Aug 2026· Nature Reviews Clinical Oncology· 0 citations· 133 references
Medicine
TL;DR
It is argued that achieving the potential of AI in oncology clinical trials will require rigorous prospective validation, harmonized regulatory standards, and coordination among clinicians, trialists, regulators, industry and patients.
TrialGPT 2.0 is presented, an AI-assisted clinical trial recommendation system designed for real-world deployment that improves clinician efficiency and identifying frequently overlooked trial opportunities, ultimately helping to expand and accelerate accrual to cancer trials.
Yin Fang, Qiao Jin, Shubo Tian et al.· 0 citations
Clinical trials are essential for developing new cancer treatments and improving patient care. However, participation remains low across oncology and is particularly challenging for people with pancreatic cancer, who often experience rapid disease progression, limited treatment options, and short timeframes for trial enrolment. In this Review, we examine the factors that limit clinical trial participation in pancreatic cancer, including patient identification and referral, eligibility assessment, molecular testing, and trial delivery. We discuss how restrictive eligibility criteria, inconsistent integration of trial processes into routine care, variability in molecular testing, and logistical barriers reduce opportunities for participation. We also consider practical strategies to improve access, including earlier and more systematic trial identification, broader clinical eligibility criteria, timely molecular testing, more flexible trial designs, and decentralised models of care. Improving participation will require coordinated changes across clinical pathways, trial design, and healthcare systems to ensure that trial availability translates into equitable patient access. Thang et al. review the barriers to clinical trial participation in pancreatic cancer across the patient pathway, from referral to enrolment. They identify coordinated improvements in referral, molecular testing, eligibility criteria, trial design, and delivery as key strategies to improve equitable access to clinical trials.
Sue-Sien Thang, Daniel Croagh, Sumitra S. Ananda et al.· Communications Medicine· 0 citations
This review synthesizes key developments in ML for oncology, covering foundational algorithms alongside emerging approaches, and describes future directions, including federated learning, graph neural networks, longitudinal modeling, and integration of real-world and wearable data to support precision oncology.
Kanishk Yadav, Taneesha Gupta· Journal of the Egyptian Nati...· 0 citations
Progress in neuro-oncology drug development has been slower than the pace of biological discovery, and trial design is increasingly recognized as a central contributor to this gap. Traditional trial paradigms, largely developed for systemic malignancies, face distinct challenges when applied to central nervous system (CNS) tumors - among them intratumoral heterogeneity, rapid clinical progression, limited tissue access, and the evolving molecular classification of gliomas. These biological and logistical realities have strained the assumptions underlying conventional phase II and III designs, and there is growing consensus that new approaches are needed. This review examines a framework of emerging trial models that better align clinical testing with the realities of CNS tumors. Master protocol designs enable simultaneous evaluation of multiple therapies within shared, molecularly informed infrastructures, supporting precision medicine approaches and improving efficiency. Bayesian adaptive frameworks allow trials to learn during conduct, reallocating patients toward promising therapies and incorporating emerging biological data in real time. Beyond efficacy assessment, trials can serve as active discovery platforms embedding longitudinal tissue sampling, window-of-opportunity designs, and multi-omic profiling to interrogate CNS drug penetrance, pharmacodynamic target engagement, and treatment-induced tumor evolution directly in human disease. Decentralized trial models and artificial intelligence offer additional tools to broaden access, improve enrollment, and reduce operational burden. Reimagining clinical trials as dynamic, biologically integrated, learning-based systems rather than static tests of individual agents is essential to accelerate therapeutic progress in neuro-oncology.
A. J. Wisdom, R. Rahman· Neurotherapeutics· 0 citations
Artificial Intelligence (AI) is rapidly transforming pharmaceutical research and drug development. The
traditional process of discovering and developing new medicines is time-consuming, expensive and associated with a high
rate of failure. AI, including machine learning, deep learning, natural language processing and generative AI, can analyses
large and complex datasets and assist researchers in making predictions and decisions. In preclinical research, AI can
support target identification, drug discovery, molecular screening, toxicity prediction, pharmacokinetic and
pharmacodynamics modelling, and analysis of animal and laboratory data. In clinical trials, AI can assist with protocol
design, patient recruitment, eligibility screening, clinical data management, monitoring, endpoint assessment, adverse-event
detection and prediction of trial outcomes. The U.S. Food and Drug Administration (FDA) reports increasing use of AI
across nonclinical, clinical, post-marketing and manufacturing stages of drug development. Despite these benefits, challenges
such as data quality, algorithmic bias, lack of transparency, privacy, cybersecurity, regulatory uncertainty and the need for
human oversight remain important. Therefore, appropriate validation, monitoring and risk-based regulatory approaches
are necessary for the safe and effective use of AI in pharmaceutical development.
Rajashree Somnath Chorgade, Srushti Dipak Nevase, Shubham Hanumant Dhavale et al.· International Journal of Inn...· 0 citations
This narrative review outlines the limitations of traditional evaluation frameworks and proposes a paradigm shift toward adaptive, iterative, and context-specific assessment methodologies that can progress from a promising technology to reliable clinical tools that improve patient outcomes, support clinical decision-making, and uphold ethical standards in routine practice.
M. Fosset, Joris Pensier, Boris Jung et al.· PLOS Digital Health· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
