EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning for predicting mortality in women diagnosed with breast cancer in the State of Mato Grosso, Brazil using linked population-based cancer registry and mortality data

Sancho Pedro Xavier iD, Audêncio Victor iD, Ana Raquel Ernesto Manuel Gotine iD, Fernando Henrique de Albuquerque Maia iD, Manuel Mahoche iD, Marco Aurélio Bertúlio das Neves, Alexandre Dias Porto Chiavegatto Filho, Noemi Dreyer Galvão, Ageo Mario Cândido da Silva

PLOS One · 2026

DOI: 10.1371/journal.pone.0356621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Sancho Pedro Xavier und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Public Health, University of São Paulo (USP), São Paulo, São Paulo, Brazil. Hauptthemen laut MEDLINE: Breast Neoplasms, Machine Learning. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: São Paulo Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Breast cancer is the most frequently diagnosed malignancy and a leading cause of cancer-related mortality among women worldwide. In Brazil, pronounced regional inequalities persist in access to timely diagnosis and treatment, particularly in large and socioeconomically heterogeneous states such as Mato Grosso. This study aimed to develop and validate machine learning (ML) models to predict 1-, 3-, 5-, and 10-year all-cause and breast cancer-specific mortality among women diagnosed with breast cancer in Mato Grosso, Brazil.

Methods

A retrospective, population-based cohort study was conducted, including 7,815 women diagnosed with breast cancer between 2001 and 2018. The dataset was randomly split into training (75%) and testing (25%) sets. Logistic regression, Random Forest, XGBoost, CatBoost, and LightGBM models were developed to predict all-cause and breast cancer-specific mortality at 1, 3, 5, and 10 years. Model performance was primarily evaluated using the area under the receiver operating characteristic curve (AUROC). Calibration was assessed using calibration plots and the Brier score (BS), with 95% confidence intervals estimated via bootstrap resampling. Model interpretability was evaluated using Shapley Additive Explanations (SHAP).

Results

Gradient boosting models consistently demonstrated superior performance across prediction horizons. For all-cause mortality, CatBoost achieved the highest discrimination at 1 year (AUROC 83.18%, 95% CI 80.01-86.33), while LightGBM showed higher discrimination at 3 and 5 years (AUROC 81.01%, 95% CI 78.63-83.42; and AUROC 78.39%, 95% CI 75.99-80.64, respectively). For breast cancer-specific mortality, logistic regression achieved the highest AUROC at 1 year (84.44%, 95% CI 81.04-87.35), whereas LightGBM achieved the highest at 3 years (AUROC 79.82%, 95% CI 77.15-82.34), XGBoost at 5 years (AUROC 80.79%, 95% CI 78.54-83.23). SHAP analyses consistently identified age at diagnosis, metastatic stage, histological diagnosis, invasive ductal carcinoma (IDC), and marital status as the most influential predictors.

Conclusions

ML models demonstrated good and stable discriminative performance in predicting breast cancer mortality using routine population-based data. These models may support the early identification of high-risk patients and help guide risk stratification and follow-up planning in resource-constrained health systems. However, the models have not yet been externally validated, and their generalizability to populations beyond Mato Grosso remains uncertain. External validation in independent populations is therefore warranted before broader implementation in other regions of Brazil.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsMachine LearningHumansFemaleBrazilRetrospective StudiesRegistriesMiddle AgedBoosting Machine Learning AlgorithmsPredictive Learning ModelsRandom ForestAgedAdultROC CurveLogistic ModelsClassification AlgorithmsPrediction Algorithms

Autor:innen und Institutionen

  • School of Public Health, University of São Paulo (USP), São Paulo, São Paulo, Brazil.
  • Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, United Kingdom.
  • Institute of Collective Health, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil.
  • State Secretary of Health of Mato Grosso (SES-MT), Cuiabá, Mato Grosso, Brazil.

ORCID-Profile: Sancho Pedro Xavier, Audêncio Victor, Ana Raquel Ernesto Manuel Gotine, Fernando Henrique de Albuquerque Maia, Manuel Mahoche

Förderung

  • São Paulo Research Foundation

Zitieren

APA

Xavier, S. P., Victor, A., Gotine, A. R. E. M., de Albuquerque Maia, F. H., Mahoche, M., Neves, M. A. B. D., Filho, A. D. P. C., Galvão, N. D., & Cândido da Silva, A. M. (2026). Machine learning for predicting mortality in women diagnosed with breast cancer in the State of Mato Grosso, Brazil using linked population-based cancer registry and mortality data. PLOS One. https://doi.org/10.1371/journal.pone.0356621

Vancouver

Xavier SP, Victor A, Gotine AREM, de Albuquerque Maia FH, Mahoche M, Neves MABD, et al. Machine learning for predicting mortality in women diagnosed with breast cancer in the State of Mato Grosso, Brazil using linked population-based cancer registry and mortality data. PLOS One. 2026. doi:10.1371/journal.pone.0356621

BibTeX
@article{Xavier2026,
  author = {Xavier, Sancho Pedro and Victor, Audêncio and Gotine, Ana Raquel Ernesto Manuel and de Albuquerque Maia, Fernando Henrique and Mahoche, Manuel and Neves, Marco Aurélio Bertúlio das and Filho, Alexandre Dias Porto Chiavegatto and Galvão, Noemi Dreyer and Cândido da Silva, Ageo Mario},
  title = {Machine learning for predicting mortality in women diagnosed with breast cancer in the State of Mato Grosso, Brazil using linked population-based cancer registry and mortality data},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0356621}
}
Kostenlos starten →