The impact of regional block presence on large language model-based postoperative analgesia recommendations in abdominal surgery: a comparative study using real-world patient data.

backgroundPostoperative pain management is a core component of anesthesiology practice, with regional anesthesia playing a key role in multimodal analgesia strategies. Large language model (LLM)-based artificial intelligence (AI) systems are increasingly proposed as clinical decision support tools; however, their ability to integrate critical perioperative context, such as the presence of an existing regional block, remains insufficiently explored.

methodsThis prospective, observational, comparative study included 144 adult patients undergoing elective abdominal surgery at a tertiary care center, after exclusion of four patients due to severe preoperative or intraoperative complications that significantly altered the planned postoperative analgesia. Patients were grouped according to the presence or absence of a regional block (70 per group). For each patient, anonymized and standardized clinical scenarios were evaluated independently by three LLM-based AI systems (ChatGPT, Gemini, and Copilot) to generate postoperative analgesia recommendations. AI outputs were assessed by blinded anesthesiology experts for opioid recommendation, multimodal analgesia, consideration of regional anesthesia, and overall clinical appropriateness using a 5-point Likert scale. Multivariable logistic and ordinal logistic regression analyses were performed to determine the independent effect of regional block presence, adjusting for relevant clinical covariates. Agreement between AI recommendations and actual clinical practice was evaluated using Cohen's kappa.

resultsRegional block presence was not independently associated with opioid recommendations generated by any AI system (all p > 0.05). However, the likelihood of recommending an additional regional block was significantly reduced by ChatGPT (adjusted odds ratio [aOR] 0.02, p < 0.001) and Copilot (aOR 0.15, p = 0.019). Gemini demonstrated complete separation, consistently recommending regional blocks only in patients without an existing block. Multimodal analgesia was universally recommended by ChatGPT and Gemini, precluding regression analysis. Expert evaluation scores were significantly higher in scenarios with an existing regional block across all AI systems. Overall agreement between AI-generated recommendations and real-world clinical decisions was limited.

conclusionsLLM-based AI systems demonstrate partial contextual awareness of regional anesthesia when generating postoperative analgesia recommendations. However, this awareness does not consistently translate into concordance with real-world clinical practice. These findings support the use of AI as an adjunctive decision support tool rather than a substitute for clinician judgment in postoperative pain management.