A New York company dedicated to using machine learning to harness our understanding of medical data has announced the development of a new program to help predict mesothelioma patients’ survival and response to treatment. According to an article published in the journal Nature Medicine, the company’s artificial intelligence program successfully identified patient characteristics found in biopsy slides that were specifically linked to overall prognosis.
Goal is identifying best treatment plan
Owkin’s CEO Thomas Clozel explained the goal of the research, saying, “Patients with mesothelioma exhibit a very high variability in survival, from a few months to a few years, and this makes it challenging for doctors to plan treatment and to care for these patients.” In trying to solve for this problem, the company scanned nearly three thousand tissue samples taken from mesothelioma patients and created a deep learning program that picked out biological features and linked them to proven outcomes.
Clozel says that the mesothelioma research provides an explanation for differences in mesothelioma patient prognosis and reaction to different therapies, and will eventually “lead to the development of more targeted drugs and better management of this terrible disease.” The program they have developed is being called MesoNet.
Research was collaborative effort
In pursuing the program’s development, Owkin collaborated with the mesothelioma database known as Mesobank, which stores both tissues and cell lines from previous patients. The results of the MesoNet program testing were confirmed by pathologists from the Centre Leon Berard cancer institute in Lyon, France, who said that its results were far superior to any existing modeling being used.
In addition to providing accurate prognostic results, the program provided visual highlights that pathologists will be able to use in the future when working with mesothelioma patients. Speaking of this valuable new tool, professor of pathology Francoise Galateau said, “As well as improving our prognostic models, MesoNet was able to identify new biomarkers within the stromal regions of the tumor microenvironment that were predictive of survival.”
If you have been diagnosed with malignant mesothelioma, you know the importance of scientific research to finding a cure. For more information on treatments available to you, contact the Patient Advocates at Mesothelioma.net at 1-800-692-8608.
