Improving the Efficiency of Clinical Trial Recruitment Using EHR via Natural Language Processing and Machine Learning

3:30 PM–4:30 PM May 19, 2020 (Conference Time: US - Pacific)

3:30 PM–4:30 PM May 19, 2020

Regency Prefunction


Abstract: Efficiently identifying eligible patients is an important component of a successful clinical trial. Using billing codes from electronic health record data to screen for potential patients leads lots of unnecessary patients for chart review. Incorporating billing codes and data extracted from notes using natural language processing to build machine learning algorithm for patient screen could significantly improve the efficiency for identifying eligible patients for clinical trials.

Describe the new knowledge and additional skills the participant will gain after attending your presentation.: 1. Leveraging electronic medical record to screen patients could help on patient recruitment
2. Using natural language processing technology to extract information from narrtive notes could enrich information for patient screening to improve accuracy and efficiency of patient recruitment
3. Incorporating billing code and data extracted from notes to build a machine learning algorithm to do patient screen could significantly reduce the number of patient needing chart review while keeping eligible patients


Tianrun Cai (Presenter)
Brigham and Women's Hospital

Fiona Cai, Massachusetts Institute of Technology
Kumar Dahal, Brigham and Women's Hospital
Chuan Hong, Harvard Medical School
Katherine Liao, Brigham and Women's Hospital