Scientists can now determine which lung cancer patients will benefit from the expensive immunotherapy. They have previously used AI to determine the type of lung cancer. Now, according to the study published in Journal, Cancer Immunology Research, AI could predict if immunotherapy will be working on the patient or not.
The new research was led by Mohammadhadi Khorrami and Prateek Prasanna, along with Madabhushi and 10 other collaborators from six different institutions. The team has developed a new artificial intelligence model to allow healthcare practitioners to find which lung cancer patients would benefit the most from immunotherapy.
They used CT scans from 50 patients to train the computer and create a mathematical algorithm to identify the changes. They are doing the research by teaching computer to find previously unseen changes in patterns in CT scans taken on first diagnose of the disease and then comparing scans to those after 2-3 cycles of immunotherapy treatment. The researchers were able to show the patterns on CT scans which were most associated with a positive response to treatment and with overall survival rates of patients. Using these scans, they trained the AI system to create algorithm for identifying changes in lung cancer lesion.
According to the researchers, only 20% of all cancer patients benefit from immunotherapy. The results provided by the scientists were consistent across scans of patients treated at two different sites and with different types of immunotherapy drugs.
“Even though immunotherapy has changed the entire ecosystem of cancer,” explains study co-author Anant Madabhushi, “it also remains extremely expensive — about $200,000 per patient, per year. Madbhushi also notes that the new tool he and his team are working on may help doctors to decide which therapy suits them the best and also help to avoid unnecessary expenses.
The information shared in this blog is for educational purposes only.