Machine learning has been used to identify an inflammatory “signature” that points to a risk of failure of CAR-T therapy, it has been announced.
The machine learning model has been able to analyse markers of inflammation in the blood and make powerful predictions of the outcome of treatment, according to a report in Nature Medicine.
The project, undertaken primarily at Memorial Sloan Kettering Cancer Centre in New York, involved training the machine learning system with results from blood samples of 149 patients with non-Hodgkin’s lymphoma.
The model, known as InflaMix, identified an inflammatory signature found to be linked to a high risk of CAR T therapy failure. This was then tested on three independent groups of 688 patients.
The researchers say the model is flexible, as it worked well even when only six blood markers were available.
Dr Marcel van den Brink, co-leader of the study from City of Hope National Medical Centre, Los Angeles, said: “These studies demonstrate that by using machine learning and blood tests, we could develop a highly reliable tool that can help predict who will respond well to CAR T cell therapy.
“With a rigorous statistical approach, we demonstrated that this is one of the most thoroughly validated tests we have for predicting CAR T outcomes in lymphoma patients and could be used by oncologists everywhere to assess the risk of CAR T in an individual patient.”
Dr van den Brink added: “InflaMix could be used to reliably identify patients who are about to be treated with CAR T and are at high risk for the treatment not working. By identifying these patients, doctors may be able to design new clinical trials that can boost the effectiveness of CAR T with additional treatment strategies.”
Source:
Raj SS, Fei T, Fried S, Ip A, Fein JA, Leslie LA, Alarcon Tomas A, Leithner D, Peled JU, Corona M, Dahi PB, Danylesko I, Epstein-Peterson Z, Funnell T, Giralt SA, Jacoby E, Kedmi M, Landego I, Lin RJ, Parascondola A, Pascual L, Orozco N, Park JH, Palomba ML, Salles G, Saldia A, Schöder H, Sdayoor I, Shah GL, Scordo M, Shem-Tov N, Shimoni A, Slingerland J, Yerushalmi R, Nagler A, Greenbaum BD, Vickers AJ, Suh HC, Avigdor A, Perales MA, van den Brink MRM, Shouval R. (2025) “An inflammatory biomarker signature of response to CAR-T cell therapy in non-Hodgkin lymphoma.” Nature Medicine, 1 April 2025, doi: 10.1038/s41591-025-03532-x.
Link: https://www.nature.com/articles/s41591-025-03532-x
Disclaimer: The news stories shared on this site are used as a way to inform our members and followers of updates and relevant information happening in Haematology. The BSH does not endorse the content of news items from external sources, and is not in a position to verify the findings, accuracy or the source of any studies mentioned. Any medical or drugs information is provided as an information resource only, and is not to be relied on for any diagnostic or treatment purposes.
News service provided by Englemed News.