GE Healthcare, Vanderbilt to develop AI-powered apps for immunotherapy cancer treatments

GE Healthcare and the Vanderbilt University Medical Center (VUMC) have partnered to develop diagnostic tools and AI-powered applications to create safer and more precise immunotherapy treatments for cancer patients.

“This partnership is a great example of the increasing convergence of the tools, technologies and data used by therapy innovators and healthcare providers,” Kieran Murphy, GE Healthcare president and chief executive officer, said in a prepared statement.

Through the five-year partnership, the entities plan to use anonymized demographic, genomic, tumor, cellular, proteomic and imaging data to retroactively analyze and correlate the immunotherapy treatment response of thousands of VUMC cancer patients. From there, the companies will create AI-powered apps and use the data to help physicians identify the best treatment for individual patients. Additionally, researchers plan to develop new PET imaging tracers that will work with the AI-powered apps to help physicians stratify cancer patients for clinical trials.

The hope is the tools will predict the effectiveness of an immunotherapy treatment and adverse effects for specific patients before the therapy is administered, allowing physicians to target immunotherapies to the right patients and avoid potentially damaging, ineffective and costly courses of treatments. Immunotherapy uses the immune system to recognize and attack cancer.

“Immunotherapy offers tremendous promise but given the current unpredictability of some patients’ reactions to treatments, it is also associated with increased morbidity and cost,” Jeff Balser, MD, PhD, VUMC president and chief executive officer and dean of the Vanderbilt University School of Medicine, said in a prepared statement. “This partnership provides the opportunity to leverage strengths of both of our organizations to further personalize cancer care by creating new tools that allow clinicians to more accurately predict how patients will respond to a specific therapy.”

The first analytics application prototype is expected to be available by the end of 2019, while the PET tracer proof-of-concept is expected to be available by the end of 2020.