Detection of Surgical Site Infection Utilizing Automated Feature Generation in Clinical Notes
This work addresses the challenge of efficiently detecting SSI, a major postsurgical complication, for healthcare providers, but it is incremental as it builds on existing NLP methods.
The study tackled the problem of detecting surgical site infections (SSI) by developing an automated method to generate keyword features from clinical notes, which was validated with medical experts and a decision tree algorithm, showing that the framework could identify SSI keywords and enhance search-based NLP approaches.
Postsurgical complications (PSCs) are known as a deviation from the normal postsurgical course and categorized by severity and treatment requirements. Surgical site infection (SSI) is one of major PSCs and the most common healthcare-associated infection, resulting in increased length of hospital stay and cost. In this work, we assessed an automated way to generate lexicon (i.e., keyword features) from clinical narratives using sublanguage analysis with heuristics to detect SSI and evaluated these keywords with medical experts. To further validate our approach, we also conducted decision tree algorithm on cohort using automatically generated keywords. The results show that our framework was able to identify SSI keywords from clinical narratives and to support search-based natural language processing (NLP) approaches by augmenting search queries.