Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Artificial neural network models to predict nodal status in clinically node-negative breast cancer

Dihge, Looket LU ; Ohlsson, Mattias LU orcid ; Edén, Patrik LU ; Bendahl, Pär Ola LU and Rydén, Lisa LU orcid (2019) In BMC Cancer 19(1).
Abstract

Background: Sentinel lymph node biopsy (SLNB) is standard staging procedure for nodal status in breast cancer, but lacks therapeutic benefit for patients with benign sentinel nodes. For patients with positive sentinel nodes, individualized surgical strategies are applied depending on the extent of nodal involvement. Preoperative prediction of nodal status is thus important for individualizing axillary surgery avoiding unnecessary surgery. We aimed to predict nodal status in clinically node-negative breast cancer and identify candidates for SLNB omission by including patient-related and pathological characteristics into artificial neural network (ANN) models. Methods: Patients with primary breast cancer were consecutively included... (More)

Background: Sentinel lymph node biopsy (SLNB) is standard staging procedure for nodal status in breast cancer, but lacks therapeutic benefit for patients with benign sentinel nodes. For patients with positive sentinel nodes, individualized surgical strategies are applied depending on the extent of nodal involvement. Preoperative prediction of nodal status is thus important for individualizing axillary surgery avoiding unnecessary surgery. We aimed to predict nodal status in clinically node-negative breast cancer and identify candidates for SLNB omission by including patient-related and pathological characteristics into artificial neural network (ANN) models. Methods: Patients with primary breast cancer were consecutively included between January 1, 2009 and December 31, 2012 in a prospectively maintained pathology database. Clinical- and radiological data were extracted from patient's files and only clinically node-negative patients constituted the final study cohort. ANN-based models for nodal prediction were constructed including 15 risk variables for nodal status. Area under the receiver operating characteristic curve (AUC) and Hosmer-Lemeshow goodness-of-fit test (HL) were used to assess performance and calibration of three predictive ANN-based models for no lymph node metastasis (N0), metastases in 1-3 lymph nodes (N1) and metastases in ≥ 4 lymph nodes (N2). Linear regression models for nodal prediction were calculated for comparison. Results: Eight hundred patients (N0, n = 514; N1, n = 232; N2, n = 54) were included. Internally validated AUCs for N0 versus N+ was 0.740 (95% CI = 0.723-0.758); median HL was 9.869 (P = 0.274), for N1 versus N0, 0.705 (95% CI = 0.686-0.724; median HL: 7.421; P = 0.492) and for N2 versus N0 and N1, 0.747 (95% CI = 0.728-0.765; median HL: 9.220; P = 0.324). Tumor size and vascular invasion were top-ranked predictors of all three end-points, followed by estrogen receptor status and lobular cancer for prediction of N2. For each end-point, ANN models showed better discriminatory performance than multivariable logistic regression models. Accepting a false negative rate (FNR) of 10% for predicting N0 by the ANN model, SLNB could have been abstained in 27.25% of patients with clinically node-negative axilla. Conclusions: In this retrospective study, ANN showed promising result as decision-supporting tools for estimating nodal disease. If prospectively validated, patients least likely to have nodal metastasis could be spared SLNB using predictive models. Trial registration: Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018. Retrospectively registered.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial neural networks, Breast cancer, Nodal status, Prediction models, Sentinel lymph node biopsy
in
BMC Cancer
volume
19
issue
1
article number
610
publisher
BioMed Central (BMC)
external identifiers
  • scopus:85068524021
  • pmid:31226956
ISSN
1471-2407
DOI
10.1186/s12885-019-5827-6
language
English
LU publication?
yes
id
4b3622ff-e993-4913-9c58-9f7d0952028f
date added to LUP
2019-07-17 08:55:45
date last changed
2024-05-28 21:02:54
@article{4b3622ff-e993-4913-9c58-9f7d0952028f,
  abstract     = {{<p>Background: Sentinel lymph node biopsy (SLNB) is standard staging procedure for nodal status in breast cancer, but lacks therapeutic benefit for patients with benign sentinel nodes. For patients with positive sentinel nodes, individualized surgical strategies are applied depending on the extent of nodal involvement. Preoperative prediction of nodal status is thus important for individualizing axillary surgery avoiding unnecessary surgery. We aimed to predict nodal status in clinically node-negative breast cancer and identify candidates for SLNB omission by including patient-related and pathological characteristics into artificial neural network (ANN) models. Methods: Patients with primary breast cancer were consecutively included between January 1, 2009 and December 31, 2012 in a prospectively maintained pathology database. Clinical- and radiological data were extracted from patient's files and only clinically node-negative patients constituted the final study cohort. ANN-based models for nodal prediction were constructed including 15 risk variables for nodal status. Area under the receiver operating characteristic curve (AUC) and Hosmer-Lemeshow goodness-of-fit test (HL) were used to assess performance and calibration of three predictive ANN-based models for no lymph node metastasis (N0), metastases in 1-3 lymph nodes (N1) and metastases in ≥ 4 lymph nodes (N2). Linear regression models for nodal prediction were calculated for comparison. Results: Eight hundred patients (N0, n = 514; N1, n = 232; N2, n = 54) were included. Internally validated AUCs for N0 versus N+ was 0.740 (95% CI = 0.723-0.758); median HL was 9.869 (P = 0.274), for N1 versus N0, 0.705 (95% CI = 0.686-0.724; median HL: 7.421; P = 0.492) and for N2 versus N0 and N1, 0.747 (95% CI = 0.728-0.765; median HL: 9.220; P = 0.324). Tumor size and vascular invasion were top-ranked predictors of all three end-points, followed by estrogen receptor status and lobular cancer for prediction of N2. For each end-point, ANN models showed better discriminatory performance than multivariable logistic regression models. Accepting a false negative rate (FNR) of 10% for predicting N0 by the ANN model, SLNB could have been abstained in 27.25% of patients with clinically node-negative axilla. Conclusions: In this retrospective study, ANN showed promising result as decision-supporting tools for estimating nodal disease. If prospectively validated, patients least likely to have nodal metastasis could be spared SLNB using predictive models. Trial registration: Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018. Retrospectively registered.</p>}},
  author       = {{Dihge, Looket and Ohlsson, Mattias and Edén, Patrik and Bendahl, Pär Ola and Rydén, Lisa}},
  issn         = {{1471-2407}},
  keywords     = {{Artificial neural networks; Breast cancer; Nodal status; Prediction models; Sentinel lymph node biopsy}},
  language     = {{eng}},
  month        = {{06}},
  number       = {{1}},
  publisher    = {{BioMed Central (BMC)}},
  series       = {{BMC Cancer}},
  title        = {{Artificial neural network models to predict nodal status in clinically node-negative breast cancer}},
  url          = {{http://dx.doi.org/10.1186/s12885-019-5827-6}},
  doi          = {{10.1186/s12885-019-5827-6}},
  volume       = {{19}},
  year         = {{2019}},
}