The American Cancer Society estimates that nearly 2 million Americans will be diagnosed with cancer in 2022 and more than 609,000 people will succumb to the disease—that’s roughly 1,670 deaths per day in the United States alone.1 As nearly 40% of the population will be diagnosed with cancer at some point during their lifetimes, it is perhaps the greatest health care challenge facing modern society.
Over the last five decades, remarkable clinical advances have substantially reduced the mortality rate for cancer survivors, yet half of those diagnosed with the disease still die within ten years.2
An innovative partnership between The University of Texas at Austin’s Machine Learning Lab, Oden Institute for Computational Engineering and Sciences, and Dell Medical School aims to do better—much better.
Their focus is to integrate two emerging disciplines—computational oncology and machine learning—to transform the future of cancer care. Machine learning applies algorithms to large data sets to build classifiers that can make accurate predictions, even in complex biological and chemical domains. Computational oncology uses physics-based and data-driven advanced mathematical and computational approaches to model tumors, calibrate patient-specific models, and simulate patient responses to potential treatment options. Modeling and simulation occur across a spectrum of scales—from the cellular level to the organ level of the human body. The models can be theory-driven, knowledge-driven, data-driven, or, increasingly, a combination of all three. Substantial computational skills and capabilities, as well as medical knowledge, are required to capture the individuality of each cancer patient’s situation for accurate decision making at all levels. Read the full article.
KAREN L. DAVIDSON 