Determining which cancer patients are a good candidate for immune checkpoint inhibitors can be a challenge, but researchers at Mount Sinai and Memorial Sloan Kettering Cancer Center have developed a promising tool to predict which patients will respond well to the therapy.
The tool, an artificial intelligence-based model called SCORPIO, uses routine blood tests to predict treatment success. Researchers developed and validated the model based on data from nearly 10,000 patients across 21 cancer types. It is the first tool capable of predicting patients' response to immune checkpoint inhibitors based on basic clinical data, according to the researchers. The study, which was published in Nature Medicine, also found the tool's predictive ability was better than FDA-approved biomarkers.
Immune checkpoint inhibitor drugs, which enhance the immune system's ability to attack cancer cells, have revolutionized the precision oncology landscape. Spending on these therapies in the U.S. soared from $2.8 million to $4.8 billion between 2011 and 2021, according to CMS data. However, clinicians primarily rely on genetic or immune system analysis tests to predict which patients may benefit from the therapies, which can be costly and inefficient.
"SCOPRIO changes that by using routine blood tests that doctors already use to monitor their patients," Diego Chowell, PhD, lead study author and assistant professor at Mount Sinai's Icahn School of Medicine, said in a Jan. 6 news release. "This makes predicting treatment success faster, simpler, more accurate and more affordable."
Researchers are now partnering with hospitals and cancer centers to validate the tool in diverse clinical environments and refine it based on real-world feedback.