Artificial Intelligence And Machine Learning In Cancer Biomarker Discovery: Emerging Approaches For Early Diagnosis
Abstract
Early detection is an important component of improving cancer diagnosis and treatment outcomes, yet conventional biomarker approaches often face limitations in sensitivity, specificity, and biological heterogeneity. The increasing availability of high-throughput genomic, transcriptomic, proteomic, metabolomic, and circulating biomarker data has created new opportunities for computational approaches to identify more informative diagnostic patterns. This review examines the application of artificial intelligence (AI) and machine learning (ML) to cancer biomarker discovery, with particular emphasis on laboratory-based approaches for early diagnosis. It discusses major biomarker classes, including circulating proteins, genomic and DNA alterations, microRNAs, metabolites, and liquid-biopsy markers, and examines how ML methods can support feature selection, dimensionality reduction, classification, and integration of molecular measurements. Applications across breast, lung, colorectal, pancreatic, ovarian, prostate, gastric, and liver cancers demonstrate how computational analysis can identify multi-biomarker signatures from complex biological datasets. The review also considers diagnostic performance measures, ROC analysis, validation strategies, overfitting, and the distinction between statistical discrimination and clinical utility. Challenges related to dataset heterogeneity, laboratory variability, external validation, interpretability, reproducibility, data privacy, and clinical implementation remain important barriers to translation. Future progress is likely to depend on integrating multiple molecular and clinical data types through multimodal and multi-omics AI approaches. Ultimately, the clinical value of AI-assisted biomarker discovery will depend on rigorous validation and successful translation of computationally identified signatures into reproducible, practical, and clinically useful laboratory tests.
Keywords
Downloads
References
- Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018). Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 68(6), 394-424.
- Ginsburg, O., Yip, C. H., Brooks, A., Cabanes, A., Caleffi, M., Dunstan Yataco, J. A., ... & Anderson, B. O. (2020). Breast cancer early detection: A phased approach to implementation. Cancer, 126, 2379-2393.
- Mann, M., Kumar, C., Zeng, W. F., & Strauss, M. T. (2021). Artificial intelligence for proteomics and biomarker discovery. Cell systems, 12(8), 759-770.
- Xiao, Q., Zhang, F., Xu, L., Yue, L., Kon, O. L., Zhu, Y., & Guo, T. (2021). High-throughput proteomics and AI for cancer biomarker discovery. Advanced drug delivery reviews, 176, 113844.
- Andrades, R., & Recamonde-Mendoza, M. (2022). Machine learning methods for prediction of cancer driver genes: a survey paper. Briefings in Bioinformatics, 23(3), bbac062.
- Nicora, G., Vitali, F., Dagliati, A., Geifman, N., & Bellazzi, R. (2020). Integrated multi-omics analyses in oncology: a review of machine learning methods and tools. Frontiers in oncology, 10, 530980.
- Pezoulas, V. C., Hazapis, O., Lagopati, N., Exarchos, T. P., Goules, A. V., Tzioufas, A. G., ... & Gorgoulis, V. G. (2021). Machine learning approaches on high throughput NGS data to unveil mechanisms of function in biology and disease. Cancer Genomics-Proteomics, 18(5), 605-626.
- Abu-Halima, M., Keller, A., Becker, L. S., Fischer, U., Engel, A., Ludwig, N., ... & Keller, V. (2023). Dynamic and static circulating cancer microRNA biomarkers–a validation study. RNA biology, 20(1), 1-9.
- Abu-Halima, M., Keller, A., Becker, L. S., Fischer, U., Engel, A., Ludwig, N., ... & Keller, V. (2023). Dynamic and static circulating cancer microRNA biomarkers–a validation study. RNA biology, 20(1), 1-9.
- Galal, A., Talal, M., & Moustafa, A. (2022). Applications of machine learning in metabolomics: Disease modeling and classification. Frontiers in genetics, 13, 1017340.
- Nicora, G., Vitali, F., Dagliati, A., Geifman, N., & Bellazzi, R. (2020). Integrated multi-omics analyses in oncology: a review of machine learning methods and tools. Frontiers in oncology, 10, 530980.
