The role of AI in oncology: present applications and future horizons.

Leveraging AI in clinical oncology: an introduction

Artificial intelligence (AI) holds tremendous promise for streamlined decision-making and data-derived treatment in healthcare. As it pertains to oncology, where patient selection, therapy response, and drug development are highly nuanced, AI offers a powerful means to accelerate precision medicine and narrow the gap between academic centers and community care.

Yet, for many oncologists, terms like “AI” and “precision medicine” remain largely conceptual if not aspirational. While there is current authoritative guidance on the clinical trial implementation of AI, concerns surrounding data have hindered broad integration 1 – 3 . In this perspective, we offer a forward-looking roadmap for the dissemination of AI in oncology. This evolutionary timeline begins with AI’s present use in abstraction for clinical trial selection, progresses toward phenotype-driven therapy selection, and ultimately envisions AI-enabled drug design (Fig. 1 ). At each stage, we highlight both capabilities and current limitations to inform realistic pathways for integration. Though not a formal systematic review, this perspective draws on a thorough literature search and input from academic and commercial leaders. Fig. 1 Visual orientation to the integration of artificial intelligence (AI) in application to oncology. Created in Biorender without the use of AI assistance.

AI-assisted patient selection in oncology clinical trials

Randomized clinical trials are the cornerstone of oncologic advancement. Such studies rely on sufficient enrollment of patients who meet specific eligibility criteria. Traditionally, this is a process involving manual chart review and data abstraction, presenting a major barrier to trial accrual. AI, particularly through natural language processing (NLP) and large language models (LLMs), offers an unparalleled ability to synthesize large datasets and parse unstructured clinical data to streamline clinical trial matching. This improvement is achieved without a loss in key performance metrics and diagnostic yield, with systematic reviews reporting accuracy, sensitivity, and specificity consistently exceeding 80% 4 , 5 . Initial AI efforts in oncology clinical trials have leveraged NLP to extract cancer phenotypes from rich clinical text, with notable efforts focused on breast and lung malignancies 4 . Tools such as Mendel.ai and Watson for Clinical Trial Matching have demonstrated automated eligibility screening by filtering patient chart information to standardized medical terminology matched to clinical trials 6 . This workflow significantly reduced manual labor time in the early stages of patient selection 7 . A 2025 review by Saady et al. identified 16 studies focused on AI in clinical trial enrollment and highlighted near-universal improvements in screening efficiency, with time reductions of 25% or more 8 . More recently, as utilized in 7 out of 33 clinical trial studies published in 2023, LLMs have advanced the interpretation of complex trial protocols, optimizing patient-trial matching 9 . TrialGPT is one such system that uses a three-stage pipeline: extracting relevant trials, evaluating eligibility criteria, and reversing the trial paradigm to generate a ranked list of candidate trials for the patient to consider. GPT-4-based TrialGPT achieved a combined-feature performance of 0.73 while reducing screening time, suggesting that newer model iterations (GPT-5.2) could further enhance trial ranking. 10 . Notably, this NCI/NIH-built system provides explanations for eligibility decisions to enhance interpretability and an open-source codebase 11 . In parallel, LLM-based tools, Criteria2Query 3.0 and AutoCriteria, have refined the extraction of granular eligibility criteria from clinical trial documents 12 , 13 . These systems generate structured queries from trials formatted for downstream software to search large patient databases, achieving a similar goal to TrialGPT without an embedded workflow.

Beyond protocol interpretation or reliance on synthetic patient datasets, emerging AI systems can be integrated directly within point-of-care pathways. This allows the use of real-world patient data to refine trial eligibility. More importantly, embedded workflow promises the democratization of clinical trial recruitment beyond high-volume centers and potentially enables smaller, peripheral sites to accrue patients. MatchMiner, an open-source platform developed at the Dana-Farber Cancer Institute, has streamlined the consent-to-trial pathway by incorporating genomic profiling into the matching process 14 , 15 . This system has been used in innovative ways, such as automatically notifying oncologists via email when a solid tumor patient with panel DNA next-generation sequencing is matched to a trial. This process achieved a 17% discordance rate between AI-generated matches and expert physician assessments 16 . Similarly, OncoLLM, a domain-specific, EHR-embedded model trained on single-center data, has demonstrated physician-level accuracy in identifying appropriate clinical trials for oncology patients 17 . Together, these integrated models may bridge the gap between abstract model development and point-of-care deployment.

While trial matching solutions continue to mature, the next frontier lies in AI-powered adaptive trials that iteratively learn from participant data streams to refine eligibility criteria, modify treatment arms, and recalibrate endpoints 18 , 19 . This shift from static to dynamic protocol is largely advanced by industry leaders in direct partnership with pharmaceutical sponsors and promises the ability to make trials more efficient, personalized, and effective.

Ideally, AI-enabled patient-trial matching would reduce recruitment costs and shorten the timeline for trial activation. Yet, current systems still require human oversight to validate AI-generated matches, and software vendors are acutely aware of the legal risk posed by using AI in patient care 20 . In addition, AI-driven selection can reinforce existing biases, particularly when training datasets underrepresent diverse patient populations and are not transparent about which parameters are valued (closed-weight) 21 , 22 . For example, tools such as TrialGPT rely on a synthetic, closed-weight dataset for development and have critical dependencies on cloud-based vendors. While platforms like MatchMiner mitigate this issue by using real patient data, they are still closed-weight and face barriers to scalability due to dependence on institution-specific infrastructure. Expert reviews consistently echo these limitations, citing small sample sizes, restricted access to patient records, and limited generalizability as persistent challenges across published models 6 , 8 . Alternatively, open weight LLMs, such as LlaMA2 and Mistral, may offer more transparency and create reproducibility and reinforce provider trust in clinical trial recruitment 23 .

