New Frontiers in 2025: Advancing Patient-Centered Cancer Care and Health Equity With AI

As 2025 kicks off, AI is continuing to revolutionize patient care, clinical trials, and health equity in new ways. One such way is the use of AI for clinical trial matching, including recent innovations that showcase AI’s potential to streamline complex processes and achieve near-human accuracy while democratizing access to life-saving trials. In this edition of his Fellows Forum Blog, Dr. Waqas Haque, Hematology/Oncology Fellow at the University of Chicago, explores these breakthroughs and provides oncology fellows with insights into how AI is reshaping cancer care delivery and research.

2024: A Transformative Year for AI

AI in oncology had a transformative year in 2024. Beyond traditional academic publications, we covered how a new wave of physician thought leaders like Dr. Eric Topol of Scripps Research are actively shaping the AI/oncology discourse through their influential social media presence, and Substacks, offering real-time analysis of emerging developments and providing nuanced perspectives on how these technologies could realistically transform cancer care delivery.

A big focus of our own AI and technology blog is to maintain focus on patient-centered outcomes and health equity. Dr. Doug Flora, Executive Medical Director of Oncology at St. Elizabeth Healthcare and Head Editor of AI in Precision Oncology, recently kicked off his blog with an analysis of the top 10 AI/oncology developments last year. The list was headlined by Demis Hassabis, John Jumper, and the DeepMind team winning the Nobel Prize in Chemistry for their groundbreaking work with AlphaFold, marking the first Nobel recognition of AI’s impact in biomedical science.

Clinical Trial Matching With AI

At #7 on Flora’s list was the revolution in clinical trial matching through AI, a domain historically fraught with inertia and inefficiency—40% of cancer clinical trials fail to enroll a single patient, and only 3% to 5% meet their recruitment targets on time. Medical terms like “randomized” and “double blind” can be difficult for patients who find health information hard to understand. These challenges persist despite projections showing that US cancer cases are expected to reach 2.3 million annually by 2030.

TrialGPT represents a paradigm shift in clinical trial matching, moving beyond traditional eligibility criteria matching systems to a more patient-centric approach. Unveiled in early 2023 through a collaboration between medical AI researchers and oncologists, TrialGPT operates by allowing patients to describe their medical situation in everyday language, then generates an eligibility score along with detailed explanations for each trial criterion. In validation studies, the system demonstrated performance comparable to human clinical trial coordinators while reducing screening time by over 40%.

Figure: The overall architecture of TrialGPT. Jin Q, Wang Z, Floudas CS, et al (2024). Matching patient to clinical trials with large language models. Nature Comm, 15(9074). DOI:10.1038/s41467-024-53081-z

This sort of breakthrough sparked broader industry and academic interest, exemplified by Dana-Farber Cancer Institute’s partnership with Meta in October 2023 to develop an open-source platform using Llama 3 for analyzing unstructured clinical notes. In a study of non–small cell lung cancer trials, GPT-3.5 achieved 95% accuracy in zero-shot scenarios and perfect accuracy with 80-case training when evaluated against human epidemiologists’ assessments.

Similarly, TrialGPT showed impressive performance across its three-module system: its retrieval module successfully identified over 90% of relevant trials while examining less than 6% of the available trial pool, and its matching module achieved 87.3% accuracy in criterion-level eligibility assessment—approaching expert-level performance. The system demonstrated practical efficiency gains, reducing screening time by 42.6%.

A separate Stanford Medicine study developed a zero-shot LLM system that processes unstructured clinical notes, generating interpretable justifications that clinicians found coherent in 97% of correct decisions. These developments mark a shift in clinical trial matching—from a process historically dependent on manual screening and rigid inclusion/exclusion criteria, to one that leverages AI to understand and interpret patient contexts more naturally and efficiently. These consistent results across multiple studies are mirrored by several commercial solutions to patient-to-trial matching through various innovative approaches:

Trial Navigator, developed by Inspirata, combines AI and natural language processing (NLP) to analyze clinical data and match cancer patients to trials. In a retrospective analysis, the platform successfully identified appropriate biomarker-driven and tumor-specific trials for 90% of pre-selected patients, suggesting its potential to enhance recruitment for early-phase oncology studies
The Trialjectory platform employs unsupervised NLP and AI to analyze patient data collected through digital questionnaires. Performance testing showed 90% sensitivity and 95% specificity in trial matching, with the system successfully identifying at least one potential trial match for virtually all patients (99.9% success rate)
“Explainable AI for Phase I Oncology Trials” (the explanation is in the name) leverages advanced natural language processing to evaluate patient records against trial protocols. The system demonstrated strong performance metrics, achieving 73.68% precision in matching patients to trials while maintaining 89.36% specificity

Figure: Utilizing oncology-specific NLP AI to interrogate individual medical reports and trial inclusion and exclusion criteria through Trial Navigator. Available at: https://www.globenewswire.com/en/news-release/2021/07/13/2261633/0/en/Inspirata-Partners-with-King-s-Health-Partners-ECMC-and-Guy-s-and-St-Thomas-NHS-Foundation-Trust-to-Evaluate-the-Application-of-AI-Automation-in-Matching-Patients-with-Cancer-to-Ea.html

Analyzing the Approach

How exactly does AI improve clinical trial matching? The most effective systems employ a multilayered approach that combines several AI technologies. At the foundation, NLP engines interpret unstructured clinical notes and eligibility criteria, while knowledge graphs map complex relationships between medical concepts, conditions, and treatments. These are augmented by deep learning models, particularly transformer-based architectures like BERT, which have demonstrated over 85% accuracy in patient-trial matching.

The true power emerges when these technologies work in concert—for example, IBM’s Watson combines NLP with rules-based systems to reduce screening time by 78%, while modern hybrid solutions simultaneously process structured data like lab values, apply semantic matching for medical terminology, and enforce explicit inclusion/exclusion rules. This multimodal approach enables the technology to mirror how human coordinators evaluate trial eligibility: understanding patient context, interpreting complex medical relationships, and applying specific trial criteria, but at a much larger scale and faster pace.

Conclusion

In summary, the convergence of AI and oncology trial matching represents one of the most promising developments in cancer care delivery (even if it only takes home the bronze medal on Dr. Flora’s list). While early systems focused on basic eligibility matching, today’s AI platforms like TrialGPT and Trial Navigator demonstrate near-human accuracy while significantly reducing screening time, suggesting a future where trial access becomes more democratic and efficient. As platforms consistently demonstrate 85% to 95% accuracy rates across different trial types, we’re witnessing a fundamental transformation where finding a potentially life-saving clinical trial is just a click away.

About Dr. Haque

Waqas Haque, MD, MPH, is a Hematology/Oncology Fellow at the University of Chicago. He recently completed his Internal Medicine Residency at New York University (NYU) in a Clinical Investigator Track. Dr. Haque has balanced his patient care work with a variety of research projects. During his fellowship training at the University of Chicago, he plans to further his work in innovative clinical trial design, value-based care delivery to cancer patients, and clinical investigation.