Unlocking the complete blood count as a risk stratification tool for breast cancer using machine learning
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1355Keywords:
Blood Cell Count, Machine Learning, Breast CancerAbstract
Objective: To evaluate the efficacy of machine learning (ML) in using complete blood count (CBC) for breast cancer risk assessment. Method: This retrospective study analyzed CBCs from 396,848 women aged 40 to 70. A total of 2861 cases were identified (1882 confirmed by biopsy and 979 by imaging), while 393,987 were controls (BI-RADS 1 or 2). Data were divided into modeling (training and validation) and testing sets based on diagnostic certainty. Results: The ridge regression model, incorporating the neutrophil-to-lymphocyte ratio, red blood cells, and age, achieved an AUC of 0.64. The study population was stratified into four risk groups: high, moderate, medium, and low, with relative ratios of 1.99, 1.32, 1.02, and 0.42, respectively. Conclusion: This ML model provides a cost-effective tool for personalized breast cancer screening, potentially improving early detection in resource-limited settings.
References
Coleman C. Early Detection and Screening for Breast Cancer. Semin Oncol Nurs. 2017 May;33(2):141–55. DOI: https://doi.org/10.1016/j.soncn.2017.02.009
Araujo DC, Rocha BA, Gomes KB, da Silva DN, Ribeiro VM, Kohara MA, et al. Unlocking the complete blood count as a risk stratification tool for breast cancer using machine learning: a large scale retrospective study. Sci Rep. 2024 May 12;14(1):1–10. DOI: https://doi.org/10.1038/s41598-024-61215-y
Zhang K, Bangma CH, Venderbos LDF, Roobol MJ. Individual and Population-Based Screening. Management of Prostate Cancer. 2017;43–55. DOI: https://doi.org/10.1007/978-3-319-42769-0_3
Cuzick J. A breast cancer prediction model incorporating familial and personal risk factors. Hered Cancer Clin Pract. 2012;10(Suppl 2):A29. DOI: https://doi.org/10.1186/1897-4287-10-S2-A29
Yala A, Mikhael PG, Strand F, Lin G, Satuluru S, Kim T, et al. Multi-Institutional Validation of a Mammography-Based Breast Cancer Risk Model. J Clin Oncol [Internet]. 2022 Jun 1 [cited 2024 May 28];40(16). Available from: https://pubmed.ncbi.nlm.nih.gov/34767469/ DOI: https://doi.org/10.1200/JCO.21.01337
Danesh H, Ziamajidi N, Mesbah-Namin SA, Nafisi N, Abbasalipourkabir R. Association between Oxidative Stress Parameters and Hematological Indices in Breast Cancer Patients. Int J Breast Cancer [Internet]. 2022 Oct 3 [cited 2024 May 29];2022. Available from: https://pubmed.ncbi.nlm.nih.gov/36225290/ DOI: https://doi.org/10.1155/2022/1459410
Amin MB, Greene FL, Edge SB, Compton CC, Gershenwald JE, Brookland RK, et al. The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more “personalized” approach to cancer staging. CA Cancer J Clin. 2017 Mar;67(2):93–9. DOI: https://doi.org/10.3322/caac.21388
Hoerl AE, Kennard RW. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics [Internet]. 1970 Feb 1 [cited 2024 May 29]; Available from: https://www.tandfonline.com/doi/abs/10.1080/00401706.1970.10488634 DOI: https://doi.org/10.2307/1267351
Ke G, Meng Q, Finely T, Wang T, Chen W, Ma W, et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: Advances in Neural Information Processing Systems 30 (NIP 2017) [Internet]. 2017 [cited 2024 May 30]. Available from: https://www.microsoft.com/en-us/research/publication/lightgbm-a-highly-efficient-gradient-boosting-decision-tree/
Zuin G, Araujo D, Ribeiro V, Seiler MG, Prieto WH, Pintão MC, et al. Prediction of SARS-CoV-2-positivity from million-scale complete blood counts using machine learning. Communications Medicine. 2022 Jun 15;2(1):1–12. DOI: https://doi.org/10.1038/s43856-022-00129-0
Amador T, Saturnino S, Veloso A, Ziviani N. Early identification of ICU patients at risk of complications: Regularization based on robustness and stability of explanations. Artif Intell Med [Internet]. 2022 Jun [cited 2024 May 30];128. Available from: https://pubmed.ncbi.nlm.nih.gov/35534141/ DOI: https://doi.org/10.1016/j.artmed.2022.102283
Michaels E, Worthington RO, Rusiecki J. Breast Cancer: Risk Assessment, Screening, and Primary Prevention. Med Clin North Am [Internet]. 2023 Mar [cited 2024 May 30];107(2). Available from: https://pubmed.ncbi.nlm.nih.gov/36759097/ DOI: https://doi.org/10.1016/j.mcna.2022.10.007
Ethier JL, Desautels D, Templeton A, Shah PS, Amir E. Prognostic role of neutrophil-to-lymphocyte ratio in breast cancer: a systematic review and meta-analysis. Breast Cancer Res [Internet]. 2017 [cited 2024 May 30];19. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5217326/ DOI: https://doi.org/10.1186/s13058-016-0794-1
De Larco JE, Wuertz BR, Furcht LT. The potential role of neutrophils in promoting the metastatic phenotype of tumors releasing interleukin-8. Clin Cancer Res [Internet]. 2004 Aug 1 [cited 2024 May 30];10(15). Available from: https://pubmed.ncbi.nlm.nih.gov/15297389/ DOI: https://doi.org/10.1158/1078-0432.CCR-03-0760
Katano M, Torisu M. Neutrophil-mediated tumor cell destruction in cancer ascites. Cancer [Internet]. 1982 Jul 1 [cited 2024 May 30];50(1). Available from: https://pubmed.ncbi.nlm.nih.gov/7083126/ DOI: https://doi.org/10.1002/1097-0142(19820701)50:1<62::AID-CNCR2820500113>3.0.CO;2-0
Gago-Dominguez M, Matabuena M, Redondo CM, Patel SP, Carracedo A, Ponte SM, et al. Neutrophil to lymphocyte ratio and breast cancer risk: analysis by subtype and potential interactions. Sci Rep [Internet]. 2020 Aug 6 [cited 2024 May 30];10(1). Available from: https://pubmed.ncbi.nlm.nih.gov/32764699/ DOI: https://doi.org/10.1038/s41598-020-70077-z
Mantovani A, Allavena P, Sica A, Balkwill F. Cancer-related inflammation. Nature [Internet]. 2008 Jul 24 [cited 2024 May 30];454(7203). Available from: https://pubmed.ncbi.nlm.nih.gov/18650914/ DOI: https://doi.org/10.1038/nature07205
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