Although LLMs may appropriately select patients meeting trial criteria 17 , a concern is that most LLM-based patient selections operate as “black boxes,” with limited insight into how variables may have been weighted in patient selection. This lack of transparency, coupled with the potential for AI hallucinations or confabulated inputs, can undermine clinician trust and clinical adoption, a challenge emphasized by expert review of clinical trial applications 24 – 26 . If clinicians cannot understand how a match is generated or created, the tool, no matter how accurate the underlying logic is, becomes a source of concern. Many LLMs are also prompt-dependent; narrow queries can drive blind data analysis in clinicians without expertise, potentially propagating misinformation and mistrust. To fully realize the potential of AI in clinical trial recruitment, future systems must prioritize data diversity, interpretability, and transparency. As emphasized by Verlingue et al., AI must not disrupt the face-to-face communication between the patient and physician 27 . There should be multi-institutional efforts to build data sources that capture the rich diversity of patients, ensuring that AI models are truly representative. While initiatives like Truveta have begun to establish shared data repositories, the lack of clear guidelines around IP ownership has hindered collaborative model training 28 . If these challenges are addressed, AI holds significant promise to fundamentally reshape how oncology clinical trials are conducted.

AI-predicted drug selection and response in oncology

Beyond optimizing clinical trial recruitment, AI has significant potential to proactively guide treatment selection and reduce therapy inefficiency 29 . Given that many patients receiving oncology drugs do not achieve the desired effect, multimodal AI platforms incorporating disparate data sources like genetic or laboratory assays, demographic variables, clinical information, and biowearable physiological signals may optimizedrug efficacy. When applied to large, multimodal datasets, AI techniques, especially deep learning (DL) approaches, can stratify patients into clinically similar cohorts to improve forecasting of treatment responses 30 , 31 .

As we gain a deeper understanding of disease heterogeneity and the expanding role of immunotherapy, AI is increasingly being used for initial treatment selection in oncology. An outline of existing models and their contributions is provided in Table 1 . In parallel, industry partners have advanced AI-driven platforms for drug selection (Table 2 ). Using machine learning (ML) with EHR data, Pan et al. derived predictive clinical subphenotypes for non-small cell lung cancer to determine response to immune checkpoint inhibitor (ICI) therapy, outperforming other models 32 . At an individual level, AI has been harnessed to predict ICI outcomes across cancer types using routine blood tests, improving on FDA-approved biomarkers 33 . At the cellular level, neural networks can “learn” tumor archetypes, facilitating selection of targeted therapy 34 . The large computational power of ML has even been harnessed to predict drug responses from single-cell RNA sequencing data 35 , 36 . Table 1 Representative list of peer-reviewed, published models of AI in application to drug selection, identified through targeted PubMed and Scopus searches Model name Model type AI approach Oncology application Stage Description Performance metrics Reference Year PERCEPTION Open Source ML Multiple myeloma, breast cancer, NSCLC Selection Predicts resistance and sensitivity to FDA-approved therapies from single-cell and bulk RNA-seq data. AUC = 0.81 for predicting sensitive cell lines, AUC = 0.83 for stratifying responder status. Sinha et al. 35 2024 ATSDP-NET Proprietary DL Oral squamous cell carcinoma, prostate cancer, and multiple myeloma Selection Predicts treatment response from single-cell and bulk RNA-seq data. High correlation ( R = 0.89) between predicted and actual gene sensitivity scores. Zhou et al. 34 2025 DL-Based MSI/dMMR Proprietary DL Colorectal cancer Selection Detects MSI/dMMR from whole-slide H&E pathology images. AUC = 0.89 for predicting MSI/dMMR status. Echle et al. 36 2022 DL-Based MSI-H Proprietary DL Prostate cancer Selection Detects MSI-H from whole-slide H&E pathology images. AUC = 0.78 for predicting MSI status. Hu et al. 37 2024 SCORPIO Open Source ML Pan-Cancer (21 types) Selection Predict the clinical benefit of ICI therapy from CBC/CMP and clinical characteristics. AUC = 0.76 for predicting 6–30 months overall survival (OS), outperforming tumor mutational burden. Yoo et al. 32 2025 GEMS Proprietary ML NSCLC Treatment Response Stratifies ICI-treated patients into predictive subphenotypes based on EHR clinical data. C-index = 0.67, outperforming unsupervised clustering methods to predict OS. Pan et al. 30 2025 AANet Proprietary ML Breast cancer Treatment Response Identifies key cell archetypes using spatial transcriptomics. Minimized mean square error (MSE) between the input expression and reconstructed profile. Venkat et al. 33 2025 H&E DL Angio Proprietary DL Renal cancer Treatment Response Predicts response to anti-angiogenic therapy from tumor regions on whole-slide H&E pathology images. Strong correlation (c-index = 0.67) with costly gold standard, Angioscore. Jasti et al. 35 2025 CHAI Proprietary DL NMIBC Treatment Response Predicts BCG response from histologic assays and clinical variables. Model stratified patients to predict 3.9 higher odds of progression, 2.3 higher odds of BCG-unresponsive disease, and 3.4 higher odds needing cystectomy. Lotan et al. 39 2024 GMLF Proprietary DL MIBC Treatment Response Predicts neoadjuvant response from whole-slide images and tissue gene expression. AUC = 0.74 for predicting response to neoadjuvant chemotherapy. Bai et al. 40 2025 PDRP Open Source ML NSCLC Treatment Response Predicts treatment response from the geometry of the drug-target binding site. 97.5% accuracy, 93% recall, 96.5% precision, and 94% F1-score for a 4-class drug response prediction task. Qureshi et al. 41 2022 DRN-CDR Open Source DL Pan-Cancer (24 types) Treatment Response Models dose-response using drug molecular structures, IC50, Cancer Cell Line Encyclopedia (CCLE). AUC = 0.76 for classifying drugs as sensitive or resistant. Saranya et al. 49 2024 DrugCell Open Source DL Pan-Cancer Treatment Response, Synergy Predicts single-agent response and synergy. High correlation ( R = 0.80) between actual and predictive drug response. Kuenzi et al. 48 2020 CURATE.AI Proprietary DL Advanced, solid tumors on palliative care, metastatic prostate cancer Dosing Creates and modulates a dosing regimen based on individualized biomarkers. Expert clinician users chose to follow dosing recommendations for 97.2% of decisions. Blasiak et al. 42 2025 Table 2 Selected commercial AI platforms for clinical trial and therapy selection in oncology, including their computational approaches and clinical use cases Company AI approach Oncology application Stage Description Country of origin CertisAI ML Pan-cancer (Solid and liquid tumors) Drug Selection Tumor molecular profiling is completed, and 5–20 genes of interest are identified to create a proprietary gene expression signature that is compared to FDA-approved medications. USA CureMatch ML Pan-cancer (solid tumor) Drug Selection Tumor molecular profiling is completed, and the efficacy of various treatments is ranked, including drug combinations. USA Foundation Medicine (Roche) Pan-cancer (solid and liquid tumors) Clinical Trial Selection, Drug Selection, Treatment Response Genomic and tumor profiling is used to match patients to targeted therapy and clinical trials. Denmark Predictive Oncology Inc DL Breast, colon, ovary, AML, MM Drug Selection, Drug Repurposing Assesses FDA-approved drugs against ovarian tumor samples. Drug repurposing from the biobank of dissociated tumor cells. Develops organoid models for hematological (AML, MM) malignancies. USA Tempus DL Pan-cancer (solid and liquid tumors) Clinical Trial Selection, Drug Selection Partners with academic centers for site activation of oncology trials. Commercially available for multi-omic sequencing to predict patient treatment response to ICI, generation of tumor organoids. USA ArteraAI DL Prostate Treatment Response A prognostic model that combines digital pathology images with clinical data to predict response to hormonal therapy and combination treatments in high-risk prostate cancer. USA ConcertAI, Guardant Health ML Pan-cancer (>60 solid tumor types) Drug Selection, Treatment Response A combination of solid tumor liquid biopsies and clinical data is used to select treatment and monitor therapy response in advanced cancer. USA Lantern Pharma (RADR) ML Pan-cancer (solid and liquid tumors) Treatment Response Uses a proprietary multi-omic database to stratify patients into responder, partial responder, and non-responder categories. USA

