Comparative Performance Analysis of Bayesian Hierarchical Models Versus Classical Statistical Approaches in Predicting Breast Cancer Treatment Outcomes: Evidence from Kenyan Healthcare Settings

References

[1] Bray, F., et al. (2024). Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 74(3), 229-263.

[2] Newman, L. A., et al. (2019). Breast cancer disparities in African women living in sub-Saharan Africa or the United States. Cancer, 125(24), 4456-4463.

[3] GLOBOCAN. (2020). Global Cancer Observatory: Cancer Today. International Agency for Research on Cancer, Lyon, France.

[4] Collins, G. S., et al. (2021). Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI). BMJ Open, 11(7), e048008.

[5] Austin, P. C., et al. (2018). To multilevel or not to multilevel: when to use multilevel modeling in health services research. Health Services Research, 53(4), 2531-2550.

[6] Gelman, A., et al. (2013). Bayesian data analysis (3rd ed.). CRC Press.

[7] Sidey-Gibbons, J. A. M., & Sidey-Gibbons, C. J. (2019). Machine learning in medicine: a practical introduction. BMC Medical Research Methodology, 19, 64.

[8] Cubasch, H., et al. (2017). Breast cancer characteristics and HIV among 1,092 women in Soweto, South Africa. Breast Cancer Research and Treatment, 166(3), 743-754.

[9] Mansell, J., et al. (2021). Improving quality and access to cancer care in sub-Saharan Africa. Journal of Global Oncology, 7, 1-4.

[10] Harrell, F. E. (2015). Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. Springer.

[11] Collins, G. S., et al. (2015). Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement. Annals of Internal Medicine, 162(1), W1-W73.

[12] Wessels, L. F., & van de Vijver, M. J. (2022). External validation of breast cancer prediction models: a systematic review. Breast Cancer Research, 24, 83.

[13] Spiegelhalter, D. J. (2019). The art of statistics: How to learn from data. Basic Books.

[14] Spiegelhalter, D. J. (2019). The art of statistics: How to learn from data. Basic Books.

[15] Hoffman, M. D., & Gelman, A. (2014). The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo. Journal of Machine Learning Research, 15(1), 1593-1623.

[16] Goldstein, H. (2011). Multilevel statistical models. John Wiley and Sons.

[17] Austin, P. C., et al. (2018). To multilevel or not to multilevel: when to use multilevel modeling in health services research. Health Services Research, 53(4), 2531-2550.

[18] Gelman, A., et al. (2013). Bayesian data analysis (3rd ed.). CRC Press.

[19] Wessels, L. F., & van de Vijver, M. J. (2022). External validation of breast cancer prediction models: a systematic review. Breast Cancer Research, 24, 83.

[20] Jedy-Agba, E., et al. (2022). Determinants of stage at diagnosis of breast cancer in Nigerian women. Cancer Causes and Control, 31(3), 233-241.

[21] Azubuike, S. O., et al. (2018). Rising global burden of breast cancer: the case of sub-Saharan Africa. World Journal of Surgical Oncology, 16, 63.

[22] Debray, T. P., et al. (2017). A framework for developing, implementing, and evaluating clinical prediction models in an era of big data. BMC Medicine, 15, 155.

[23] Berger, J. O. (2020). The case for objective Bayesian analysis. Bayesian Analysis, 15(3), 859-899.

[24] Berger, J. O. (2020). The case for objective Bayesian analysis. Bayesian Analysis, 15(3), 859-899.

[25] Lee, P. M. (2019). Bayesian statistics: an introduction. John Wiley & Sons.

@article{1709508,
      author = {Muhati Nelson Lwoyelo, Richard Simwa, Vincent Marani},
      title = {Comparative Performance Analysis of Bayesian Hierarchical Models Versus Classical Statistical Approaches in Predicting Breast Cancer Treatment Outcomes: Evidence from Kenyan Healthcare Settings},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {1},
      pages = {243-250},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1709508.pdf},
      abstract = {Current breast cancer treatment prediction models inadequately quantify uncertainty and fail to account for institutional clustering effects, particularly in resource-constrained healthcare settings. This study compared the performance of Bayesian hierarchical models against classical frequentist approaches for predicting pathological complete response (pCR) in breast cancer patients. We analyzed data from 5,400 breast cancer patients across 12 Kenyan treatment centers. Three progressively complex models were developed: single-level logistic regression (M0), Bayesian empty hierarchical model (M1), and Bayesian hierarchical model with clinical covariates (M2). Performance comparison utilized multiple metrics including Area Under the Curve (AUC), Brier Score, calibration measures, and information criteria. The Bayesian hierarchical model demonstrated superior performance with AUC = 0.837 compared to classical approaches (AUC = 0.752). Bayesian methods showed consistent 2-8 unit improvements in information criteria across all model complexity levels. The hierarchical structure captured 26.5% of outcome variation attributable to institutional clustering (ICC = 0.265), which classical models failed to address. Uncertainty quantification through credible intervals provided clinically meaningful prediction confidence assessment. Bayesian hierarchical approaches significantly outperform classical statistical methods in breast cancer treatment outcome prediction, particularly in settings with institutional clustering. The explicit uncertainty quantification and superior discrimination make Bayesian methods more suitable for clinical decision-making in resource-constrained environments.},
      keywords = {Bayesian Statistics, Breast Cancer, Treatment Outcomes, Model Comparison},
      month = {July},
  }