Researchers have demonstrated that a novel artificial intelligence (AI)-based platform could aid physicians and patients in assessing the benefit from a particular therapy being tested in a clinical trial, according to a recent study published by Orcutt et al in Nature Medicine. The AI platform may help with making informed treatment decisions, understanding the expected benefits of novel therapies, and planning future care.
Background
Clinical trials of potential novel treatments may be limited because less than 10% of all patients with cancer participate in a clinical trial. As a result, clinical trials do not often represent all patients with that cancer type. Even if a clinical trial shows a novel treatment strategy has better outcomes than the standard of care, there are many patients in whom the novel treatment may not be effective.
Study Methods and Results
In the study, the researchers developed TrialTranslator, a machine-learning framework designed to translate clinical trial results to real-world populations. By emulating 11 landmark cancer clinical trials using real-world data, they were able to recapitulate actual clinical trial findings, thereby enabling them to identify which distinct groups of patients may respond well to treatments in a clinical trial and which groups may not.
The researchers used a nationwide database of electronic health records from Flatiron Health to emulate 11 landmark randomized controlled trials that investigated anticancer regimens considered standard of care for the four most prevalent advanced solid malignancies in the United States: advanced non–small cell lung cancer, metastatic breast cancer, metastatic prostate cancer, and metastatic colorectal cancer.
They revealed that patients with low- and medium-risk phenotypes—which are machine learning–based traits used to assess the underlying prognosis of a patient—had survival times and treatment-associated survival benefits comparable to those who were observed in the randomized controlled trials. In contrast, those with high-risk phenotypes showed lower survival times and treatment-associated survival benefits compared with those in the randomized controlled trials.
“This framework and our open-source calculators will allow patients and [physicians] to decide whether results from phase III clinical trials are applicable to individual patients with cancer,” explained co–senior study author Ravi B. Parikh, MD, MPP, FACP, Associate Professor in the Department of Hematology and Medical Oncology at the School of Medicine and Medical Director of the Data and Technology Applications Shared Resource at the Winship Cancer Institute at Emory University. “[T]his study offers a platform to analyze the real-world generalizability of other randomized trials, including trials that have had negative results,” he continued.
Conclusions
Their findings indicated that machine learning can identify groups of real-world patients in whom randomized controlled trial results are less generalizable.
“[R]eal-world patients likely have more heterogeneous prognoses than randomized controlled trial participants,” the study authors noted. “[The study] suggested that patient prognosis, rather than eligibility criteria, better predicts survival and treatment benefit,” they emphasized.
The researchers recommend that prospective trials “should consider more sophisticated ways of evaluating patients’ prognosis upon entry, rather than relying solely on strict eligibility criteria.”
Further, they cited recommendations by ASCO and Friends of Cancer Research that efforts should be made to improve the representation of high-risk subgroups in randomized controlled trials, “considering that treatment effects for these [patients] might differ from other participants,” the study authors underlined.
“We hope that this AI platform will provide a framework to help [physicians] and patients decide if the results of a clinical trial can apply to individual patients,” emphasized Dr. Parikh. “Furthermore, this study may help researchers identify subgroups in whom novel treatments do not work, spurring newer clinical trials for those high-risk groups,” he added.
“Our work demonstrates the enormous potential of leveraging AI/[machine learning] to harness the power of rich, yet complex real-world data to advance precision medicine at its best,” highlighted co–senior study author Qi Long, PhD, Professor of Biostatistics and Computer and Information Science and Founding Director of the Center for Cancer Data Science at the University of Pennsylvania as well as Associate Director for Quantitative Data Science at the Abramson Cancer Center at Penn Medicine.
“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,” Dr. Parikh concluded.
Disclosure: The research in this study was supported by grants from the National Institute of Health. For full disclosures of the study authors, visit nature.com.
