What question did this study set out to answer?

The research aims to evaluate the effectiveness of machine learning methods in classifying breast cancer risk among Puerto Rican women.

April 5, 2026

Abstract 4226: Machine learning based classification of breast cancer using lifestyle and clinical risk factors in Puerto Rican women

Key Result

A CatBoost machine learning classifier outperformed other models in predicting breast cancer status in Puerto Rican women, achieving a ROC-AUC of 0.8009 and balanced accuracy of 0.7342.

Key Points

The research aims to evaluate the effectiveness of machine learning methods in classifying breast cancer risk among Puerto Rican women.
Utilized a dataset of lifestyle, demographic, and clinical risk factors from 1,393 Puerto Rican women.
Preprocessed data to ensure quality, including cleaning, normalization, and imputation.
Employed various machine learning models such as CatBoost, XGBoost, and Logistic Regression.
Implemented stratified 10-fold cross-validation for model evaluation.
Assessed model interpretability using SHAP and permutation-based feature importance.
The CatBoost classifier achieved a ROC-AUC of 0.8009 and PR-AUC of 0.8285.
Identified key predictors of breast cancer risk including menopausal status and family history.
Demonstrated that gradient boosting methods effectively handle complex health data interactions.
Outperformed traditional models and other boosting algorithms in classification accuracy.

Structured PICO

Do machine learning models using lifestyle and clinical risk factors accurately classify breast cancer status in Puerto Rican women?

Population

1393 Puerto Rican women with lifestyle, demographic, reproductive, and established epidemiological risk-factor variables

Intervention

Machine learning models (Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost) for breast cancer classification

Comparator

Comparison among different machine learning algorithms

Outcome

Model classification performance (ROC-AUC, PR-AUC, F1-score, and balanced accuracy)surrogate

Gradient-boosting approaches, particularly CatBoost, effectively predict breast cancer risk using non-genetic and genetic risk factors in a Puerto Rican population.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Globally, breast cancer incidence has increased by more than 20 percent and mortality has increased by 14 percent making it a significant public health challenge. Effective prevention and screening strategies require improved early risk assessment tools, especially for understudied populations. Current risk models are predominantly trained on European descent populations, resulting in suboptimal and uneven performance in admixed populations. Our goal was to compare how current machine learning (ML) methods perform to classify breast cancer status in a Puerto Rican population. We used a structured dataset of lifestyle, demographic, reproductive, and established epidemiological risk-factor variables from a Puerto Rican cohort of 1393 woman. Data was preprocessed using systematic data cleaning, removal of outcome-leaking features, normalization of categorical labels, imputation of missing values, and encoding of non-numeric variables. The final dataset was split using a stratified train-test strategy to preserve case-control balance, followed by model development using multiple supervised algorithms. Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost models were trained and compared using stratified 10-fold cross-validation and standardized performance metrics. After hyperparameter tuning with randomized search, the CatBoost classifier achieved the strongest performance on the held-out test set, with a ROC-AUC of 0.8009, PR-AUC of 0.8285, F1-score of 0.7239, and balanced accuracy of 0.7342, outperforming both traditional models and other boosting algorithms. Model interpretability was assessed using SHapley Additive exPlanations (SHAP) and permutation-based feature importance, which consistently identified influential predictors including menopausal status, smoking history, polygenic risk score, age, and number of sisters with breast cancer, among other risk factors. These findings confirm that gradient-boosting approaches, particularly CatBoost, effectively capture nonlinear interactions in multidimensional health data while maintaining interpretability. Overall, this work demonstrates the feasibility and utility of integrating machine learning to predict breast cancer risk using non-genetic and genetic risk factors in a Puerto Rican population. Citation Format: Jorge E. Martínez-Jiménez, Sol V. Pérez-Mártir, Doralis de León-Vázquez, Nelly A. Arroyo, Julie Dutil. Machine learning based classification of breast cancer using lifestyle and clinical risk factors in Puerto Rican women abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 4226.

Ask AI

Helpful

Bookmark