ASCO: Concerto HealthAI uses real-world data to fill the research gap among patients excluded from NSCLC trials

Through its real-world evidence collaboration with the FDA and the American Society of Clinical Oncology’s (ASCO's) CancerLinQ data repository, Concerto HealthAI has helped provide a peek into the performance of immune checkpoint inhibitors among a population of cancer patients who are frequently excluded from clinical trials.

A series of four abstracts presented at ASCO’s annual meeting in Chicago explored patients with preexisting autoimmune disorders being treated with the immune-targeting therapies, including those with advanced non-small cell lung cancer (NSCLC).

“By combining Concerto’s analytic capabilities with FDA’s vision and CancerLinQ’s medical informatics expertise, we help address deficits in the external validity of clinical trials by revealing how ICIs have been used since their introduction in 2011 in patients with a wide variety of cancers, and show the interplay between autoimmune disease, immune-related adverse events and efficacy,” lead author Wendy Rubinstein, CancerLinQ’s deputy medical director, said in a statement.

The abstracts cover a retrospective analysis of more than 12,000 treated patients from a de-identified CancerLinQ data set, detailing their characteristics, demographics and outcomes. In one study of about 2,400 patients with advanced NSCLC, about 22% had demonstrated evidence of an autoimmune disease in the year before starting cancer treatment with a checkpoint inhibitor.

With a median overall survival (OS) of 12.4 months across all patients, there were no statistically significant differences in OS between the two groups. In addition, there were no associations between autoimmune status and real-world progression-free survival or the time to discontinuation of treatment and the start of subsequent therapies.

However, while there was no increase in the incidence of adverse events, a subanalysis did show higher rates of selected events such as endocrine, gastrointestinal and blood disorders.

Another study showed that, in the real world, advanced NSCLC patients receiving checkpoint therapies are older than what was reported in some clinical trials, though survival outcomes were comparable. Researchers said further study is needed to examine the effects of autoimmune disease on treatment results as well as on the risk of adverse events.

RELATED: Concerto HealthAI signs on with Pfizer to apply real-world data to precision cancer medicine

Concerto also presented a new artificial intelligence model at the ASCO meeting for predicting the survival of lung cancer patients, aimed at expediting clinical development.

Derived from de-identified, real-world data from about 55,000 patients in the CancerLinQ database, the model weighs nearly 4,000 unique variables—including biomarkers, diagnostic codes, surgeries and test results—to estimate the survival of patients in the three months to a year following their most recent clinical visit.

“A model that can accurately predict risk of mortality in patients at various time points could help guide clinical development teams to more effectively select attributes of patients for different pre- and post-approval studies to bring needed new therapies forward and enhance the effectiveness of existing therapies respectively,” said Concerto’s Smita Agrawal, senior director of product management.

“There are enormous costs associated with every patient recruited into a clinical trial,” said Concerto CEO Jeff Elton. “Researchers can now determine with a high degree of confidence which patients are expected to survive the next three months and recruit accordingly to ensure a successful clinical trial at a faster pace.”