- Desaire, H., Go, E. P., & Hua, D. (2022). Advances, obstacles, and opportunities for machine learning in proteomics. Cell Reports Physical Science, 3(10).
- Lee, D., Park, Y., & Kim, S. (2021). Towards multi-omics characterization of tumor heterogeneity: a comprehensive review of statistical and machine learning approaches. Briefings in bioinformatics, 22(3), bbaa188.
- Pezoulas, V. C., Hazapis, O., Lagopati, N., Exarchos, T. P., Goules, A. V., Tzioufas, A. G., ... & Gorgoulis, V. G. (2021). Machine learning approaches on high throughput NGS data to unveil mechanisms of function in biology and disease. Cancer Genomics-Proteomics, 18(5), 605-626.
- Schneider, L., Laiouar-Pedari, S., Kuntz, S., Krieghoff-Henning, E., Hekler, A., Kather, J. N., ... & Brinker, T. J. (2022). Integration of deep learning-based image analysis and genomic data in cancer pathology: A systematic review. European journal of cancer, 160, 80-91.
- Kumar, S., Warrell, J., Li, S., McGillivray, P. D., Meyerson, W., Salichos, L., ... & Gerstein, M. B. (2020). Passenger mutations in more than 2,500 cancer genomes: overall molecular functional impact and consequences. Cell, 180(5), 915-927.
- Cheng, F., Zhao, J., & Zhao, Z. (2016). Advances in computational approaches for prioritizing driver mutations and significantly mutated genes in cancer genomes. Briefings in bioinformatics, 17(4), 642-656.
- Abu-Halima, M., Keller, A., Becker, L. S., Fischer, U., Engel, A., Ludwig, N., ... & Keller, V. (2023). Dynamic and static circulating cancer microRNA biomarkers–a validation study. RNA biology, 20(1), 1-9.
- Li, J., Liu, K., Ji, Z., Wang, Y., Yin, T., Long, T., ... & Cheng, L. (2022). Serum Untargeted Metabolomics Analyses Reveal Metabolic Alteration of Non-Small Cell Lung Cancer and Refine Cancer Detection in Chinese Population. Available at SSRN 4153825.
- Cardoso, M. R., Silva, A. A. R., Talarico, M. C. R., Sanches, P. H. G., Sforca, M. L., Rocco, S. A., ... & Derchain, S. F. (2022). Metabolomics by NMR combined with machine learning to predict neoadjuvant chemotherapy response for breast cancer. Cancers, 14(20), 5055.
- Ye, X., Yang, X. Z., Carbone, R., Barshack, I., & Katz, R. L. (2021). Diagnosis of non-small cell lung cancer via liquid biopsy highlighting a fluorescence-in-situ-hybridization circulating tumor cell approach. In Pathology-From Classics to Innovations. IntechOpen.
- Batool, S. M., Yekula, A., Khanna, P., Hsia, T., Gamblin, A. S., Ekanayake, E., ... & Balaj, L. (2023). The Liquid Biopsy Consortium: Challenges and opportunities for early cancer detection and monitoring. Cell Reports Medicine, 4(10).
- Menyhárt, O., & Győrffy, B. (2021). Multi-omics approaches in cancer research with applications in tumor subtyping, prognosis, and diagnosis.
- Afzal, S., Hassan, M., Ullah, S., Abbas, H., Tawakkal, F., & Khan, M. A. (2022). Breast cancer; discovery of novel diagnostic biomarkers, drug resistance, and therapeutic implications. Frontiers in molecular biosciences, 9, 783450.
- Xie, Y., Meng, W. Y., Li, R. Z., Wang, Y. W., Qian, X., Chan, C., ... & Leung, E. L. H. (2021). Early lung cancer diagnostic biomarker discovery by machine learning methods. Translational oncology, 14(1), 100907.
- Capello, M., Bantis, L. E., Scelo, G., Zhao, Y., Li, P., Dhillon, D. S., ... & Hanash, S. M. (2017). Sequential validation of blood-based protein biomarker candidates for early-stage pancreatic cancer. JNCI: Journal of the National Cancer Institute, 109(4), djw266.