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
4 affiliations
- 1School of Public Health, University of São Paulo (USP), São Paulo, São Paulo, Brazil
- 2Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, United Kingdom
- 3Institute of Collective Health, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil
- 4State Secretary of Health of Mato Grosso (SES-MT), Cuiabá, Mato Grosso, Brazil
Abstract
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.
Related
- Hyperuricaemia risk and its association with kidney failure and mortality in newly diagnosed type 2 diabetes with preserved renal function: a multicentre machine learning study.
- Incident transient ischemic attack and subsequent cardiovascular events and mortality in patients with newly diagnosed type 2 diabetes: a population-based cohort study
- Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
- Machine Learning for Predicting Mortality Following Transcatheter Aortic Valve Replacement: A Scoping Review of Current Literature
- Stage Migration, Treatment Patterns, and Machine Learning-Based Prediction of 12-Month Mortality in Lung Adenocarcinoma Across the COVID-19 Era: A SEER Population-Based Study
BibTeX
@article{xavier2026machine,
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}},
author = {Sancho Pedro Xavier and Audêncio Victor and Ana Raquel Ernesto Manuel Gotine and Fernando Henrique de Albuquerque Maia and Manuel Mahoche and Marco Aurélio Bertúlio das Neves and Alexandre Dias Porto Chiavegatto Filho and Noemi Dreyer Galvão and Ageo Mario Cândido da Silva},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0356621},
url = {https://doi.org/10.1371/journal.pone.0356621},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - 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
AU - Sancho Pedro Xavier
AU - Audêncio Victor
AU - Ana Raquel Ernesto Manuel Gotine
AU - Fernando Henrique de Albuquerque Maia
AU - Manuel Mahoche
AU - Marco Aurélio Bertúlio das Neves
AU - Alexandre Dias Porto Chiavegatto Filho
AU - Noemi Dreyer Galvão
AU - Ageo Mario Cândido da Silva
PY - 2026
DA - 2026/09/18
JO - PLOS One
DO - 10.1371/journal.pone.0356621
UR - https://doi.org/10.1371/journal.pone.0356621
AB - 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.
SN - 1932-6203
ER -