Sign In

Communications of the ACM

ACM TechNews

Scientists Teaching Machines to Make Clinical Trials More Successful

View as: Print Mobile App Share:
Yizhao Ni, a researcher in the Division of Biomedical Informatics at Cincinnati Childrens Hospital Medical Center.

Yizhao Ni and his colleagues are mining electronic health record data and blending human and artificial intelligence to find better ways to recruit patients for clinical trials.

Credit: Cincinnati Children's Hospital Medical Center

Researchers at Cincinnati Children's Hospital Medical Center are using machine-learning technology to find better ways to recruit patients for clinical trials.

The team developed an automated algorithm to mine data on the various factors that influence patient recruitment. The algorithm analyzes, compares, and interprets different data sources to predict specific patient decision making. It was tested on data from 2010 through 2012 involving clinical trial recruitment in the Emergency Department of Cincinnati Children's. Researchers then compared its effectiveness to a "random-response-prediction program" developed to simulate the current recruiting method in the Emergency Department.

"The ultimate goal of our research is to impact patient recruitment strategies to increase participation in clinical trials, and to help ensure that studies can be completed and the data are meaningful," says lead researcher Yizhao Ni.

The study confirmed patients are less likely to participate in randomized studies, multicenter trials, more complex trials, and trials that require follow-up visits.

The researchers also found about 60% of patients approached with traditional recruitment practices ultimately agreed to participate. However, they predict their new automated algorithm could push acceptance rates up to about 72%.

From Cincinnati Children's Hospital Medical Center
View Full Article


Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account