Machine Learning Based Analysis Of Clinical And Laboratory Biomarkers For Early Cancer Detection
Abstract
Early detection remains an important objective in cancer diagnostics because clinical outcomes are strongly influenced by the stage at which disease is identified. Clinical and laboratory biomarkers provide measurable information about physiological, biochemical, and disease-related changes that may support earlier detection; however, the simultaneous analysis of multiple biomarkers and patient characteristics can be challenging using conventional statistical approaches. Machine learning (ML) offers computational methods for identifying complex patterns within clinical and laboratory datasets and for developing predictive models that may assist in distinguishing cancer from non-cancer conditions. This article examines the application of ML-based analysis to clinical and laboratory biomarkers for early cancer detection, with particular attention to data preparation, feature selection, classification, prediction, and model evaluation. Research involving commonly used clinical measurements, biochemical markers, hematological parameters, tumor-associated biomarkers, and combinations of laboratory and clinical variables is discussed. Supervised learning methods, including logistic regression, decision trees, random forests, support vector machines, k-nearest neighbors, and artificial neural networks, are considered in relation to their use in biomarker-based cancer prediction. The discussion further examines how feature selection and multivariable modelling can identify combinations of biomarkers that provide greater diagnostic information than individual measurements. Findings reported across the literature indicate that ML can improve the analysis of heterogeneous biomarker profiles by capturing nonlinear relationships and interactions among clinical variables. Nevertheless, model performance is influenced by dataset size, biomarker selection, data quality, class imbalance, validation strategies, and differences between patient populations. The article concludes that ML-based analysis provides a useful framework for combining clinical and laboratory biomarkers in early cancer detection, while emphasizing the need for independent validation, interpretable models, and clinically representative datasets before widespread diagnostic application.
Keywords
Downloads
References
- World Health Organization. (2022). A short guide to cancer screening: increase effectiveness, maximize benefits and minimize harm. World Health Organization. Regional Office for Europe.
- Hornbrook, M. C., Goshen, R., Choman, E., O’Keeffe-Rosetti, M., Kinar, Y., Liles, E. G., & Rust, K. C. (2017). Early colorectal cancer detected by machine learning model using gender, age, and complete blood count data. Digestive diseases and sciences, 62(10), 2719-2727.
- Wu, J., Zan, X., Gao, L., Zhao, J., Fan, J., Shi, H., & Xie, X. (2019). A machine learning method for identifying lung cancer based on routine blood indices: qualitative feasibility study. JMIR medical informatics, 7 (3), e13476.
- Fan, G., Cui, R., Zhang, R., Zhang, S., Guo, R., Zhai, Y., ... & Wang, Q. (2022). Routine blood biomarkers for the detection of multiple myeloma using machine learning. International Journal of Laboratory Hematology, 44(3), 558-566.
- Ahamad, M. M., Aktar, S., Uddin, M. J., Rahman, T., Alyami, S. A., Al-Ashhab, S., ... & Moni, M. A. (2022). Early-stage detection of ovarian cancer based on clinical data using machine learning approaches. Journal of personalized medicine, 12(8), 1211.
- Ahamad, M. M., Aktar, S., Uddin, M. J., Rahman, T., Alyami, S. A., Al-Ashhab, S., ... & Moni, M. A. (2022). Early-stage detection of ovarian cancer based on clinical data using machine learning approaches. Journal of personalized medicine, 12(8), 1211.
- Gould, M. K., Huang, B. Z., Tammemagi, M. C., Kinar, Y., & Shiff, R. (2021). Machine learning for early lung cancer identification using routine clinical and laboratory data. American journal of respiratory and critical care medicine, 204(4), 445-453.
- Fan, G., Cui, R., Zhang, R., Zhang, S., Guo, R., Zhai, Y., ... & Wang, Q. (2022). Routine blood biomarkers for the detection of multiple myeloma using machine learning. International Journal of Laboratory Hematology, 44(3), 558-566.
- Yan, W., Shi, H., He, T., Chen, J., Wang, C., & Liao, A. (2021). Employment of artificial intelligence based on routine laboratory results for the early diagnosis of multiple myeloma. Front Oncol. 2021; 11: 608191.
- Li, H., Lin, J., Xiao, Y., Zheng, W., Zhao, L., Yang, X., ... & Liu, H. (2021). Colorectal cancer detected by machine learning models using conventional laboratory test data. Technology in Cancer Research & Treatment, 20, 15330338211058352.
- Sato, M., Morimoto, K., Kajihara, S., Tateishi, R., Shiina, S., Koike, K., & Yatomi, Y. (2019). Machine-learning approach for the development of a novel predictive model for the diagnosis of hepatocellular carcinoma. Scientific reports, 9(1), 7704.
- Ahamad, M. M., Aktar, S., Uddin, M. J., Rahman, T., Alyami, S. A., Al-Ashhab, S., ... & Moni, M. A. (2022). Early-stage detection of ovarian cancer based on clinical data using machine learning approaches. Journal of personalized medicine, 12(8), 1211.
- Kim, M., Chen, C., Wang, P., Mulvey, J. J., Yang, Y., Wun, C., ... & Heller, D. A. (2022). Detection of ovarian cancer via the spectral fingerprinting of quantum-defect-modified carbon nanotubes in serum by machine learning. Nature Biomedical Engineering, 6(3), 267-275.
- Nitta, S., Tsutsumi, M., Sakka, S., Endo, T., Hashimoto, K., Hasegawa, M., ... & Nishiyama, H. (2019). Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity. Prostate international, 7(3), 114-118.
- Perera, M., Mirchandani, R., Papa, N., Breemer, G., Effeindzourou, A., Smith, L., ... & Smith, E. (2021). PSA-based machine learning model improves prostate cancer risk stratification in a screening population. World journal of urology, 39(6), 1897-1902.
- Xu, Z., Huang, Y., Hu, C., Du, L., Du, Y. A., Zhang, Y., ... & Cheng, X. (2023). Efficient plasma metabolic fingerprinting as a novel tool for diagnosis and prognosis of gastric cancer: a large-scale, multicentre study. Gut, 72(11), 2051-2067.
- Schneider, J. L., Layefsky, E., Udaltsova, N., Levin, T. R., & Corley, D. A. (2020). Validation of an algorithm to identify patients at risk for colorectal cancer based on laboratory test and demographic data in diverse, community-based population. Clinical Gastroenterology and Hepatology, 18(12), 2734-2741.
- Wang, H. Y., Chen, C. H., Shi, S., Chung, C. R., Wen, Y. H., & Wu, M. H. Improving multi-tumor biomarker health check-up tests with machine learning algorithms. Cancers. 2020.
- Chen, X., Gole, J., Gore, A., He, Q., Lu, M., Min, J., ... & Jin, L. (2020). Non-invasive early detection of cancer four years before conventional diagnosis using a blood test. Nature communications, 11(1), 3475.
- Jia, Y., Liu, Z., Guo, J., He, C., Zhou, X., Xue, M., ... & Liu, S. (2023). Machine Learning and Bioinformatics Analysis for Laboratory Data in Pan‐Cancers Detection. Advanced Intelligent Systems, 5(12), 2300283.
- Jansen, T., Geleijnse, G., Van Maaren, M., Hendriks, M. P., Ten Teije, A., & Moncada-Torres, A. (2020). Machine learning explainability in breast cancer survival. In Digital Personalized Health and Medicine: Proceedings of MIE 2020 (pp. 307-311). 1 Oliver's Yard, 55 City Road, London, EC1Y 1SP: SAGE Publications.