Influence
February 8, 2021

Natural language processing helps identify patients with chronic cough

Natural language processing helps identify patients with chronic cough

Algorithm developed by Regenstrief and partners could help improve research into condition

Researchers from Regenstrief Institute, Indiana University School of Medicine and Merck & Co. created and validated a natural language processing (NLP) algorithm to identify patients with chronic cough. The validation paper, published in Chest® Journal, is the first to use NLP to identify and examine this condition, and the study created the largest assembled cohort of chronic cough patients to this point.

Chronic cough is classified as a cough that lasts eight weeks or more. It affects 10 percent of the population, but it does not have a diagnostic code. That makes it hard to identify people with the condition through electronic health records (EHRs). Identifying these patients is important for characterizing treatment and unmet needs.

Regenstrief research scientist Michael Weiner, M.D., MPH, and his team created an NLP algorithm to analyze unstructured data in the medical records. That method was instrumental in identifying 74 percent of people with chronic cough who did not have structured evidence of the condition and addressed the gap in ability to characterize the disease burden.

This method can be used to create larger and more robust cohorts for studies related to treatment of chronic cough.

“Identifying and characterizing a chronic cough cohort through electronic health records” was published online ahead of print in Chest. Funding for this research came from Merck & Co., Inc. This is part of a partnership between Regenstrief Institute and Merck to collaborate on projects using clinical data to inform delivery of healthcare.

Read the entire paper here

Dr. Weiner is the first author on the paper. Other authors are Paul Dexter, M.D., of Regenstrief Institute, Indiana University School of Medicine and Eskenazi Health; Kim Heithoff, ScD, Monument Analytics; Anna Roberts, Regenstrief Institute; Ziyue Liu, PhD, Indiana University; Ashley Griffiths, MHA, Regenstrief Institute; Siu Hui, PhD, Regenstrief Institute; Jonathan Schelfhout, PhD, Merck and Co., Inc.; Peter Dicpinigaitis, M.D., Albert Einstein College of Medicine and Montefiore Medical Center; and Ishita Doshi, PhD, and Jessica P. Weaver, PhD, both of Merck and Co., Inc.

About Michael Weiner, M.D., MPH

Michael Weiner, M.D., MPH, is the associate director of Regenstrief Institute William M. Tierney Center for Health Services Research, principal investigator and director at VA HSR&D Center for Health Information and Communication, Richard L. Roudebush VA Medical Center and a professor of medicine at Indiana University School of Medicine.

Related News

illustration of digestive tract with magnifier and stool sample container

New study provides evidence for three-year interval for multi-target stool DNA screening for those at average risk of colon cancer

A scientific study exploring the appropriate interval for colorectal cancer screening via non-invasive multi-target stool DNA testing for individuals

Dr. Tom Imperiale on tailoring colonoscopy screening for 45- to 49-year-olds

Dr. Tom Imperiale on tailoring colonoscopy screening for 45- to 49-year-olds

Dr. Tom Imperiale explains why physicians should be good stewards of colonoscopy resources.  [button_links href=”https://www.regenstrief.org/article/regenstrief-researcher-calls-for-tailoring-colorectal-cancer-screening-45-49-year-olds/” title=”Read the full

Drs. David Haggstrom and Eric Vachon: Personal Health Records for Cancer Survivors

Drs. David Haggstrom and Eric Vachon: Personal Health Records for Cancer Survivors

Dr. David Haggstrom, MD, MAS, and Dr. Eric Vachon, PhD, RN, discuss their feasibility study that showed implementing a

Joshua Vest, PhD, MPH

Regenstrief researcher among 14 fellows to be inducted into American College of Medical Informatics

2022 class of new fellows represents 2 countries and 8 states The American College of Medical Informatics (ACMI) announced