Researchers from Cleveland Clinic developed a machine learning tool that predicts whether cancer immunotherapy drugs will be effective for patients, according to a Nov. 1 study published in Nature Biotechnology.
Four things to know:
- For the study, researchers tested the tool in 1,479 patients treated with immune checkpoint blockade across 16 different cancer types. The artificial intelligence-powered tool looks at biological and clinical factors specific to the patient to predict how different types of cancers will respond to the drug treatment, according to a Nov. 3 news release.
- Oncologists can use the tool to discern which patients the immune checkpoint blockade will be effective on, reducing patients' exposure to unnecessary side effects and medical expenses. Immune checkpoints are proteins specific to immune cells that prevent immune responses from destroying healthy cells when activated. Some cancer cells are able to activate the checkpoints and disguise themselves to avoid being targeted by the immune system. The immunotherapy drugs prevent cancer cells from inappropriately activating these checkpoints.
- While these drugs have the potential to help patients, at least half of patients who are treated with immunotherapy drugs do not benefit from them. In the study, the tools outperformed two FDA-approved forecasting tools, according to the release. The study also found that the tool performs well regardless of which form of cancer it is.
- Timothy Chan, MD, PhD, director of Cleveland Clinic's Center for Immunotherapy and Precision Immuno-Oncology, who worked with researchers to develop the tool, said: "It's important to know which treatment modalities patients are most suited for. Our model provides a more comprehensive understanding of the diversity of responses among patients to immune checkpoint blockade. It's the first to assemble such a large-scale set of clinical and genomic variables that have predictive value for immunotherapy across numerous cancer types."