Co-occurring evidence discovery for COPD patients using natural language processing

Publication Type:
Conference Proceeding
Citation:
2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017, 2017, pp. 321 - 324
Issue Date:
2017-04-11
Full metadata record
Files in This Item:
Filename Description Size
07897270.pdfPublished version273.23 kB
Adobe PDF
© 2017 IEEE. Chronic Obstructive Pulmonary Disease (COPD) is a chronic lung disease that affects airflow to the lungs. Discovering the co-occurrence of COPD with other diseases and symptoms is invaluable to medical staff. Building co-occurrence indexes and finding causal relationships with COPD can be difficult because often times disease prevalence within a population influences results. A method which can better separate occurrence within COPD patients from population prevalence would be desirable. Natural Language Processing (NLP) methods are used to examine 64,371 deidentified clinical notes and discover associations between COPD and medical terms. A co-occurrence score is presented which can penalize scores based on term prevalence. The maximum improvements in recall for symptoms and diseases were 0.212 and 0.130. The maximum improvements in precision for symptoms and diseases were 0.303 and 0.333.
Please use this identifier to cite or link to this item: