Using these scans, they trained the AI system to create an algorithm for identifying changes in the lung-cancer lesion. (Photo Credit: File Photo)
Researchers have developed a novel artificial intelligence (AI) based method to determine which lung-cancer patients may benefit from an expensive treatment called immunotherapy, an advance that may help reduce health care costs for underprivileged cancer patients. The study, published in the journal Cancer Immunology Research, noted that the AI system can assess the scans taken when lung cancer is first diagnosed in a patient, and compare it to scans taken after the first 2-3 cycles of treatment to find changes.
The researchers, including those from the Case Western Reserve University in the US, used an X-ray imaging equipment called a CT scan to probe into tissue samples from 50 patients.
Using these scans, they trained the AI system to create an algorithm for identifying changes in the lung-cancer lesion.
The researchers said currently only about 20 per cent of all cancer patients benefit from immunotherapy -- which is a treatment that uses drugs to help one's own immune system to fight cancer, as opposed to chemotherapy drugs which directly target and kill cancer cells.
"Even though immunotherapy has changed the entire ecosystem of cancer, it also remains extremely expensive--about $200,000 per patient, per year," said study co-author Anant Madabhushi from the Case Western Reserve University.
"That's part of the financial toxicity that comes along with cancer and results in about 42 per cent of all new diagnosed cancer patients losing their life savings within a year of diagnosis," he added.
Madabhushi said the new tool can do a better job of matching up which patients will respond to immunotherapy, "instead of throwing $800,000 down the drain".
According to the researchers, one of the significant advances in the research was the AI tool's ability to spot the changes in texture, volume and shape of a cancer lesion, not just its size -- which they said is often the only parameter used by doctors to identify cancerous growths.
The scientists said the results were consistent across scans of patients treated at two different sites, and with three different types of immunotherapy drugs.