Project 459000

Of the female reproductive system cancers, ovarian cancer is the deadliest, with a five-year survival rate of less than 50%. Most people with ovarian cancer are diagnosed at a late stage because of vague symptoms and a lack of effective screening practices. Therefore, the prevention of ovarian cancer is a clear target to reduce deaths from the disease. While surgical removal of the ovaries has the highest prevention rate, this is not recommended for the general population due to early menopause and fertility concerns. Recent evidence shows that most ovarian cancers start in the fallopian tube rather than the ovary itself. Opportunistic salpingectomy is the removal of the fallopian tubes at the time of another surgery in the pelvis, such as removing the uterus (hysterectomy) or for sterilization procedures such as tubal ligation. Opportunistic salpingectomy is safe and cost-effective with a very low surgical complication rate. It is also highly effective in preventing the most lethal ovarian cancers. However, with decreasing number of hysterectomies and tubal ligations, we will miss the opportunity to prevent ovarian cancer in many people. We know of many risk factors that increase the risk of ovarian cancer. We also have a provincial data set that includes many of these risk factors that could be used to predict the lifetime risk of ovarian cancer. However, no one has developed a risk prediction model to identify those who could benefit from opportunistic salpingectomy, even without another surgery. We will use machine learning, an arm of artificial intelligence, to create a prediction model to identify people who could benefit from opportunistic salpingectomy. We will also conduct interviews with patients and doctors to understand better if this emerging technology is acceptable. This research has the potential to significantly reduce deaths from ovarian cancer by predicting and preventing ovarian cancer with opportunistic salpingectomy.