Zietlow, John M

Introduction: Mass casualty incident (MCI) simulation scenarios are developed based on detailed review and planning by multidisciplinary trauma teams. This study aimed to assess the feasibility of using generative artificial intelligence (AI) in developing mass casualty trauma simulation scenarios. The study evaluated a range of mass casualty trauma simulation scenarios generated from a public generative artificial intelligence platform based on publicly available data with a validated objective simulation scoring tool. Methods: Using a large language model (LLM) platform (ChatGPT4, OpenAI, San Francisco, CA, USA), 10 complex MCI trauma simulation scenarios were generated based on publicly available US reported trauma data. Each scenario was evaluated by two Advanced Trauma Life Support (ATLS) certified raters based on the Simulation Scenario Evaluation Tool (SSET), a validated scoring tool out of 100 points. The tool scoring is based on learning objectives, tasks for performance, clinical progression, debriefing criteria, and resources. Two publicly available mass casualty trauma scenarios were similarly evaluated as controls. Revision and recommended feedback was provided for the scenarios, with review time recorded. Post-revision scenarios were evaluated. Interrater reliability was calculated based on Intraclass Correlation Coefficients (2, k) (ICCs). For the scenarios, scores and review times were reported as medians with interquartile range (IQR) as 25th and 75th percentiles. Results: Ten mass casualty trauma simulation scenarios were generated by an LLM, producing a total of 62 simulated patients. The initial LLM-generated scenarios demonstrated a median SSET score of 78.5 (IQR 74–82), substantially lower than the median score of 94 (IQR 93–95) observed in publicly available scenarios. The interrater reliability ICC for the LLM-generated scenarios was 0.965 and 1.00 for publicly available scenarios. Following secondary human revision and iterative refinement, the LLM-generated scenarios improved, achieving a median SSET score of 94 (IQR 93–96) with an interrater reliability ICC of 0.7425. Conclusions: The feasibility study suggests that a structured, collaborative workflow combining LLM-based generation with expert human review may enable a new approach to mass casualty trauma simulation scenario creation. LLMs hold promise as a scalable tool for the development of MCI training materials. However, consistent human oversight, quality assurance processes, and governance frameworks remain essential to ensure clinical accuracy, safety, and educational value.

Abstract Acute appendicitis is a common surgical emergency, most often caused by luminal obstruction from fecaliths. Rarely, foreign body ingestion can lead to appendicitis, particularly when small objects like lead shot become lodged in the appendix. We present the case of a 30-year-old man with chronic intermittent right lower quadrant pain who presented with an acute exacerbation. Imaging revealed two metallic densities in the appendix without overt signs of inflammation. He underwent laparoscopic appendectomy, which confirmed the presence of two retained lead pellets and histologic evidence of acute appendicitis. The patient had a history of frequent game meat consumption. This case underscores a rare but important etiology of appendicitis and the potential for systemic lead exposure from retained foreign bodies. In patients with relevant social histories and suggestive imaging, clinicians should consider this diagnosis and proceed with timely surgical management to prevent complications.

ABSTRACTBackgroundWe aimed to determine the performance of postoperative computed tomography (CT) and upper gastrointestinal series (UGI) in patients who underwent surgery for a perforated peptic ulcer and to assess the yield of routine postoperative studies.MethodsRetrospective, single‐institution, chart‐review study of patients who underwent a repair of a perforated gastric or duodenal ulcer between August 2004 and September 2021 at Mayo Clinic, Rochester, Minnesota.ResultsWe identified a total of 240 patients, 28 (12%) were found to have leaks. When any of the four findings (extraluminal gas or fluid collection adjacent to the repair, worsening pneumoperitoneum, or enteral contrast extravasation) was present on postoperative CT scan (n = 116) it had sensitivity of 76% (95% CI 53%–90%), with a specificity of 90% (95% CI 84%–91%). Upper gastrointestinal series (UGI, n = 150) showed a sensitivity of 57% (95% CI 25%–84%) and a specificity of 99% (95% CI 96%–100%). UGI demonstrated higher specificity compared to CT (p < 0.01); there was no significant difference in sensitivity (p = 0.34). The findings from CT scans led to changes in management for a significantly greater number of patients compared to UGI (20% vs. 4%, p < 0.01). The diagnostic yield for leak identification was 3% for routine postoperative CT (n = 63) and 2% for routine UGI studies (n = 141).ConclusionsPostoperative CT is more likely to change management in patients who underwent repair of a perforated peptic ulcer compared to postoperative upper gastrointestinal series. The yield of routine postoperative studies is low, and their benefit is uncertain.