Given that microsatellite instability (MSI) is an indicator of response to immunotherapy, AI has been applied to characterize this molecular-level biomarker. In colorectal cancer, DL has predicted MSI status directly from pathology slides with clinical-grade performance, accelerating therapeutic decision-making 37 . A similar model was developed for prostate cancer, where MSI status is not routinely tested; an AI screening tool may broaden access to ICI by identifying eligible patients 38 . DL digital histopathology models have shown promise in multiple settings, including identifying patients with metastatic clear cell renal cell carcinoma responsive to anti-angiogenic therapy at a fraction of the cost and predicting BCG-responsiveness in non-muscle-invasive bladder cancer (NMIBC) 39 , 40 . With AI, whole-slide image data can be supplemented with gene expression profiles for superior predictive accuracy. This has been implemented in predicting the response to neoadjuvant chemotherapy in muscle-invasive bladder cancer (MIBC) 41 . Macroscopically, AI models contextualizing protein-drug interaction features with patient data have accurately predicted EGFR-TKI responses in NSCLC 42 .

Multimodal assessment with AI can also anticipate dynamic changes in treatment response, enabling earlier intervention before toxicity or resistance is clinically evident. CURATE.AI is an agnostic platform that uses clinical biomarkers alongside patient medical history to dynamically adjust a palliative chemotherapy dosing regimen 43 . This system has also been trialed in metastatic castration-resistant prostate cancer to modulate combination chemotherapy dosing on an individual-by-individual basis 44 . Given that targeted radionuclide therapy has become a treatment option in select metastatic cancers, emerging digital twin platforms in nuclear oncology promise patient-specific simulations of radiopharmaceutical kinetics to optimize dosing and minimize adverse toxicity 45 . Dose modulation based on patient-specific multi-omics has drawn considerable attention from industry, with companies like OncoKDM and DoseMeRx aiming to personalize dosing strategies. Similarly, when this dynamic dosing regimen is paired with outcomes-based feedback loops, it challenges the need for large-scale clinical trials, enabling continuous learning mechanisms for personalized treatment regimens. AI also holds promise in assisting with response-adaptive radiotherapy, increasing physician confidence to maximize tumor control while minimizing side effects 46 , 47 . Building on these applications, AI has been employed to identify synergistic drug combinations from existing large-scale datasets 48 , 49 .

In an ideal setting, trends in biomarkers, along with clinical and genetic data, could be continuously integrated using AI to proactively modify treatment plans before detrimental effects or suboptimal response 43 , 50 . However, broad implementation remains limited by data fragmentation and the challenges of synthesizing high-volume information in real-time. High-quality and well-annotated data are necessary to train models, yet relevant data sources, such as oncology notes and imaging, are difficult to incorporate. Even when high-quality data is extracted, small datasets are prone to overfitting, resulting in poor generalization to new patient data, particularly when the data the model is applied to is significantly larger in magnitude than the training data itself. Beyond this, ground truth data for predicting pathologic or physiologic response is not standardized. In the models discussed above, some assign a complete response as ground truth, whereas others do not. As such, models may differ in their utility based on what the training set comprises and how training was achieved.

Achieving real-time AI-driven treatment adaptation would require centralized data repositories (data lakes) and seamless EHR integration that is difficult to coordinate within institutions, let alone between institutions. Even when large data synthesis is achieved, LLMs can become overwhelmed and inadvertently overweight irrelevant factors. Small language models may be a good initial step before federated learning with LLMs, accomplishing targeted computing tasks and rapid iteration locally within the healthcare systems. Their ability to function locally also bypasses privacy concerns and shows promise for N-of-One therapy 51 .

AI in de novo drug design: the final frontier

While the use of AI in optimizing existing treatments continues to evolve, transformative potential may lie even further upstream. The discovery and development of new oncologic therapies often spans decades and costs millions, only to have the majority fail to gain regulatory approval. By processing vast amounts of data and simulating human decision-making through neural networks, AI can accelerate the bench-to-bedside workflow of pharmaceutical development.

Just as AI may uncover overlooked patterns in existing treatment selections, it is now used to generate entirely new therapeutic compounds. The presence of AI-discovered molecules in clinical trials has grown exponentially from the early stages of PubChem bioassays and the clinical trial introduction of AI-discovered molecules in 2015 52 , 53 . AI can contribute to every stage of drug design: identifying molecular targets, predicting protein-ligand interactions, and modeling in-vivo drug behavior with simulation of pharmacologic properties.

