The featured image was bought on Istock.com. Copyrights.
In 2017, approximately 26,300 women and 230 men were diagnosed with breast cancer in Canada. For women, this represented 25% of all new cancer cases . When caught early, the chances of curing cancer are higher. For breast cancer, mammograms are the best test available. However they are not perfect. They often produce false positive results that can lead to unnecessary biopsies, surgery, radiation and even chemotherapy. One of the common causes of false positives are called “high-risk” lesions that appear suspicious on mammograms and show abnormal cells when tested by needle biopsy. The term high-risk breast lesion is given to a breast lesion that carries an increased risk for the future development of breast cancer or suspicion of a more sinister pathology around or in association with the lesion . In this case, the patient typically undergoes surgery to have the lesion removed. In the United States, a third of patients with breast cancer detected by a mammogram receives unnecessary treatment .
When a suspicious lesion is detected on a mammogram, a needle biopsy is performed to determine if the lesion is cancerous. Roughly 70 percent of the lesions are benign, 20 percent are malignant, and 10 percent are high-risk lesions . The treatment depends on the doctors; some do surgery in all cases, while others perform surgery only for lesions that have higher cancer rates, such as “atypical ductal hyperplasia” (ADH) or “lobular carcinoma in situ” (LCIS). The first approach requires that the patient undergo a painful, time-consuming, and expensive surgery that is usually unnecessary; the second approach is imprecise and could result in missing cancers in high-risk lesions other than ADH and LCIS.
To improve detection and diagnosis of breast cancer, Researchers at the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts General Hospital, and Harvard Medical School collaborated to develop an AI system that uses machine learning to predict if a patient will have to go through surgery when a high-risk breast lesion is identified by needle biopsy after a mammogram.
The algorithm was trained on more than 600 existing high-risk breast lesions and searched patterns among many different data elements such as demographics, family history, past biopsies, and pathology reports. The program was tested with 335 high-risk breast lesions and correctly diagnosed 97 percent of the breast cancers as malignant, while reducing the number of benign surgery by more than 30 percent compared to today’s methods .
Chatbots Health Assistant
Chatbots are also used as health assistants. They can be compact medical reference books for those who want to learn more about health or can even be a “friend” that reminds you to take your medication. A French startup called WeFight recently launched Vik Sein, a new artificial intelligence companion dedicated to help patients and their family affected by breast cancer.
Vik chats in French with patients, via Facebook Messenger, to answer questions and concerns, and to provide advice and recommendations on the disease. All the information is validated by a team of health professionals. Integrating Vik in the care journey reduces costs of managing cancers by improving the quality of life of patients, promoting safe treatment at home, and strengthening the relation with their caregivers.
Marie-Anne Valiquette obtained a Bachelor's degree in Mechanical Engineering at the École de technologie supérieure (ÉTS) in Montreal. She lives in Silicon Valley, California where she studies artificial intelligence through online platforms like Udacity and deeplearning.ai.
Program : Mechanical Engineering