prognosis of breast cancer patients. However, this system does not exploit information yielded by markers of the biological aggressiveness of breast cancer and is clearly unsatisfactory for optimal-treatment decision-making and for patient counseling. We have developed a prognostic model, based on a few routinely evaluated prognostic variables, that produces quantitative estimates for risk of relapse of individual breast cancer patients. We used data concerning 2441 of 2990 consecutive breast cancer patients to develop an artificial neural network (ANN) for the prediction of the probability of relapse over 5 years. The prognostic variables used were: patient age, tumor size, number of axillary metastases, estrogen and progesterone receptor levels, S-phase fraction, and tumor ploidy. Performances of the model were evaluated in terms of discrimination ability and quantitative precision. Predictions were validated on an independent series of 310 patients from an institution in another country. The ANN discriminated patients according to their risk of relapse better than the TNM classification (P = 0.0015). The quantitative precision of the model's estimates was accurate and was confirmed on the series from the second institution. The 5-year relapse risk yielded by the model varied greatly within the same TNM class, particularly for patients with four or more nodal metastases. The model discriminates prognosis better than the TNM classification and is able to identify patients with strikingly different risks of relapse within each TNM class.",
author = "{De Laurentiis}, Michelino and {De Placido}, Sabino and Bianco, {Angelo R.} and Clark, {Gary M.} and Ravdin, {Peter M.}",
year = "1999",
month = "12",
language = "English",
volume = "5",
pages = "4133--4139",
journal = "Clinical Cancer Research",
issn = "1078-0432",
publisher = "American Association for Cancer Research Inc.",
number = "12",

}

TY - JOUR

T1 - A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients

AU - De Laurentiis, Michelino

AU - De Placido, Sabino

AU - Bianco, Angelo R.

AU - Clark, Gary M.

AU - Ravdin, Peter M.

PY - 1999/12

Y1 - 1999/12

N2 - Tumor-node-matastasis (TNM) staging is the standard system for the estimation of prognosis of breast cancer patients. However, this system does not exploit information yielded by markers of the biological aggressiveness of breast cancer and is clearly unsatisfactory for optimal-treatment decision-making and for patient counseling. We have developed a prognostic model, based on a few routinely evaluated prognostic variables, that produces quantitative estimates for risk of relapse of individual breast cancer patients. We used data concerning 2441 of 2990 consecutive breast cancer patients to develop an artificial neural network (ANN) for the prediction of the probability of relapse over 5 years. The prognostic variables used were: patient age, tumor size, number of axillary metastases, estrogen and progesterone receptor levels, S-phase fraction, and tumor ploidy. Performances of the model were evaluated in terms of discrimination ability and quantitative precision. Predictions were validated on an independent series of 310 patients from an institution in another country. The ANN discriminated patients according to their risk of relapse better than the TNM classification (P = 0.0015). The quantitative precision of the model's estimates was accurate and was confirmed on the series from the second institution. The 5-year relapse risk yielded by the model varied greatly within the same TNM class, particularly for patients with four or more nodal metastases. The model discriminates prognosis better than the TNM classification and is able to identify patients with strikingly different risks of relapse within each TNM class.

AB - Tumor-node-matastasis (TNM) staging is the standard system for the estimation of prognosis of breast cancer patients. However, this system does not exploit information yielded by markers of the biological aggressiveness of breast cancer and is clearly unsatisfactory for optimal-treatment decision-making and for patient counseling. We have developed a prognostic model, based on a few routinely evaluated prognostic variables, that produces quantitative estimates for risk of relapse of individual breast cancer patients. We used data concerning 2441 of 2990 consecutive breast cancer patients to develop an artificial neural network (ANN) for the prediction of the probability of relapse over 5 years. The prognostic variables used were: patient age, tumor size, number of axillary metastases, estrogen and progesterone receptor levels, S-phase fraction, and tumor ploidy. Performances of the model were evaluated in terms of discrimination ability and quantitative precision. Predictions were validated on an independent series of 310 patients from an institution in another country. The ANN discriminated patients according to their risk of relapse better than the TNM classification (P = 0.0015). The quantitative precision of the model's estimates was accurate and was confirmed on the series from the second institution. The 5-year relapse risk yielded by the model varied greatly within the same TNM class, particularly for patients with four or more nodal metastases. The model discriminates prognosis better than the TNM classification and is able to identify patients with strikingly different risks of relapse within each TNM class.

UR - http://www.scopus.com/inward/record.url?scp=0033375308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033375308&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 4133

EP - 4139

JO - Clinical Cancer Research

JF - Clinical Cancer Research

SN - 1078-0432

IS - 12

ER -