Detection of Surgical Site Infection Utilizing Automated Feature Generation in Clinical Notes

TL;DR

This paper presents an automated method to generate keyword features from clinical notes to detect surgical site infections, improving NLP search capabilities and supporting clinical decision-making.

Contribution

It introduces a novel heuristic-based lexicon generation approach from clinical narratives for SSI detection, validated with expert input and decision tree analysis.

Findings

Successfully identified SSI keywords from clinical notes

Enhanced search-based NLP for SSI detection

Validated approach with expert and algorithmic evaluation

Abstract

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.