EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning predictors of post‐radiotherapy cardiotoxicity in a Latin American breast cancer cohort: Clinical risk factors outperform cardiac dosimetry

Víctor Aguirre-Bravo, Rodrigo El Far, María Herrera Ruiz, Sophia Gálvez Santelices, Pablo Munoz-Schuffenegger, Tomás Merino, Sergio Diez Domingo, Marcelo E Andia

Journal of Applied Clinical Medical Physics · 2026

DOI: 10.1002/acm2.70862 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2026. Verfasst von Víctor Aguirre-Bravo und 7 weiteren Autor:innen. Beteiligte Einrichtung: Radiation Safety, UC CHRISTUS, Santiago, Chile. Hauptthemen laut MEDLINE: Cardiotoxicity, Breast Neoplasms, Machine Learning, Radiotherapy, Intensity-Modulated. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondo Nacional de Desarrollo Científico y Tecnológico, Agencia Nacional de Investigación y Desarrollo.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Most evidence on post‐radiotherapy cardiotoxicity (CDT) derives from Global North cohorts, and the relative contribution of baseline clinical risk versus cardiac dosimetry remains poorly characterized in Latin American populations.

Purpose

To examine, in a Chilean breast cancer cohort, whether baseline clinical risk factors or cardiac dose‐volume metrics better predict post‐RT cardiac events, using supervised and unsupervised learning.

Methods

Retrospective cohort of 42 breast cancer patients treated with thoracic radiotherapy (RT, median heart dose 2.6 Gy; median follow‐up 84.4 months). CDT was defined per CTCAE v5.0 ( Grade 1), excluding Grade 1 events coded under the non‐specific term “Cardiac disorders – Other, specify” , which on review were incidental imaging findings. Dose‐volume histogram (DVH) parameters from seven cardiac substructures were extracted. Firth penalized logistic regression was used for prediction, principal component analysis (PCA) and kernel PCA for exploratory clustering, and bootstrap 0.632+ for optimism correction. The 2023 American Heart Association (AHA) PREVENT score was evaluated post hoc.

Results

Ten patients (23.8%) developed CDT and 16 (38.1%) experienced cardiovascular events. No DVH differences were found between CDT+ and CDT− groups across any cardiac structure (all ), although the design is powered only for large effects. By contrast, IMRT delivered significantly higher cardiac doses than 3D‐CRT across multiple substructures, without a differential CDT rate. Pre‐existing cardiovascular disease was the strongest predictor (crude OR = 6.50, ; adjusted OR = 2.08, 95% CI 1.03–4.16, ). The median time to the first CTCAE‐graded event was 48.4 months. The clinical‐only model reached an area under the curve (AUC) of 0.783 versus 0.604 for dosimetry alone; the combined model corrected to 0.649 (95% CI 0.204–0.933). The AHA PREVENT score showed no significant risk gradient (trend ) but was markedly less susceptible to overfitting than DVH‐only models (optimism 0.089 vs. 0.194).

Conclusions

In this low‐cardiac‐dose cohort, baseline clinical variables outperformed cardiac dose‐volume metrics in predicting post‐RT cardiac events, although the design was not powered to exclude a dose‐effect relationship at these exposures. Registry‐based baseline risk assessment is therefore the more robust starting point in this setting, and IMRT breast RT planning warrants multi‐substructure cardiac dosimetry monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CardiotoxicityBreast NeoplasmsMachine LearningRadiotherapy, Intensity-ModulatedHeartHumansFemaleRetrospective StudiesMiddle AgedRadiotherapy DosageOrgans at RiskRisk FactorsRadiometryAgedAdultPrognosisFollow-Up StudiesRadiotherapy Planning, Computer-AssistedPredictive Learning Models

Stichwörter der Autor:innen

AHA PREVENT scoreFirth logistic regressionLatin Americabreast cancer radiotherapycardiac dosimetrycardio‐oncologymachine learningpost‐radiotherapy cardiotoxicity

Autor:innen und Institutionen

  • Radiation Safety, UC CHRISTUS, Santiago, Chile.
  • Institute of Physics, Pontificia Universidad Católica de Chile, Santiago, Chile.
  • Radiotherapy, UC CHRISTUS, Santiago, Chile.
  • Department of Hematology-Oncology, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile.
  • Department of Physiology, Universitat de València, Valencia, Spain.
  • Department of Radiology, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile.

Förderung

  • Fondo Nacional de Desarrollo Científico y Tecnológico
  • Agencia Nacional de Investigación y Desarrollo

Zitieren

APA

Aguirre-Bravo, V., El Far, R., Herrera Ruiz, M., Gálvez Santelices, S., Munoz-Schuffenegger, P., Merino, T., Diez Domingo, S., & Andia, M. E. (2026). Machine learning predictors of post‐radiotherapy cardiotoxicity in a Latin American breast cancer cohort: Clinical risk factors outperform cardiac dosimetry. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70862

Vancouver

Aguirre-Bravo V, El Far R, Herrera Ruiz M, Gálvez Santelices S, Munoz-Schuffenegger P, Merino T, et al. Machine learning predictors of post‐radiotherapy cardiotoxicity in a Latin American breast cancer cohort: Clinical risk factors outperform cardiac dosimetry. Journal of Applied Clinical Medical Physics. 2026. doi:10.1002/acm2.70862

BibTeX
@article{AguirreBravo2026,
  author = {Aguirre-Bravo, Víctor and El Far, Rodrigo and Herrera Ruiz, María and Gálvez Santelices, Sophia and Munoz-Schuffenegger, Pablo and Merino, Tomás and Diez Domingo, Sergio and Andia, Marcelo E},
  title = {Machine learning predictors of post‐radiotherapy cardiotoxicity in a Latin American breast cancer cohort: Clinical risk factors outperform cardiac dosimetry},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  doi = {10.1002/acm2.70862}
}
Kostenlos starten →