Jones Barbara

Characterizing mentions found in clinical texts that support, refute, or represent uncertainty for suspected pneumonia is one area where automated Natural Language Processing (NLP) screening algorithms could be improved. Mentions of uncertainty and negation commonly occur in clinical texts, and opportunities exist to extend existing algorithms [1] and taxonomies [2]. In general there are three main sources of uncertainty found in healthcare: 1) probability or risk; 2) ambiguity – lack of reliability, credibility or adequacy of the information; and, 3) complexity – aspects of the phenomenon that make it difficult to comprehend [3].

Objective

We sought to identify relevant evidence that supports, refutes or contributes uncertainty when reviewing cases of suspected pneumonia and characterize their interaction with uncertainty phenomena found in clinical texts.

 

Natural language processing algorithms that accurately screen clinical documents for suspected pneumonia must extract and reason about whether these mentions provide evidence that supports, refutes, or represents uncertainty. Our efforts extend existing algorithms [1] and taxonomies [2] that can be leveraged by NLP tools for more accurate handling of uncertainty for suspected pneumonia case review.

Objective

We sought to classify evidence that supports, refutes, or contributes uncertainty when reviewing cases of suspected pneumonia. We extend an existing taxonomy of uncertainty to classify these phenomena with the goal of improving existing Natural Language Processing (NLP) algorithms.