ArticleBritish journal of anaesthesia2025
Automated structured data extraction from intraoperative echocardiography reports using large language models.
Article in British journal of anaesthesia, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 10 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
10 citing papers in PubMed.
- Automated Identification of Complex Percutaneous Coronary Intervention from Cardiac Catheterization Reports using Large Language Models.medRxiv : the preprint server for health sciences · 2026Article
- Development and Clinical Evaluation of a Large Language Model-Based System for Generating Patient-Friendly Echocardiography Reports: Two-Stage Retrospective Validation and Prospective Survey Study.Journal of medical Internet research · 2026Article
- Leveraging natural language processing artificial intelligence for automated data extraction of ejection fraction and strain from cardiovascular imaging reports.American heart journal plus : cardiology research and practice · 2026Article
- Open-source large language model-based on-premises pipeline for automated data extraction from unstructured electronic health records: a pilot study.BMJ health & care informatics · 2026Article
- Proof-of-Concept Automated Framework for Intraoperative Transesophageal Echocardiography: View Classification and Biventricular Function Assessment.Journal of cardiothoracic and vascular anesthesia · 2026Article
- Exploration of Anesthetic Strategies for Transcatheter Tricuspid Valve Intervention.Reviews in cardiovascular medicine · 2026Review
- Improving reliability and accuracy of structured data extraction using a consensus large-language model approach-a use case description in multiple sclerosis.Frontiers in artificial intelligence · 2026Article
- Toward Artificial Intelligence in Oncology and Cardiology: A Narrative Review of Systems, Challenges, and Opportunities.Journal of clinical medicine · 2025Article
- Enhanced global oil spill dataset from 1967 to 2023 based on text-form incident information.Scientific data · 2025Article
- Generative AI models: the next anaesthetic agent?British journal of anaesthesia · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
Abstract
backgroundConsensus-based large language model (LLM) ensembles might provide an automated solution for extracting structured data from unstructured text in echocardiography reports.
methodsThis cross-sectional study utilised 600 intraoperative transoesophageal reports (100 for prompt engineering; 500 for testing) randomly sampled from 7106 adult patients undergoing cardiac surgery at two hospitals within the University of Pennsylvania Healthcare System. Three echocardiographic parameters (left ventricular ejection fraction, right ventricular systolic function, and tricuspid regurgitation) were extracted from both the presurgical and postsurgical sections of the reports. LLM ensembles were generated using five open-source LLMs and four voting strategies: (1) unanimous (five out of five in agreement); (2) supermajority (four or more of five in agreement); (3) majority (three or more of five in agreement); and (4) plurality (two or more of five in agreement). Returned LLM ensemble responses were compared with the reference standard dataset to calculate raw accuracy, consensus accuracy, error rate, and yield.
resultsOf the four LLM ensembles, the unanimous LLM ensemble achieved the highest consensus accuracies (99.4% presurgical; 97.9% postsurgical) and the lowest error rates (0.6% presurgical; 2.1% postsurgical) but had the lowest data extraction yields (81.7% presurgical; 80.5% postsurgical) and the lowest raw accuracies (81.2% presurgical; 78.9% postsurgical). In contrast, the plurality LLM ensemble achieved the highest raw accuracies (96.1% presurgical; 93.7% postsurgical) and the highest data extraction yields (99.4% presurgical; 98.9% postsurgical) but had the lowest consensus accuracies (96.7% presurgical; 94.7% postsurgical) and highest error rates (3.3% presurgical; 5.3% postsurgical).
conclusionsA consensus-based LLM ensemble successfully generated structured data from unstructured text contained in intraoperative transoesophageal reports.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.