Novel models by machine learning to predict the risk of cardiac disease-specific death in young patients with breast cancer
2024

Machine Learning Models to Predict Cardiac Death Risk in Young Breast Cancer Patients

Sample size: 253362 publication 10 minutes Evidence: high

Author Information

Author(s): Li Yi, Li Handong, Ye Xuan, Zhu Zhigang, Qiu Yixuan

Primary Institution: The Second Affiliated Hospital, School of Medicine, South China University of Technology

Hypothesis

Can machine learning models effectively predict the risk of cardiac disease-specific death in young breast cancer patients?

Conclusion

The study identified independent risk factors for cardiac disease-specific death in young breast cancer patients and developed machine learning models that accurately predict these risks.

Supporting Evidence

  • Young breast cancer patients with lower household income are at higher risk of cardiac disease-specific death.
  • Machine learning models, particularly XGBoost, showed high accuracy in predicting cardiac disease-specific death risks.
  • Factors such as race, marital status, and age at diagnosis were identified as significant predictors of cardiac disease-specific death.

Takeaway

This study found that young women with breast cancer can be at risk of dying from heart problems, and it created computer models to help doctors figure out who is at the highest risk.

Methodology

Data from breast cancer patients under 50 was analyzed using a competing risk model and machine learning techniques, including XGBoost, to predict cardiac disease-specific death risks.

Potential Biases

Potential biases may arise from the retrospective nature of the study and the limitations of the SEER database.

Limitations

The study is retrospective and relies on data from the SEER database, which may have inherent deficiencies.

Participant Demographics

The study focused on female breast cancer patients under 50 years old, with a significant portion being unmarried and from lower-income backgrounds.

Statistical Information

P-Value

p<0.001

Confidence Interval

95% CI 1.062–1.093

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1007/s12672-024-01676-9

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication