Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 15, 2022Anesthesia & AnalgesiaOpen Access

The NLP pipeline and anesthesiologist agreed in 81.24% of instances; the NLP pipeline identified information not noted by the anesthesiologist in 16.57% of instances, and missed conditions found by the anesthesiologist in 2.19% of instances.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Methods to automate, support, and streamline the preanesthesia evaluation process may improve resource utilization and efficiency.

Does an NLP pipeline accurately identify preanesthetic history elements compared to manual anesthesiologist review in surgical patients?

Population

93 patients with 9765 free-text clinical notes

Comparison

NLP pipeline vs anesthesiologist review

Design

Proof-of-concept validation study

Authors

HSHarrison S. SuhJTJeffrey TullyMMMinhthy N. Meineke

Discussion

Loading...

Member takes

Overview

NLP may aid preoperative history extraction from notes; leaves open validation for efficiency gains or practice change.

Structured PICO

Does an NLP pipeline accurately identify preanesthetic history elements compared to manual anesthesiologist review in surgical patients?

P
Population
93 patients planned to undergo elective surgery from a single-day census of the Anesthesia Preparedness Clinic at a quaternary academic medical center (UC San Diego).
I
Intervention
Natural language processing (NLP) pipeline (Named Entity Recognition model) analyzing unstructured free-text clinical notes to identify preoperative medical history conditions.
C
Comparator
Manual chart review by an anesthesiologist.
O
Outcome
Concordance rate between the NLP pipeline and the anesthesiologist on the presence or absence of specific medical conditions.

An NLP pipeline can effectively extract relevant preanesthetic medical history from unstructured clinical notes, often identifying conditions missed by manual review.

Cite This Study

Suh et al. (2022) studied this question.

synapsesocial.com/papers/6a7cefa8cc8444f0202fa794https://doi.org/10.1213/ane.0000000000006152
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Automated Identification of Cardiopulmonary Disease Cases for Preoperative Risk Stratification Using Machine Learning: A Retrospective Analysis2026
  2. 2Early evaluation of a natural language processing tool to improve access to educational resources for surgical patients2024 · 3 citations
  3. 3Exploring Named Entity Recognition Potential and the Value of Tailored Natural Language Processing Pipelines for Radiology, Pathology, and Progress Notes in Clinical Decision Support: Quantitative Study (Preprint)2024
  4. 4Use of natural language processing method to identify regional anesthesia from clinical notes2024 · 4 citations
  5. 5Assessing the utility of natural language processing for detecting postoperative complications from free medical text2024 · 3 citations