Natural Language Processing in Surgery

Abstract

Objective: The aim of this study was to systematically assess the application and potential benefits of natural language processing (NLP) in surgical outcomes research. Summary Background Data: Widespread implementation of electronic health records (EHRs) has generated a massive patient data source. Traditional methods of data capture, such as billing codes and/or manual review of free-text narratives in EHRs, are highly labor-intensive, costly, subjective, and potentially prone to bias. Methods: A literature search of PubMed, MEDLINE, Web of Science, and Embase identified all articles published starting in 2000 that used NLP models to assess perioperative surgical outcomes. Evaluation metrics of NLP systems were assessed by means of pooled analysis and meta-analysis. Qualitative synthesis was carried out to assess the results and risk of bias on outcomes. Results: The present study included 29 articles, with over half (n = 15) published after 2018. The most common outcome identified using NLP was postoperative complications (n = 14). Compared to traditional non-NLP models, NLP models identified postoperative complications with higher sensitivity [0.92 (0.87–0.95) vs 0.58 (0.33–0.79), P < 0.001]. The specificities were comparable at 0.99 (0.96–1.00) and 0.98 (0.95–0.99), respectively. Using summary of likelihood ratio matrices, traditional non-NLP models have clinical utility for confirming documentation of outcomes/diagnoses, whereas NLP models may be reliably utilized for both confirming and ruling out documentation of outcomes/diagnoses. Conclusions: NLP usage to extract a range of surgical outcomes, particularly postoperative complications, is accelerating across disciplines and areas of clinical outcomes research. NLP and traditional non-NLP approaches demonstrate similar performance measures, but NLP is superior in ruling out documentation of surgical outcomes.

Concept Recognition and Characterization of Patients Undergoing Resection of Vestibular Schwannoma Using Natural Language Processing

“…NLP applications, such as CogStack, can rapidly process large volumes of clinical data and extract concepts associated with a disease process to create a unique fingerprint of text concepts associated with a disease, complication, or outcome. 7 For example, our group have substantiated the efficacy of NLP in identifying concepts associated with normal pressure hydrocephalus, which may in future aid timely diagnosis and discrimination from mimics. 8 This study aims to identify text concepts associated with surgically managed VS using an NLP model (CogStack) through analysis of free-text clinical data from patient EHRs, to create a unique concept panel associated with surgically managed VS. Resultantly, we aim to highlight how NLP may be applied in a surgical health care setting using VS as an exemplar.…”

Artificial Intelligence: Singularity Approaches

“…Most surgical applications of NLP involve the analysis of perioperative complications captured from data within the electronic health record. 57 However, current examples of NLP within plastic surgery involve sentiment analysis of social media platforms regarding general attitudes toward plastic surgery. 58,59 A Mayo Clinic study used NLP within a virtual assistant smartphone app to reproduce human-like conversations and understand intent within human speech.…”

The Use of Artificial Intelligence and Machine Learning in Surgery: A Comprehensive Literature Review

“…NLP provides a potential solution for these challenges by automating the identification of predetermined keywords. 39 For instance, NLP has been used for automated detection of incidental durotomies in the free-text operative notes of patients undergoing lumbar spine surgery. 40 In this manner, the NLP algorithms can be programmed to run through extensive databases to look for specific keywords, identify particular complications, and allow for tabulation of the same without manual effort through extensive reviews of patient records.…”