ArticleHeliyon2024
ChatGPT achieves comparable accuracy to specialist physicians in predicting the efficacy of high-flow oxygen therapy.
Article in Heliyon, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 6 papers, 2 of them syntheses that pooled it.
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
6 citing papers in PubMed, 2 syntheses or guidelines pooled it.
- Machine learning-based prediction models for noninvasive respiratory support failure in acute respiratory failure: a systematic review and meta-analysis.Frontiers in medicine · 2026Pooled it
- The applications of ChatGPT and other large language models in anesthesiology and critical care: a systematic review.Canadian journal of anaesthesia = Journal canadien d'anesthesie · 2025Pooled it
- Computational tools for personalizing treatment of acute respiratory failure, from machine learning to digital twins: a narrative review.Critical care (London, England) · 2026Review
- Large Language Models in Critical Care Medicine: Scoping Review.JMIR medical informatics · 2025Article
- Primer on large language models: an educational overview for intensivists.Critical care (London, England) · 2025Review
- Beware the self-fulfilling prophecy: enhancing clinical decision-making with AI.Critical care (London, England) · 2024Article
Corrections and comments
- Commented on by
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: The failure of high-flow nasal cannula (HFNC) oxygen therapy can necessitate endotracheal intubation in patients, making timely prediction of the intubation risk following HFNC therapy crucial for reducing mortality due to delays in intubation. Objectives: To investigate the accuracy of ChatGPT in predicting the endotracheal intubation risk within 48 h following HFNC therapy and compare it with the predictive accuracy of specialist and non-specialist physicians. Methods: We conducted a prospective multicenter cohort study based on the data of 71 adult patients who received HFNC therapy. For each patient, their baseline data and physiological parameters after 6-h HFNC therapy were recorded to create a 6-alternative-forced-choice questionnaire that asked participants to predict the 48-h endotracheal intubation risk using scale options ranging from 1 to 6, with higher scores indicating a greater risk. GPT-3.5, GPT-4.0, respiratory and critical care specialist physicians and non-specialist physicians completed the same questionnaires (N = 71) respectively. We then determined the optimal diagnostic cutoff point, using the Youden index, for each predictor and 6-h ROX index, and compared their predictive performance using receiver operating characteristic (ROC) analysis. Results: The optimal diagnostic cutoff points were determined to be ≥ 4 for both GPT-4.0 and specialist physicians. GPT-4.0 demonstrated a precision of 76.1 %, with a specificity of 78.6 % (95%CI = 52.4-92.4 %) and sensitivity of 75.4 % (95%CI = 62.9-84.8 %). In comparison, the precision of specialist physicians was 80.3 %, with a specificity of 71.4 % (95%CI = 45.4-88.3 %) and sensitivity of 82.5 % (95%CI = 70.6-90.2 %). For GPT-3.5 and non-specialist physicians, the optimal diagnostic cutoff points were ≥5, with precisions of 73.2 % and 64.8 %, respectively. The area under the curve (AUC) in ROC analysis for GPT-4.0 was 0.821 (95%CI = 0.698-0.943), which was the highest among the predictors and significantly higher than that of non-specialist physicians [0.662 (95%CI = 0.518-0.805), P = 0.011]. Conclusion: GPT-4.0 achieves an accuracy level comparable to specialist physicians in predicting the 48-h endotracheal intubation risk following HFNC therapy, based on patient baseline data and physiological parameters after 6-h HFNC therapy.
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.