Cognitive Computing Expedites Matching Patients to Clinical Trials
Researchers examined the use of IBM Watson for Clinical Trial Matching (CTM) in a community-based oncology practice.
|The following article features coverage from the 2017 American Society of Clinical Oncology Annual Meeting in Chicago, Illinois. Click here to read more of Oncology Nurse Advisor's conference coverage.|
CHICAGO — Cognitive computing can speed the process of matching cancer patients to appropriate clinical trials, investigators reported at the 2017 American Society of Clinical Oncology (ASCO) Annual Meeting.
J. Thaddeus Beck, MD, of the Highlands Oncology Group (HOG) in Arkansas, and colleagues, in collaboration with Novartis and IBM Watson Health, explored the use of IBM Watson for Clinical Trial Matching (CTM) in a community-based oncology practice. CTM uses natural language processing (NLP) to increase the efficiency and accuracy of determining patient eligibility for clinical trials, the researchers explained. It helps providers locate suitable protocols for their patients by reading trial criteria and matching these to the structured and unstructured patient characteristics when integrated with electronic medical records.
“Use of a cognitive computing approach, such as CTM, in a community oncology practice, could improve efficiency and accuracy of the process of screening patients for clinical trials,” Dr Beck told attendees.
During a 16-week pilot period, data from 2620 patient visits by lung and breast cancer patients were processed by the CTM system. Using NLP capabilities, CTM read clinical trial protocols provided by Novartis and evaluated patient data against the protocols' inclusion and exclusion criteria. In an initial prescreening test, the HOG clinical trial coordinator took 1 hour and 50 minutes to process 90 patients against 3 breast cancer protocols. This was reduced to 24 minutes when the CTM system was used, a significant reduction of 86 minutes, or 78%, according to the investigators.
In addition, the CTM system excluded 94% of patients automatically, providing criteria level evidence as to the reason for exclusion, thereby decreasing the screening workload dramatically.
Read more of Oncology Nurse Advisor's coverage of the 2017 American Society of Clinical Oncology Annual Meeting by visiting the conference page.
1. Beck JT, Vinegra M, Dankwa-Mullan I, et al. Cognitive technology addressing optimal cancer clinical trial matching and protocol feasibility in a community cancer practice. Oral presentation at: 2017 American Society of Clinical Oncology Annual Meeting; June 2-6, 2017; Chicago, IL.