Florida-based Jupiter Medical Center will adopt Watson for Oncology trained by Memorial Sloan Kettering, becoming the first U.S. community hospital to adopt the cognitive computing platform, which will go live at the facility in the beginning of March.
The platform from IBM aims to provide insights to physicians to help them deliver personalized, evidence-based cancer treatment. Watson for Oncology provides information to oncologists to help them deliver evidence-based treatment options by analyzing massive volumes of medical literature to identify individualized treatment options and scaling access to oncology expertise. Watson for Oncology draws from more than 300 medical journals, more than 200 textbooks, and nearly 15 million pages of text to provide insights about different treatment options and also provides oncologists with information regarding drug options and administration instructions. Watson also ranks the evidence-based treatment options, linking to peer reviewed studies and clinical guidelines. Its machine-learning capability means it continuously learns, gaining in value and knowledge over time, officials attest.
This is particularly important as in the U.S., there will be an estimated 1.7 million new cancer cases this year, with 125,000 in Florida alone, according to the American Cancer Society. As such, as healthcare providers and systems seek to enable data-driven, evidence-based cancer care, an explosion of medical information has created both challenges and opportunities to improve quality care. Currently, approximately 50,000 oncology research papers are published annually, and by 2020 medical information is projected to double every 73 days, outpacing the ability of humans to keep up with the proliferation of medical knowledge, according to recent research.
Recent research published in Medscape revealed that in a study of 638 breast cancer cases at Manipal, a top cancer center in India, Watson had a high level of agreement with the recommendations of the oncologists on the center's multidisciplinary tumor board. The report noted, “Watson's treatment endorsements, which are presented as ‘for consideration’ or ‘recommended,’ were concordant with the recommendations of the tumor board 90 percent of the time.” However, according to the research, that 90 percent figure was hit only after the cases were reviewed a second time, adjusted by the oncologists, and passed through Watson again. The first time around, Watson and the tumor board agreed 73 percent of the time.
IBM and MSK have been accelerating Watson for Oncology’s training; Watson for Oncology is now available to assist clinicians in developing treatment plans for breast, lung, colorectal, cervical, ovarian and gastric cancers. IBM and MSK plan to train Watson on at least nine additional cancer types this year, covering nearly 80 percent of the worldwide incidence of cancer.
“We were impressed by Watson’s analytical ability to help provide relevant treatment options for patients to allow physicians to personalize patient care in an unparalleled way,” Abraham Schwarzberg, M.D., chief of oncology at Jupiter Medical Center, said in a statement. “Harnessing the power of Watson will help our oncology multidisciplinary team identify individual treatments. As one of the first in the country to implement this incredible tool, Jupiter Medical Center continues to be a regional leader in integrating technology to provide cutting-edge clinical care.”
