Now Artificial Intelligence will Anticipate the Recurrence of Breast Cancer

These new artificial intelligence model can soon do wonders in the health space

Artificial Intelligence

Artificial Intelligence

Did you know that nearly 59,000 new cases annually are observed concerning breast cancer, which surpasses lung and colorectal cancers? It is also cancer that results in the greatest number of deaths in women. But these cancers are heterogeneous as about 20% of patients will relapse with distant metastasis. The RACE AI study that was conducted by Gustave Roussy along with a start-up called Owkin, as part of the AI for Health Challenge organized by the lle-de-France Region in 2019, was presented as a proffered paper at the European Society of Medical Oncology or ESMO. The study shows artificial intelligence can classify patients with localized breast cancer into high and low-risk categories in the next five years.  

This new model with the use of Artificial Intelligence can also become a help to the therapeutic decision making, thereby can avoid unnecessary chemotherapy that can have an impact on the personal, social and professional lives of women who are at a low risk for breast cancer. This becomes the first proof of concept illustrating the power of an artificial intelligence model for identifying and recognizing the associated parameters with relapse that the human brain cannot detect. 

While coming to the RACE AI, it is a retrospective study that was conducted on a cohort of 1400 patients who were managed at Gustave Roussy from 2005 to 2013 for localized hormone-sensitive breast cancer. And then these women are treated with radiotherapy, surgery, hormone therapy, and chemotherapy to reduce the risk of distant relapse. 

As chemo is not administered regularly as not all women will receive the benefit from it due to a naturally favorable prognosis. The practitioner’s choice is based on the clinicopathological criteria such as age, size of the tumor, lymph node invasion etc. with this decision to administer or not to adjuvant chemotherapy varies between various oncology centers. Most of the genomic signatures exist today to help locate women who can get help from chemotherapy, but they are not recommended by the French National Authority for Health and are also reimbursed by the French National Health Insurance that makes their access and use heterogeneous in France. 

Both Gustave Roussy and Owkin took this up as a challenge and thought of proposing a new method that can be simple and inexpensive to use in all oncology centers as a therapeutic decision-making tool. The goal is to direct patients identified as being high risk towards new innovative therapies and to avoid unnecessary chemotherapy for low-risk patients. 

In the RACE AI study, Owkin’s Data Scientists that were guided by Gustave Roussy’s research physicians came up with an AI model capable of reliably assessing the risk of relapse with an AUC of 81% to help the practitioner determine the benefit or risk balance of chemotherapy. This calculation is based on the patient’s clinical data combined with the analysis of stained and digitized histological slides of the tumor. 

Coming up with a new technique or to equip a specific technical platform, the only essential equipment is the slide scanner which is a common piece of equipment in laboratories. The results are exciting as the first study by the Owkin and Gustave Roussy teams open up strong prospects and the next steps include prospectively validating the model on an independent cohort of patients treated outside Gustave Roussy. If the results are confirmed, through providing reliable information to clinicians, this Artificial Intelligence tool proves to be a valuable aid to therapeutic decisions.