For example, druggability, the likelihood a gene can be targeted for therapeutic effect, can be predicted with DrugnomeAI and PINNED, ML frameworks that use genomic data to identify oncologic therapeutics 54 , 55 . Other AI-learning systems also exploit the concept of druggability, outperforming existing methods 56 – 58 . Similarly, AI has enhanced the identification of synthetic lethal interactions, a strategy that selectively kills cancer cells by targeting gene pairs, with neural network models advancing prior computational methods 59 . A major leap came with the development of AlphaFold, a neural network platform to predict protein structure with high accuracy at a fraction of the cost and time of traditional techniques, like X-Ray crystallography 60 . When coupled with generative adversarial networks, AI can further refine predictions of protein-ligand interactions to accelerate lead compound development 61 , 62 .

In addition to early-stage discovery, AI is also reshaping the modeling of drug-host interactions. Simulations now allow for the prediction of pharmacokinetics/pharmacodynamics. As highlighted in a preliminary analysis by Jayatunga et al., these models have shown improved success rates in Phase I trials compared to industry standards 52 , 63 .

Several of these AI-driven approaches have already led to in silico investigational compounds. Although, as of this publication, no AI-designed drugs have completed the full approval process for oncology indications, a growing number have received Investigational New Drug clearance. One notable example includes a CDK12/13 dual inhibitor, identified through a multi-omic AI pipeline to block upregulation of DNA-damage response pathways and the subsequent tumorigenesis 64 . AI has also aided the design of proteolysis-targeting chimeras (PROTACs); bifunctional molecules that induce the degradation of disease-relevant proteins within a cell. AI assistance led to a PROTAC targeting p300, a chromatin regulator implicated in prostate cancer progression 65 .

Beyond designing new compounds, AI promises the ability to repurpose existing therapies that may otherwise be orphaned, a faster and cheaper process than developing new agents. For example, the neural network-based GraphRepur model extracts drug gene expression signatures and structural information to identify new therapeutic indications, such as repurposing agents for breast cancer 66 . Interest in AI for drug development and repurposing is ever-growing, and the field is already populated by several clinical-stage companies (Table 3 ). Table 3 Representative AI enterprises for drug discovery and repurposing in oncology, summarizing their applications and design features Company AI approach Oncology application Stage Description Country of origin Numerion Labs DL Pan-cancer (solid and liquid tumors) Drug Design Developed a protocol to quickly screen chemical libraries and identify drug-like molecules that can bind disease-related targets (i.e., androgen receptor sites). USA Benevolent AI ML Pan-cancer (solid and liquid tumors) Drug Design, Drug Repurposing Uses “patient-level data” to group patients into endotypes for subsequent drug discovery. Partnered with Novartis to investigate new indications for drugs in clinical development. Luxembourg Exscientia DL Pan-cancer (solid and liquid tumors) Drug Design Trains on pharmacology data and patient multi-omics to iteratively design and chemically synthesize targeted compounds, including an A2a receptor antagonist. UK Insilico DL Pan-cancer (solid and liquid tumors) Drug Design Uses AI generative chemistry platforms (Chemistry42) to generate molecular scaffolds tailored to target binding affinity, with a specific focus on tumors that invade the immune system. USA Recursion Pharmaceuticals DL Pan-cancer (solid tumor, B-cell lymphoma) Drug Design Conducts molecular design using multi-omics data and iterative loops, discovering a CDK12-adjacent target for DNA-damage response. USA Schrodinger DL Pan-cancer (solid tumor) Drug Design Integrates ML and physics-based algorithms to predict protein-ligand binding affinity and identify chemotypes. Germany Xaira Pharmaceuticals DL Pan-cancer (solid and liquid tumors) Drug Design Created the largest Perturb-seq platform and uses diffusion-based generative AI for protein design. Has implemented early research in CTLA-4 antibodies. USA

While the term “precision medicine” is often applied broadly, many current programs fall short of true patient-level specificity. The full actualization would involve drugs custom-tailored to an individual’s gene expression, somatic mutations, and clinical context. This vision may become possible with the maturation of General AI, systems capable of integrating germline sequencing, tumor-specific genomic alterations, EHRs, environmental exposures, and more to generate drug candidates. Achieving this goal requires not only high-volume, high-quality data but also systems that deliver interpretable recommendations. In addition, the concept of General AI requires a combination of multiple complex computational skills: a higher level of transfer reasoning, short-term “memory” to support self-directed and single-shot learning, and datasets that support reasoning beyond narrow AI’s capabilities.

While AI has shown strong performance across both well-defined and increasingly complex tasks, current systems remain dependent on human oversight and are constrained by several limitations. Datasets used in drug discovery often involve millions of candidate compounds and can overwhelm traditional ML algorithms 67 . Although AI is promoted to reduce cost, the computational demands of high-complexity modeling impose a significant resource burden that should not be overlooked 68 . Moreover, AI-generated molecules often resemble known ligands, suggesting current models are better suited for optimizing existing chemical scaffolds versus generating entirely novel hits 69 . While the majority of AI-based drug design has leveraged supervised learning to follow existing chemical scaffolds, unsupervised learning may hypothetically generate truly novel compounds. Yet, many of these drug designs fail secondary to toxicity, synthesis feasibility, pharmacokinetics, or biocompatability 70 . As with AI in clinical trial matching and drug selection, external validity is also a major challenge 6 . The diversity of models and the absence of a standardized protocol hinder regulatory acceptance 71 , 72 .

Perhaps the most formidable barrier lies in this latter domain 73 . Oncology drugs already undergo rigorous evaluation for safety and efficacy; the introduction of AI-generated variants raises several questions. Would every unique molecular permutation require separate approval? What role would AI systems play in submission and review? 74 What safeguards would be needed to protect patient data, particularly when therapies are derived from genomic profiles 75 ?

No matter how new therapies are generated, the bottleneck may be obtaining real-world clinical data 68 . Until models can reliably simulate accurate, physiologic responses for novel therapies, clinical validation will continue to be the limiting step 76 , 77 . The use of AI in drug design is one of the most ambitious frontiers in oncologyand the potential is shadowed by the ethical, technical, and regulatory hurdles. Realizing individualized cancer therapies will depend not only on algorithmic innovation, but on the development of infrastructure and governance standards to ensure safety and reproducibility in the new era of oncologic therapeutics.

