AI-assisted interpretation of arterial blood gases using a hybrid Stewart and standard base excess model
Authors' conclusion
A formula-guided ChatGPT-based framework using the Partitioned SBE model generated interpretable ABG reports, graphical visualizations, and contextual clinical comments with high concordance to expert assessment.
Study context
- Population
- ICU patients, stratified by primary admission diagnosis
- Participants
- 1,234 patients
- Outcome
- Clinical concordance of model outputs, reviewed by two independent anesthesiologists
Methodological detailssingle-center
- Single-center
Main finding
As reported in the abstract
Clinical concordance of clinical comments and management suggestions with expert assessment
Clinical comments and management suggestions rated concordant
93.1%
95% CI 91.6–94.4
Observational data: associations, not effects.
Further findings
Concordance by admission diagnosis (subgroup)
- Concordance exceeded 96% in renal, metabolic and sepsis subgroups
- Lower concordance in hematologic and malignancy subgroups
Original publication
AI-assisted interpretation of arterial blood gases using a hybrid Stewart and standard base excess model. J Clin Anesth. Published 28 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →