Advancing cancer care through artificial intelligence: from innovative models to clinical decision-making and regulatory integration

Abstract

Artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools across the oncology drug development pipeline, spanning from early discovery and compound screening to clinical trial optimization and regulatory oversight. With the growing complexity of cancer biology and the rising demand for precision medicine, AI technologies offer new strategies to accelerate therapeutic innovation, reduce development costs, and improve clinical outcomes. This review synthesizes recent advancements in AI-driven oncology, integrating perspectives from computational modeling, predictive analytics, clinical decision-making, and evolving regulatory frameworks. We highlight how AI-enabled platforms are being employed to identify druggable targets, optimize molecular design, predict drug target interactions, and support preclinical and clinical decision-making. Special attention is given to advanced architectures such as cascade deep forest models, deep learning networks, and the transformative impact of large language models and multimodal AI, including AlphaFold 3, which have demonstrated superior performance in drug target interaction prediction and de novo compound generation. Beyond technical accuracy, we emphasize the importance of “model actionability,” a concept rooted in the ability of AI models to reduce diagnostic and therapeutic uncertainty, thus enhancing their practical value in clinical oncology. Furthermore, we discuss the U.S. Food and Drug Administration’s (FDA) proactive engagement with AI/ML applications, particularly in the context of clinical trials, safety monitoring, and real-world evidence generation. The integration of AI into regulatory science underscores the need for transparency, contextual validation, and risk-based oversight. By bridging scientific innovation with clinical utility and regulatory expectations, this review underscores the pivotal role of AI in advancing oncology drug development and shaping the future of cancer care.

Keywords

Artificial intelligence / Oncology drug development / Machine learning / Clinical decision making / Drug target interaction / Model actionability / Regulatory integration

References

[1] Mak KK, Pichika MR. Artificial intelligence in drug development: present status and future prospects. Drug Discov Today, 2019, 24(3): 773-780

[2] Ferreira FJN, Carneiro AS. Ai-driven drug discovery: a comprehensive review. ACS Omega, 2025, 10(23): 23889-23903

[3] Ocana A, Pandiella A, Privat C, Bravo I, Luengo-Oroz M, Amir E, Györffy B. Integrating artificial intelligence in drug discovery and early drug development: a transformative approach. Biomark Res, 2025, 13(1): 45

[4] Rusanov A, et al.. Artificial Intelligence in oncology: current applications and future directions. npj Precision Oncol, 2023, 7(157

[5] Ryu JY, Kim HU, Lee SY. Deep learning improves prediction of drug–drug and drug–food interactions. Proc Natl Acad Sci U S A, 2018, 115(18E4304-E4311

[6] Stokes JM, et al.. A deep learning approach to antibiotic discovery. Cell, 2020, 180(4): 688-702.e13

[7] U.S. Food & Drug Administration. Artificial Intelligence and machine learning in software as a medical device. 2021. https://www.fda.gov.

[8] Öztürk H, Özgür A, Ozkirimli E. DeepDTA: deep drug–target binding affinity prediction. Bioinformatics, 2018, 34(17): i821-i829

[9] Zhou ZH, Feng J. Deep forest: towards an alternative to deep neural networks. Int Joint Conf Artif Intell, 2017, 30: 3553-3559

[10] Segler MH, Kogej T, Tyrchan C, Waller MP. Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci, 2018, 4(1): 120-131

[11] Zhou Z, Qin P, Cheng X, et al.. ChatGPT in oncology diagnosis and treatment: applications, legal and ethical challenges. Curr Oncol Rep, 2025, 27(4): 336-354

[12] Wang W, Wang Y, Zhao H, Sciabola S. A transformer-based generative model for de novo molecular design. 2022. arXiv preprint, arXiv: 2210.08749. .

[13] Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, Venkatesh S. GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics, 2021, 37(8): 1140-1147

[14] Chithrananda S, Grand G, Ramsundar B. ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. 2020. arXiv preprint, arXiv: 2010.09885.

[15] Abramson J, Adler J, Dunger J, et al.. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature, 2024, 630(7991): 493-500

[16] Hou J. De Novo molecular design enabled by direct preference optimization and curriculum learning. 2025. arXiv preprint, arXiv:2504.01389. .

[17] Preuer K, et al.. DeepSynergy: predicting anti-cancer drug synergy with deep learning. Bioinformatics, 2018, 34(9): 1538-1546

[18] Wei CH, Allot A, Leaman R, Lu Z. PubTator central: automated concept annotation for biomedical full text articles. Nucleic Acids Res, 2019, 47(W1): W587-W593

[19] Verlingue L, Boyer C, Olgiati L, et al.. Artificial intelligence in oncology: ensuring safe and effective integration of language models in clinical practice. Lancet Regional Health - Europe, 2024, 46 101064

[20] Walters WP, Murcko MA. Assessing the impact of generative AI on drug discovery. Nat Biotechnol, 2023, 41(4): 432-444

[21] Hopkins AL, et al.. Exscientia: centaur chemist and AI-driven drug discovery. Drug Discov Today Technol, 2020, 38: 35-43

[22] Keane H, Topol E. BenevolentAI: using AI to unlock complex biology. Lancet, 2021, 397(10273): 977

[23] Zhavoronkov A, et al.. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol, 2019, 37(91038-1040

[24] Wallach I, Dzamba M, Heifets A. AtomNet: a deep convolutional neural network for bioactivity prediction. 2015. arXiv preprint, arXiv: 1510.02855.

[25] Kingma DP, Welling M. Auto-encoding variational bayes. 2014. arXiv preprint, arXiv:1312.6114.