Conclusion

AI now touches virtually every stage of oncologic care. LLMs substantially reduce trial-screening burden, while industry groups have launched AI-enabled adaptive trials to scale recruitment and prioritize the most promising studies. Advances in computation have enabled academic and commercial systems that integrate “multi-omic” data to forecast therapeutic benefit and resistance on an individual level. In parallel, AI-driven platforms for de novo discovery and repurposing have accelerated drug design. Yet, broad clinical impact will depend on establishing the infrastructure, standards, and oversight necessary for equitable implementation.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Author contributions

A.W. contributed to methodology, original manuscript drafting, and revisions. N.S. contributed to conceptualization, original manuscript drafting, revisions, and supervision. A.R. contributed to conceptualization, original manuscript drafting, revisions, and supervision.

Data availability

No datasets were generated or analyzed during the current study.

Competing interests

The authors declare no competing interests.

References

1. Liu, X. et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat. Med. 26 , 1364–1374 (2020). 10.1038/s41591-020-1034-x PMC7598943 32908283

2. Cruz Rivera, S. et al. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat. Med. 26 , 1351–1363 (2020). 10.1038/s41591-020-1037-7 PMC7598944 32908284

3. Saltman, A. FDA’s Regulation of AI/ML SaMD. NAMSA. https://namsa.com/resources/blog/fdas-regulation-of-ai-ml-samd/ (2024).

4. Chow, R. et al. Use of artificial intelligence for cancer clinical trial enrollment: a systematic review and meta-analysis. J. Natl. Cancer Inst. 115 , 365–374 (2023). 10.1093/jnci/djad013 PMC10086633 36688707

5. Han R Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review Lancet Digit. Health 2024 6 e367 e373 10.1016/S2589-7500(24)00047-5 38670745 PMC11068159 Han, R. et al. Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review. Lancet Digit. Health 6 , e367–e373 (2024). 38670745 10.1016/S2589-7500(24)00047-5 PMC11068159

6. Lu X Artificial intelligence for optimizing recruitment and retention in clinical trials: a scoping review J. Am. Med. Inform. Assoc. 2024 31 2749 2759 10.1093/jamia/ocae243 39259922 PMC11491624 Lu, X. et al. Artificial intelligence for optimizing recruitment and retention in clinical trials: a scoping review. J. Am. Med. Inform. Assoc. 31 , 2749–2759 (2024). 39259922 10.1093/jamia/ocae243 PMC11491624

7. Wang, K. et al. Evaluation of an artificial intelligence-based clinical trial matching system in Chinese patients with hepatocellular carcinoma: a retrospective study. BMC Cancer 24 , 246 (2024). 10.1186/s12885-024-11959-7 PMC10885498 38388861

8. Saady M Eissa M Yacoub AS Hamed AB Azzazy HMES Implementation of artificial intelligence approaches in oncology clinical trials: a systematic review Artif. Intell. Med 2025 161 103066 10.1016/j.artmed.2025.103066 39837136 Saady, M., Eissa, M., Yacoub, A. S., Hamed, A. B. & Azzazy, H. M. E. S. Implementation of artificial intelligence approaches in oncology clinical trials: a systematic review. Artif. Intell. Med 161 , 103066 (2025). 39837136 10.1016/j.artmed.2025.103066

9. Teodoro D Naderi N Yazdani A Zhang B Bornet A A scoping review of artificial intelligence applications in clinical trial risk assessment npj Digit. Med. 2025 8 486 10.1038/s41746-025-01886-7 40731070 PMC12307910 Teodoro, D., Naderi, N., Yazdani, A., Zhang, B. & Bornet, A. A scoping review of artificial intelligence applications in clinical trial risk assessment. npj Digit. Med. 8 , 486 (2025). 40731070 10.1038/s41746-025-01886-7 PMC12307910

10. Jin, Q. et al. Matching patients to clinical trials with large language models. Nat. Commun. 15 , 9074 (2024). 10.1038/s41467-024-53081-z PMC11574183 39557832

11. ARTIFICIAL INTELLIGENCE Connecting Patients to Clinical Trials with Artificial Intelligence—American Urological Association. https://auanews.net/issues/articles/2024/march-2024/artificial-intelligence-connecting-patients-to-clinical-trials-with-artificial-intelligence .

12. Park, J. et al. Criteria2Query 3.0: Leveraging generative large language models for clinical trial eligibility query generation. J. Biomed. Inform. 154 , 104649 (2024). 10.1016/j.jbi.2024.104649 PMC11129920 38697494

13. Datta, S. et al. AutoCriteria: a generalizable clinical trial eligibility criteria extraction system powered by large language models. J. Am. Med. Inform. Assoc. 31 , 375–385 (2024). 10.1093/jamia/ocad218 PMC10797270 37952206

14. Klein, H. et al. MatchMiner: an open-source platform for cancer precision medicine. npj Precis. Oncol. 6 , 69 (2022). 10.1038/s41698-022-00312-5 PMC9537311 36202909

15. Perlis R Watts J How AI could increase clinical trial enrollment in adults with cancer JAMA 2025 334 496 10.1001/jama.2025.10264 40569625 Perlis, R. & Watts, J. How AI could increase clinical trial enrollment in adults with cancer. JAMA 334 , 496 (2025). 40569625 10.1001/jama.2025.10264

16. Mazor, T. et al. Clinical trial notifications triggered by artificial intelligence-detected cancer progression. JAMA Netw. Open 8 , e252013 (2025). 10.1001/jamanetworkopen.2025.2013 PMC12013351 40257799

17. Gupta, S. et al. PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching system using large language models. npj Digit. Med. 7 , 305 (2024). 10.1038/s41746-024-01274-7 PMC11519882 39468259

18. Rosenthal JT Beecy A Sabuncu MR Rethinking clinical trials for medical AI with dynamic deployments of adaptive systems npj Digit. Med. 2025 8 252 10.1038/s41746-025-01674-3 40328886 PMC12056174 Rosenthal, J. T., Beecy, A. & Sabuncu, M. R. Rethinking clinical trials for medical AI with dynamic deployments of adaptive systems. npj Digit. Med. 8 , 252 (2025). 40328886 10.1038/s41746-025-01674-3 PMC12056174

