Machine Learning Algorithms Predict Breast Cancer Incidence Risk with Enhanced Biomarkers

Strategic Insights -

Researchers at the Guangzhou University of Chinese Medicine have developed a machine learning-based model to predict breast cancer incidence risk by incorporating both personal clinical factors and peripheral blood biochemical biomarkers. The study aimed to enhance the understanding of breast cancer risk by identifying novel risk factors using machine learning algorithms. The researchers screened and normalized data from 17,360 cases and 8,551 cases, and employed logistic regression and six other machine learning algorithms to identify variables associated with breast cancer incidence. The performance of the models was evaluated using the area under the curve (AUC) through 5-fold cross-validation.

Key Takeaways:

  • The study used machine learning algorithms to identify novel breast cancer risk factors, including peripheral blood biochemical biomarkers.
  • The researchers employed logistic regression and six other machine learning algorithms to evaluate the performance of the models.
  • The study found that breast cancer incidence was increased with age, with an odds ratio of 1.136 (95% confidence interval: [1.130, 1.142], P < 0.001).
  • The study concluded that incorporating the identified risk factors into a tailored breast cancer risk prediction model is needed in future research.
  • The study's findings have implications for enhancing the understanding of breast cancer risk and developing more accurate predictive models.

Statistics:

  • 17,360 cases were used in the training cohort.
  • 8,551 cases were used in the testing cohort.
  • The odds ratio for breast cancer incidence was 1.136 (95% confidence interval: [1.130, 1.142], P < 0.001).
  • The area under the curve (AUC) was used to evaluate the performance of the models.

Sources:

  • Machine learning algorithms predict breast cancer incidence risk: a data-driven retrospective study based on biochemical biomarkers. BMC Cancer, 2025; 25(1): 1061.
  • Our news journalists report: Peng Wu, Second Clinical College, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, People's Republic of China.
  • Keywords for this news article include: Asia, Cyborgs, Oncology, Guangdong, Algorithms, Biomarkers, Cancer Risk, Biochemicals, Biochemistry, Transferases, Breast Cancer, Women's Health, Machine Learning, Health and Medicine, Risk and Prevention, Alanine Transaminase, Emerging Technologies, Enzymes and Coenzymes, Information Technology, Diagnostics and Screening.