Cancer treatment and research, perhaps more than other diseases, create mass quantities of data, arguably more data than any one clinician can stay on top of on a daily basis between keeping up with patient treatments, published findings from clinical trials and trying to draw actionable connections between all of the information. IBM is betting its "Watson for Oncology" offering can help.
Through a collaboration with Memorial Sloan Kettering Cancer Center in New York City, Watson engineers are having the computer analyze patient medical records to process both structured and unstructured data, such as clinical notes and codes, respectively. Watson then arranges key patient information and produces suggestions for treatment based on its findings, according to a post on IBM's Think blog.
"By combining attributes from the patient's file with clinical expertise, external research and data, Watson for Oncology identifies potential treatment plans a doctor may want to consider for a patient," IBM research scientists Gerald Tesauro and Murray Campbell wrote in the post.
Watson for Oncology also scans sources including curated literature, textbooks, and medical journals — more than 12 million pages of text — to back up the options it identifies and help oncologists review treatments.
"We see a potential for this technology to transform industries and professions, leading to greater productivity, and much more highly informed decision-making," the authors wrote.