19. Youssef A External validation of AI models in health should be replaced with recurring local validation Nat. Med. 2023 29 2686 2687 10.1038/s41591-023-02540-z 37853136 Youssef, A. et al. External validation of AI models in health should be replaced with recurring local validation. Nat. Med. 29 , 2686–2687 (2023). 37853136 10.1038/s41591-023-02540-z

20. Price WN Big Data and Black-Box Medical algorithms Sci. Transl. Med. 2018 10 eaao5333 10.1126/scitranslmed.aao5333 30541791 PMC6345162 Price, W. N. Big Data and Black-Box Medical algorithms. Sci. Transl. Med. 10 , eaao5333 (2018). 30541791 10.1126/scitranslmed.aao5333 PMC6345162

21. Zwack, C. et al. The evolution of digital health technologies in cardiovascular disease research. npj Digit. Med. 6 , 1 (2023). 10.1038/s41746-022-00734-2 PMC9808768 36596833

22. Hovy D Prabhumoye S Five sources of bias in natural language processing Lang. Linguist. Compass 2021 15 e12432 10.1111/lnc3.12432 35864931 PMC9285808 Hovy, D. & Prabhumoye, S. Five sources of bias in natural language processing. Lang. Linguist. Compass 15 , e12432 (2021). 35864931 10.1111/lnc3.12432 PMC9285808

23. Chowdhury, S. et al. Matching patients to clinical trials using LLaMA 2 embeddings and Siamese neural network. Preprint at medRxiv 10.1101/2024.06.28.24309677 (2024).

24. Lee P Bubeck S Petro J Benefits, limits, and risks of GPT-4 as an AI Chatbot for medicine N. Engl. J. Med. 2023 388 1233 1239 10.1056/NEJMsr2214184 36988602 Lee, P., Bubeck, S. & Petro, J. Benefits, limits, and risks of GPT-4 as an AI Chatbot for medicine. N. Engl. J. Med. 388 , 1233–1239 (2023). 36988602 10.1056/NEJMsr2214184

25. Azenkot T Rivera DR Stewart MD Patel SP Artificial intelligence and machine learning innovations to improve design and representativeness in oncology clinical trials Am. Soc. Clin. Oncol. Educ. Book 2025 45 e473590 10.1200/EDBK-25-473590 40403202 Azenkot, T., Rivera, D. R., Stewart, M. D. & Patel, S. P. Artificial intelligence and machine learning innovations to improve design and representativeness in oncology clinical trials. Am. Soc. Clin. Oncol. Educ. Book 45 , e473590 (2025). 40403202 10.1200/EDBK-25-473590

26. El Arab, R. et al. Bridging the gap: from AI success in clinical trials to real-world healthcare implementation—a narrative review. Healthcare 13 , 701 (2025). 10.3390/healthcare13070701 PMC11988730 40217999

27. Verlingue, L. et al. Artificial intelligence in oncology: ensuring safe and effective integration of language models in clinical practice. Lancet Reg. Health Eur. 46 , 10.1016/j.lanepe.2024.101064 (2024). 10.1016/j.lanepe.2024.101064 PMC11406067 39290808

28. CommonSpirit Health. Health providers unite to advance patient care by forming Truveta. https://www.commonspirit.org/news-articles/health-providers-unite-to-advance-patient-care-by-forming-truveta (2020).

29. Gyawali B Hey SP Kesselheim AS Assessment of the clinical benefit of cancer drugs receiving accelerated approval JAMA Intern. Med. 2019 179 906 10.1001/jamainternmed.2019.0462 31135808 PMC6547118 Gyawali, B., Hey, S. P. & Kesselheim, A. S. Assessment of the clinical benefit of cancer drugs receiving accelerated approval. JAMA Intern. Med. 179 , 906 (2019). 31135808 10.1001/jamainternmed.2019.0462 PMC6547118

30. Skrede, O. J. et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet 395 , 350–360 (2020). 10.1016/S0140-6736(19)32998-8 32007170

31. Hartman, E. et al. Interpreting biologically informed neural networks for enhanced proteomic biomarker discovery and pathway analysis. Nat. Commun. 14 , 5359 (2023). 10.1038/s41467-023-41146-4 PMC10475049 37660105

32. Pan, W. et al. Identification of predictive subphenotypes for clinical outcomes using real world data and machine learning. Nat. Commun. 16 , 3797 (2025). 10.1038/s41467-025-59092-8 PMC12069721 40355420

33. Yoo, S. K. et al. Prediction of checkpoint inhibitor immunotherapy efficacy for cancer using routine blood tests and clinical data. Nat. Med. 31 , 869–880 (2025). 10.1038/s41591-024-03398-5 PMC11922749 39762425

34. Venkat, A., Youlten, S. E., San Juan, B. P. et al. AAnet resolves a continuum of spatially-localized cell states to unveil intratumoral heterogeneity. Cancer Discov . 10.1158/2159-8290.CD-24-0684 (2025). 10.1158/2159-8290.CD-24-0684 PMC12498099 40552975

35. Zhou B Sun S Liu S Long H Li Y A drug response prediction method for single-cell tumors combining attention networks and transfer learning Front. Med. 2025 12 1631898 10.3389/fmed.2025.1631898 PMC12408664 40917838 Zhou, B., Sun, S., Liu, S., Long, H. & Li, Y. A drug response prediction method for single-cell tumors combining attention networks and transfer learning. Front. Med. 12 , 1631898 (2025). 10.3389/fmed.2025.1631898 PMC12408664 40917838

36. Sinha, S. et al. PERCEPTION predicts patient response and resistance to treatment using single-cell transcriptomics of their tumors. Nat. Cancer 5 , 938–952 (2024). 10.1038/s43018-024-00756-7 PMC13447014 38637658

37. Echle, A. et al. Artificial intelligence for detection of microsatellite instability in colorectal cancer—a multicentric analysis of a pre-screening tool for clinical application. ESMO Open 7 , 100400 (2022). 10.1016/j.esmoop.2022.100400 PMC9058894 35247870

