Endometrial cancer affects 48,000 women per year in the United States. For patients with tumors greater than two centimeters in diameter, the effected organ(s) and lymph nodes may be surgically removed. Yet post-surgery analysis shows that only 22 percent of patients had metastasis, meaning 78 percent of these surgeries may have been unnecessary. How can doctors predict which patients need surgery?
Mathukumalli Vidyasagar discusses how new computational algorithms from National Science Foundation-sponsored research have been successfully applied to cancer data in a clinical translational setting. One such algorithm can predict the time to tumor recurrence in ovarian cancer patients and has been shown to predict the efficacy levels of several natural product compounds on lung cancer cells. This cutting-edge research in machine learning and computational algorithms has the potential to transform clinical practice and personalized cancer treatment therapies.
Vidyasagar is the Cecil & Ida Green Chair in Systems Biology Science in the Erik Jonsson School of Engineering & Computer Science at the University of Texas at Dallas. He has received a number of awards in recognition of his research contributions, including Fellowship in The Royal Society, the IEEE Control Systems (Field) Award, and the Rufus Oldenburger Medal of ASME.