Linked to from EHR Usability, Workflow & NLP Presentations at AMIA 2012 on the EHR Workflow Management Systems blog.

AMIA 2012: Asthma Status Identification with Natural Language Processing

ABSTRACT: Commonly-used ICD-9 codes have been estimated to ignore about 70% of asthma cases. Though manual chart review with rigorous criteria for determining the asthma status of patients is more accurate, the costliness of manual approaches makes them difficult to apply to large-scale epidemiologic research. Here, we automatically search the unstructured text of electronic medical records using natural language processing (NLP) techniques, thereby aiding the criteria-based asthma ascertainment processes. Evaluations show that automatic ascertainment of the asthma status of patients from electronic records is significantly more accurate than ICD-9 codes.

AMIA 2012 Itinerary Planner


Clinical NLP at 2012 NAACL Human Language Technology Conference