EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A novel machine learning-based cancer-specific cardiovascular disease risk score among patients with breast, colorectal, or lung cancer

Nickolas Stabellini iD, Omar M Makram iD, Harikrishnan Hyma Kunhiraman iD, Hisham Daoud iD, John Shanahan iD, Alberto J Montero iD, Roger S Blumenthal iD, Charu Aggarwal iD, Umang Swami iD, Salim S Virani iD, Vanita Noronha iD, Neeraj Agarwal iD und 2 weitere

JNCI Cancer Spectrum · 2025

DOI: 10.1093/jncics/pkaf016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JNCI Cancer Spectrum, 2025. Verfasst von Nickolas Stabellini und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Cardiology, Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA 30912, United States. Hauptthemen laut MEDLINE: Machine Learning, Breast Neoplasms, Lung Neoplasms, Colorectal Neoplasms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: American Heart Association-Strategically Focused Research Network Grant in Disparities in Cardio-Oncology, Department of Defense Prostate Cancer Research Program's Physician Research, American Heart Association—Strategically Focused Research Network Grant in Disparities in Cardio-Oncology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cancer patients have up to a 3-fold higher risk for cardiovascular disease (CVD) than the general population. Traditional CVD risk scores may be less accurate for them. We aimed to develop cancer-specific CVD risk scores and compare them with conventional scores in predicting 10-year CVD risk for patients with breast cancer (BC), colorectal cancer (CRC), or lung cancer (LC).

Methods

We analyzed adults diagnosed with BC, CRC, or LC between 2005 and 2012. An machine learning (ML) Extreme Gradient Boosting algorithm ranked 40-50 covariates for predicting CVD for each cancer type using SHapley Additive exPlanations values. The top 10 ML-predictors were used to create predictive equations using logistic regression and compared with American College of Cardiology (ACC)/American Heart Association (AHA) Pooled Cohort Equations (PCE), Predicting Risk of cardiovascular disease EVENTs (PREVENT), and Systematic COronary Risk Evaluation-2 (SCORE2) using the area under the curve (AUC).

Results

We included 10 339 patients: 55.5% had BC, 15.6% had CRC, and 29.7% had LC. The actual 10-year CVD rates were: BC 21%, CRC 10%, and LC 28%. The predictors derived from the ML algorithm included cancer-specific and socioeconomic factors. The cancer-specific predictive scores achieved AUCs of 0.84, 0.76, and 0.83 for BC, CRC, and LC, respectively, and outperformed PCE, PREVENT, and SCORE2, increasing the absolute AUC values by up to 0.31 points (with AUC ranging from 0 to 1). Similar results were found when excluding patients with cardiac history or advanced cancer from the analysis.

Conclusions

Cancer-specific CVD predictive scores outperform conventional scores and emphasize the importance of integrating cancer-related covariates for precise prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBreast NeoplasmsLung NeoplasmsColorectal NeoplasmsCardiovascular DiseasesHumansFemaleMiddle AgedMaleAgedRisk AssessmentLogistic ModelsArea Under CurveAdultAlgorithms

Autor:innen und Institutionen

  • Division of Cardiology, Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA 30912, United States.
  • Case Western Reserve University School of Medicine, Case Western Reserve University, Cleveland, OH 44106, United States.
  • Department of Hematology-Oncology, University Hospitals Seidman Cancer Center, Cleveland, OH 44106, United States.
  • Faculdade Israelita de Ciências da Saúde Albert Einstein, Hospital Israelita Albert Einstein, São Paulo, SP 05652-900, Brazil.
  • Cardio-Oncology Program, Medical College of Georgia at Augusta University, Augusta, GA 30912, United States.
  • School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30912, United States.

ORCID-Profile: Nickolas Stabellini, Omar M Makram, Harikrishnan Hyma Kunhiraman, Hisham Daoud, John Shanahan, Alberto J Montero, Roger S Blumenthal, Charu Aggarwal, Umang Swami, Salim S Virani, Vanita Noronha, Neeraj Agarwal, Susan Dent, Avirup Guha

Förderung

  • American Heart Association-Strategically Focused Research Network Grant in Disparities in Cardio-Oncology
  • Department of Defense Prostate Cancer Research Program's Physician Research
  • American Heart Association—Strategically Focused Research Network Grant in Disparities in Cardio-Oncology
  • Department of Defense Prostate Cancer Research Program’s Physician Research

Zitieren

APA

Stabellini, N., Makram, O. M., Kunhiraman, H. H., Daoud, H., Shanahan, J., Montero, A. J., Blumenthal, R. S., Aggarwal, C., Swami, U., Virani, S. S., Noronha, V., Agarwal, N., Dent, S., & Guha, A. (2025). A novel machine learning-based cancer-specific cardiovascular disease risk score among patients with breast, colorectal, or lung cancer. JNCI Cancer Spectrum. https://doi.org/10.1093/jncics/pkaf016

Vancouver

Stabellini N, Makram OM, Kunhiraman HH, Daoud H, Shanahan J, Montero AJ, et al. A novel machine learning-based cancer-specific cardiovascular disease risk score among patients with breast, colorectal, or lung cancer. JNCI Cancer Spectrum. 2025. doi:10.1093/jncics/pkaf016

BibTeX
@article{Stabellini2025,
  author = {Stabellini, Nickolas and Makram, Omar M and Kunhiraman, Harikrishnan Hyma and Daoud, Hisham and Shanahan, John and Montero, Alberto J and Blumenthal, Roger S and Aggarwal, Charu and Swami, Umang and Virani, Salim S and Noronha, Vanita and Agarwal, Neeraj and Dent, Susan and Guha, Avirup},
  title = {A novel machine learning-based cancer-specific cardiovascular disease risk score among patients with breast, colorectal, or lung cancer},
  journal = {JNCI Cancer Spectrum},
  year = {2025},
  doi = {10.1093/jncics/pkaf016}
}
Kostenlos starten →