Image Credit: © Kaikoro – stock.adobe.com
A new study led by Winship Cancer Institute of Emory University and Abramson Cancer Center of University of Pennsylvania researchers on the effectiveness of the emerging artificial intelligence (AI) clinical trial solution, TrialTranslator, has been published in Nature Medicine. The authors demonstrated the solution’s ability in helping clinicians and patients assess how much an individual patient may benefit from a particular therapy being tested in a clinical trial.1
The study was led by board-certified medical oncologist Ravi B. Parikh, MD, MPP, medical director of the Data and Technology Applications Shared Resource at Winship Cancer Institute of Emory University and associate professor in the Department of Hematology and Medical Oncology at Emory University School of Medicine. The co-author is Qi Long, PhD, a professor of biostatistics, and computer and information science, and founding director of the Center for Cancer Data Science at the University of Pennsylvania, and associate director for quantitative data science of the Abramson Cancer Center of Penn Medicine.
Alongside his fellow researchers, Parikh developed TrialTranslator, which is a machine learning (ML) framework that can translate clinical trial results to real-world populations.
In a press release, Parikh said, “We hope that this AI platform will provide a framework to help doctors and patients decide if the results of a clinical trial can apply to individual patients. Furthermore, this study may help researchers identify subgroups in whom novel treatments do not work, spurring newer clinical trials for those high-risk groups.”
Long added, “Our work demonstrates the enormous potential of leveraging AI/ML to harness the power of rich, yet complex real-world data to advance precision medicine at its best.”
Titled, “Evaluating generalizability of oncology trial results to real-world patients using machine learning-based trial emulations,” the study used a nationwide database of electronic health records (EHR) from Flatiron Health to emulate 11 clinical trials that investigated anticancer regimens considered standard of care across non-small cell lung cancer, metastatic breast cancer, metastatic prostate cancer, and metastatic colorectal cancer.
Following their analysis, the authors found that patients with low- and medium-risk phenotypes had survival times and treatment-associated survival benefits similar to those who were observed in the trials. On the other hand, patients with high-risk phenotypes showed significantly lower survival times and treatment-associated survival benefits.
“These findings highlight the potential of frameworks such as TrialTranslator, which integrates EHR-derived datasets, ML-based phenotyping and trial emulation, to translate oncology randomized clinical trial results to individual patients,” the study authors wrote of their findings. “Such tools can support clinicians and patients in making informed treatment decisions, understanding expected benefits of novel therapies and planning future care.”2
Overall, the results of the study suggest that patient prognosis better predicts survival and treatment benefit rather than eligibility criteria. Additionally, the authors recommend that trials should use more sophisticated ways of evaluating patients’ prognosis rather than relying solely on eligibility criteria.
In the previously mentioned press release, Parikh added, “Soon, with appropriate oversight and evidence, there will be an increasing tide of AI-based biomarkers that can analyze pathology, radiology or electronic health record information to help predict whether patients will or will not respond to certain therapies, diagnose cancers earlier or result in better prognoses for our patients.”
References
1. New AI platform identifies which patients are likely to benefit most from a clinical trial. News release. Emory Health Sciences. Winship Cancer Institute of Emory University. January 8, 2025. Accessed January 10, 2025. https://www.eurekalert.org/news-releases/1069923
2. Orcutt, X., Chen, K., Mamtani, R. et al. Evaluating generalizability of oncology trial results to real-world patients using machine learning-based trial emulations. Nat Med (2025). https://doi.org/10.1038/s41591-024-03352-5.