AI model developed by Northwestern researchers could suggest better treatment plans for breast cancer patients

Mohamed Tageldin has worked at the intersection of artificial intelligence and pathology, which involves the study and diagnosis of diseases, for six years. He is a resident physician at Northwestern University’s McGaw Medical Center and is part of a research team that has developed an artificial intelligence model to predict long-term outcomes for breast cancer patients more precisely.

At a time when some industries are questioning the use of AI in daily work, those in the medical field are embracing the Technology‘s potential to support doctors. This new model, specifically designed for breast cancer, aims to provide patients with more personalized treatment recommendations and agency in their choice of treatment plans. It may also spare patients unnecessary chemotherapy treatments, according to a report published in late November.

The algorithm assesses patients differently from human pathologists and previous models by studying both cancerous and noncancerous cells in a prognosis. This comprehensive approach takes into account noncancerous cells, such as immune cells, that can impact long-term outcomes for patients. It can also provide more information and reasoning behind its predictions, addressing a main concern of AI for pathologists.

The research team used sample tissue from 3,177 breast cancer patients through a partnership with the American Cancer Society (ACS) Cancer Prevention Studies program, where people donate their cancer tissue for research. The data collected from a variety of medical clinics, including community centers in low-income and rural areas, allows the AI model to be trained on a diverse set of patient tissues.

The use of digital images in medical practice has increased in recent years, with Northwestern Medicine transitioning to digital imaging over the next three years. The AI model could potentially benefit patients in lower-income areas where it could aid doctors who are not specialized pathologists in providing grades and treatment care options.

Moving forward, researchers will need to evaluate the model using data from clinical trials, tackle operational challenges, and ensure predictions are generated on time for pathologists. If approved for clinical use, the same template could potentially be applied to other cancers as well.

Overall, the AI model aims to help doctors make more informed treatment decisions, ultimately improving the outcomes and quality of life for breast cancer patients.