38. Hu, Q. et al. Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images. npj Precis. Oncol. 8 , 88 (2024). 10.1038/s41698-024-00560-7 PMC11004110 38594360

39. Jasti, J. et al. Histopathology based AI model predicts anti-angiogenic therapy response in renal cancer clinical trial. Nat. Commun. 16 , 2610 (2025). 10.1038/s41467-025-57717-6 PMC11914575 40097393

40. Lotan, Y., Krishna, V. & Abuzeid, W. M. et al. Predicting response to intravesical BCG in high-risk NMIBC using an artificial intelligence–powered pathology assay: development and validation in an International 12-Center Cohort. J. Urol. 10.1097/JU.0000000000004278 (2024). 10.1097/JU.0000000000004278 PMC12674634 39383345

41. Bai, Z. et al. Predicting response to neoadjuvant chemotherapy in muscle-invasive bladder cancer via interpretable multimodal deep learning. npj Digit. Med. 8 , 174 (2025). 10.1038/s41746-025-01560-y PMC11929913 40121304

42. Qureshi, R. et al. Machine learning based personalized drug response prediction for lung cancer patients. Sci. Rep. 12 , 18935 (2022). 10.1038/s41598-022-23649-0 PMC9640729 36344580

43. Blasiak, A. et al. Personalized dose selection platform for patients with solid tumors in the PRECISE CURATE.AI feasibility trial. npj Precis. Oncol. 9 , 49 (2025). 10.1038/s41698-025-00835-7 PMC11845749 39984618

44. Pantuck, A. J. et al. Modulating BET bromodomain inhibitor ZEN-3694 and enzalutamide combination dosing in a metastatic prostate cancer patient using CURATE.AI, an artificial intelligence platform. Adv. Ther. 1 , 1800104 (2018).

45. Turner, J. H. Avatar: personalized precision radio-genomic theranostic oncology. Cancer Biother. Radiopharm . 10.1089/cbr.2025.0152 (2025). 10.1089/cbr.2025.0152 40576646

46. Niraula, D. et al. A decision support software for AI-assisted decision making in response-adaptive radiotherapy—an evaluation study. Int. J. Radiat. Oncol. Biol. Phys. 114 , e101–e102 (2022).

47. Niraula, D. et al. Intricacies of human–AI interaction in dynamic decision-making for precision oncology. Nat. Commun. 16 , 1138 (2025). 10.1038/s41467-024-55259-x PMC11779952 39881134

48. Baptista D Ferreira PG Rocha M A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer PLoS Comput. Biol. 2023 19 e1010200 10.1371/journal.pcbi.1010200 36952569 PMC10072473 Baptista, D., Ferreira, P. G. & Rocha, M. A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer. PLoS Comput. Biol. 19 , e1010200 (2023). 36952569 10.1371/journal.pcbi.1010200 PMC10072473

49. Kuenzi, B. et al. Predicting drug response and synergy using a deep learning model of human cancer cells. Cancer Cell 38 , 672–684.e6 (2020). 10.1016/j.ccell.2020.09.014 PMC7737474 33096023

50. Saranya KR Vimina ER DRN-CDR: A cancer drug response prediction model using multi-omics and drug features Comput. Biol. Chem. 2024 112 108175 10.1016/j.compbiolchem.2024.108175 39191166 Saranya, K. R. & Vimina, E. R. DRN-CDR: A cancer drug response prediction model using multi-omics and drug features. Comput. Biol. Chem. 112 , 108175 (2024). 39191166 10.1016/j.compbiolchem.2024.108175

51. Lu, Z. et al. Small Language Models: Survey, Measurements, and Insights 10.48550/arXiv.2409.15790 (2025).

52. KP Jayatunga M Ayers M Bruens L Jayanth D Meier C How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons Drug Discov. Today 2024 29 104009 10.1016/j.drudis.2024.104009 38692505 KP Jayatunga, M., Ayers, M., Bruens, L., Jayanth, D. & Meier, C. How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons. Drug Discov. Today 29 , 104009 (2024). 38692505 10.1016/j.drudis.2024.104009

53. Chen B Wild DJ PubChem BioAssays as a data source for predictive models J. Mol. Graph. Model. 2010 28 420 426 10.1016/j.jmgm.2009.10.001 19897391 Chen, B. & Wild, D. J. PubChem BioAssays as a data source for predictive models. J. Mol. Graph. Model. 28 , 420–426 (2010). 19897391 10.1016/j.jmgm.2009.10.001

54. Raies, A. et al. DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets. Commun. Biol. 5 , 1291 (2022). 10.1038/s42003-022-04245-4 PMC9700683 36434048

55. Cunningham M PINNED: identifying characteristics of druggable human proteins using an interpretable neural network J. Cheminform. 2023 15 64 10.1186/s13321-023-00735-7 37468968 PMC10354961 Cunningham, M. et al. PINNED: identifying characteristics of druggable human proteins using an interpretable neural network. J. Cheminform. 15 , 64 (2023). 37468968 10.1186/s13321-023-00735-7 PMC10354961

56. Krishnan, S. R., Roy, A., Wong, L. & Gromiha, M. M. DRLiPS: a novel method for prediction of druggable RNA-small molecule binding pockets using machine learning. Nucleic Acids Res . 53 , 10.1093/nar/gkaf239 (2025). 10.1093/nar/gkaf239 PMC11963762 40173014

57. Borhani, N., Izadi, I., Motahharynia, A., Sheikholeslami, M. & Gheisari, Y. DrugTar improves druggability prediction by integrating large language models and gene ontologies. Bioinformatics 10.1093/bioinformatics/btaf360 (2025). 10.1093/bioinformatics/btaf360 PMC12312791 40581797

58. Charoenkwan P Computational prediction and interpretation of druggable proteins using a stacked ensemble-learning framework iScience 2022 25 104883 10.1016/j.isci.2022.104883 36046193 PMC9421381 Charoenkwan, P. et al. Computational prediction and interpretation of druggable proteins using a stacked ensemble-learning framework. iScience 25 , 104883 (2022). 36046193 10.1016/j.isci.2022.104883 PMC9421381

59. Wang, S. et al. KG4SL: knowledge graph neural network for synthetic lethality prediction in human cancers. Bioinformatics 37 , i418–i425 (2021). 10.1093/bioinformatics/btab271 PMC8336442 34252965

60. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596 , 583–589 (2021). 10.1038/s41586-021-03819-2 PMC8371605 34265844

61. Lin CT Shiau YP Lin CC Machine learning in targeted protein degradation drug design: a technical review of PROTACs and molecular glues Drug Discov. Today 2026 31 104563 10.1016/j.drudis.2025.104563 41318024 Lin, C. T., Shiau, Y. P. & Lin, C. C. Machine learning in targeted protein degradation drug design: a technical review of PROTACs and molecular glues. Drug Discov. Today 31 , 104563 (2026). 41318024 10.1016/j.drudis.2025.104563

62. Sim J Kim D Kim B Choi J Lee J Recent advances in AI-driven protein-ligand interaction predictions Curr. Opin. Struct. Biol. 2025 92 103020 10.1016/j.sbi.2025.103020 39999605 Sim, J., Kim, D., Kim, B., Choi, J. & Lee, J. Recent advances in AI-driven protein-ligand interaction predictions. Curr. Opin. Struct. Biol. 92 , 103020 (2025). 39999605 10.1016/j.sbi.2025.103020

63. Wu, K. et al. Predicting pharmacodynamic effects through early drug discovery with artificial intelligence-physiologically based pharmacokinetic (AI-PBPK) modelling. Front. Pharmacol . 15 , 10.3389/fphar.2024.1330855 (2024). 10.3389/fphar.2024.1330855 PMC10904617 38434709

64. Lu, H. et al. Design, synthesis, and biological evaluation of novel orally available covalent CDK12/13 dual inhibitors for the treatment of tumors. J. Med. Chem. 68 , 4148–4167 (2025). 10.1021/acs.jmedchem.4c01616 39948720

65. Zhang, D. et al. Discovery of a peptide proteolysis-targeting chimera (PROTAC) drug of p300 for prostate cancer therapy. EBioMedicine 105 , 105212 (2024). 10.1016/j.ebiom.2024.105212 PMC11261775 38954976

66. Cui, C. et al. Drug repurposing against breast cancer by integrating drug-exposure expression profiles and drug–drug links based on graph neural network. Bioinformatics 37 , 2930–2937 (2021). 10.1093/bioinformatics/btab191 PMC8479657 33739367

67. Nazari E Aghemiri M Avan A Mehrabian A Tabesh H Machine learning approaches for classification of colorectal cancer with and without feature selection method on microarray data Gene Rep. 2021 25 101419 10.1016/j.genrep.2021.101419 Nazari, E., Aghemiri, M., Avan, A., Mehrabian, A. & Tabesh, H. Machine learning approaches for classification of colorectal cancer with and without feature selection method on microarray data. Gene Rep. 25 , 101419 (2021).

68. Ligero M Nahhas OSM El Aldea M Kather JN Artificial intelligence-based biomarkers for treatment decisions in oncology Trends Cancer 2025 11 232 244 10.1016/j.trecan.2024.12.001 39814650 Ligero, M., Nahhas, O. S. M., El, Aldea, M. & Kather, J. N. Artificial intelligence-based biomarkers for treatment decisions in oncology. Trends Cancer 11 , 232–244 (2025). 39814650 10.1016/j.trecan.2024.12.001

69. Stanley M Segler M Fake it until you make it? Generative de novo design and virtual screening of synthesizable molecules Curr. Opin. Struct. Biol. 2023 82 102658 10.1016/j.sbi.2023.102658 37473637 Stanley, M. & Segler, M. Fake it until you make it? Generative de novo design and virtual screening of synthesizable molecules. Curr. Opin. Struct. Biol. 82 , 102658 (2023). 37473637 10.1016/j.sbi.2023.102658

70. Özçelik R Grisoni F How evaluation choices distort the outcome of generative drug discovery J. Cheminform. 2025 17 169 10.1186/s13321-025-01108-y 41225661 PMC12613558 Özçelik, R. & Grisoni, F. How evaluation choices distort the outcome of generative drug discovery. J. Cheminform. 17 , 169 (2025). 41225661 10.1186/s13321-025-01108-y PMC12613558

71. Gottlieb S Silvis L Regulators face novel challenges as artificial intelligence tools enter medical practice JAMA Health Forum 2023 4 e232300 10.1001/jamahealthforum.2023.2300 37289461 Gottlieb, S. & Silvis, L. Regulators face novel challenges as artificial intelligence tools enter medical practice. JAMA Health Forum 4 , e232300 (2023). 37289461 10.1001/jamahealthforum.2023.2300

72. Han H Challenges of reproducible AI in biomedical data science BMC Med Genom. 2025 18 8 10.1186/s12920-024-02072-6 PMC11724458 39794788 Han, H. Challenges of reproducible AI in biomedical data science. BMC Med Genom. 18 , 8 (2025). 10.1186/s12920-024-02072-6 PMC11724458 39794788

73. Derraz, B. et al. New regulatory thinking is needed for AI-based personalised drug and cell therapies in precision oncology. npj Precis. Oncol. 8 , 23 (2024). 10.1038/s41698-024-00517-w PMC10828509 38291217

74. Westphalen, C. B. et al. ESMO Precision Oncology Working Group recommendations on the structure and quality indicators for molecular tumour boards in clinical practice. Ann. Oncol. 36 , 614–625 (2025). 10.1016/j.annonc.2025.02.009 40194904

75. Advancing Precision Medicine for Europe’s Cancer Patients with AI-Powered Imaging Joint Statement https://eosc4cancer.eu/ .

76. Sebastian, A. M. & Peter, D. Artificial intelligence in cancer research: trends, challenges and future directions. 12 , 1991 10.3390/life12121991 (2022). 10.3390/life12121991 PMC9786074 36556356

77. Sarvepalli S Vadarevu S Role of artificial intelligence in cancer drug discovery and development Cancer Lett. 2025 627 217821 10.1016/j.canlet.2025.217821 40414522 Sarvepalli, S. & Vadarevu, S. Role of artificial intelligence in cancer drug discovery and development. Cancer Lett. 627 , 217821 (2025). 40414522 10.1016/j.canlet.2025.217821