[26] Ardila D, et al.. End-to-end lung cancer screening with 3D deep learning. Nat Med, 2019, 25(6): 954-961

[27] Fu L, Jia G, Liu Z, Pang X, Cui Y. The applications and advances of artificial intelligence in drug regulation: a global perspective. Acta Pharm Sin B, 2025, 15(1): 1-14

[28] Esteva A, et al.. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, 542(7639): 115-118

[29] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med, 2019, 25(1): 44-56

[30] Gupta R, Ahmed A, Syed T, et al.. Real-world evaluation of IBM watson for oncology. JCO Glob Oncol, 2020, 6: 827-836

[31] Chen M, et al.. Smart health: AI technologies enabling the future of personalized healthcare. IEEE Rev Biomed Eng, 2018, 11: 21-32

[32] Watson DS, et al.. Clinical applications of machine learning algorithms: beyond the black box. BMJ, 2019, 364 l886

[33] Tomašev N, et al.. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature, 2019, 572(7767): 116-119

[34] Badawi M, et al.. Explainable AI for precision oncology: from black box to translational insight. JCO Clin Cancer Inform, 2022, 6e2100172

[35] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst, 2017, 30: 4765-4774

[36] Awan SE, et al.. Application of AI to stratify colorectal cancer patients for adjuvant chemotherapy. Cancer Med, 2022, 11(6): 1361-1372

[37] U.S. Food & Drug Administration. Proposed regulatory framework for modifications to artificial intelligence/machine learning-based software. 2019.

[38] Liu Y, et al.. Artificial intelligence–based breast cancer nodal metastasis detection: insights into the LYNA model. JAMA Oncol, 2019, 5(9): 1305-1309

[39] Senders JT, et al.. Natural language processing in neurosurgical clinical practice. Neurosurg Focus, 2018, 45(6): E18

[40] London AJ. Artificial intelligence and black-box medical decisions: accuracy versus explainability. Hastings Cent Rep, 2019, 49(115-21

[41] Derraz B, Breda G, Kaempf C, et al.. New regulatory thinking is needed for AI-based personalised drug and cell therapies in precision oncology. NPJ Precis Oncol, 2024, 8(1 23

[42] Beam AL, Kohane IS. Big data and machine learning in health care. JAMA, 2018, 319(13): 1317-1318

[43] Shah A, et al.. Safe and responsible use of artificial intelligence in health care: current regulatory landscape and considerations for regulatory policy. JCO Clin Cancer Inform, 2025, 9 e2500123

[44] Kim DW, Jang HY, Kim KW, Shin Y, Park SH. Design characteristics of studies reporting the performance of AI algorithms for diagnostic analysis. Radiology, 2019, 293(3): 607-617

[45] Amann J, Blasimme A, Vayena E, Frey D, Madai VI. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak, 2020, 20(1): 310

[46] Bzdok D, Altman N, Krzywinski M. Points of significance: statistics versus machine learning. Nat Methods, 2018, 15(4233-234

[47] Yang G, et al.. Medical imaging AI for cancer diagnosis: a review. Med Image Anal, 2021, 72102102

[48] Chen RJ, Lu MY, Wang J, Williamson DFK, Mahmood F. Synthetic data in machine learning for medicine and healthcare. Nat Biomed Eng, 2021, 5(6): 493-497

[49] Reddy S, Allan M, Shaban M, et al.. A review of AI in medical imaging. BMJ Health Care Informatics, 2020, 27(3e100104

[50] Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with AI. BMC Med, 2019, 17(1): 195

[51] Mennella C, Maniscalco U, De Pietro G, Esposito M. Ethical and regulatory challenges of AI technologies in healthcare: a narrative review. Heliyon, 2024, 10(4 e26297

[52] Haenssle HA, et al.. Man against machine: diagnostic performance of a deep learning convolutional neural network versus dermatologists. Eur J Cancer, 2018, 102: 91-96

[53] Narayan A, et al.. Real-world use of AI in pathology: challenges and solutions. Am J Surg Pathol, 2021, 45(81075-1082

[54] Sahiner B, Pezeshk A, Hadjiiski LM, Wang X, Drukker K, Cha KH, et al.. Deep learning in medical imaging and radiation therapy. Med Phys, 2019, 46(1): e1-e36

[55] Lee JG, et al.. Deep learning in medical imaging: general overview. Korean J Radiol, 2017, 18(4): 570-584

[56] Rajpurkar P, et al. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. 2017. arXiv preprint, arXiv:1711.05225.

[57] Johnson KW, et al.. Artificial intelligence in cardiology. J Am Coll Cardiol, 2018, 71(23): 2668-2679

[58] Coudray N, et al.. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat Med, 2018, 24(10): 1559-1567

[59] Kann BH, Hosny A, Aerts HJWL. Artificial intelligence for clinical oncology. Cancer Cell, 2021, 39(7): 916-927

[60] Litjens G, et al.. A survey on deep learning in medical image analysis. Med Image Anal, 2017, 42: 60-88

[61] Xiang H, Zeng L, Hou L, et al.. A molecular video-derived foundation model for scientific drug discovery. Nat Commun, 2024, 15(1): 9696

[62] Luchini C, Pea A, Scarpa A. Artificial intelligence in oncology: current applications and future perspectives. Br J Cancer, 2022, 126: 4-9

[63] Askr H, Elgeldawi E, Aboul Ella H, El-Sappagh S. Deep learning in drug discovery: an integrative review and future challenges. Artif Intell Rev, 2023, 56(75975-6037

RIGHTS & PERMISSIONS

The Author(s)