D’Hoore, André

BACKGROUND: The Ventral Rectopexy International Expert Panel recently published a consensus update on ventral rectopexy. The ability of large language models to synthesize the literature on ventral rectopexy without an explicit knowledge base was studied before the publication of the consensus. OBJECTIVE: To compare the responses and citations of different large language models on ventral rectopexy using the expert panel consensus as the reference standard. DESIGN: ChatGPT-4o, Gemini 1.5 Pro, and OpenEvidence were compared on content appropriateness (1 = inappropriate to 5 = appropriate), readability (Flesch reading ease), response length, citation fabrication, and citation quality per Oxford Levels of Evidence. The most content-appropriate chatbot response selected by the expert panel was de-identified and presented alongside the consensus text to 15 colorectal surgeons who attempted to identify the chatbot-generated text. SETTINGS: Questions were submitted from September 18 to 19, 2024. Analysis was performed before the online publication of the consensus on January 30, 2025. MAIN OUTCOME MEASURES: The main outcome measures included content appropriateness, fabricated citation rate, citation quality, and the accuracy of identifying human versus chatbot text by colorectal surgeons. RESULTS: OpenEvidence ranked highest for content appropriateness (mean 3.5/5), above Gemini (3.0/5) and ChatGPT (2.8/5; p < 0.001). ChatGPT was most verbose with the highest readability scores ( p = 0.021). ChatGPT fabricated 53% of citations; Gemini fabricated 12%; OpenEvidence fabricated 0% ( p < 0.001). All OpenEvidence citations were peer reviewed, with 40 of 117 (34%) citing level I to III studies compared with 46 of 94 (49%) of the references cited in the consensus ( p = 0.043). Chatbot-generated responses were identified with 28 of 51 (55%) accuracy. LIMITATIONS: Reproducibility may be affected due to the nature of large language models and the availability of the consensus after publication. CONCLUSIONS: OpenEvidence outperformed Gemini 1.5 Pro and ChatGPT-4o in content appropriateness and peer-reviewed citation quantity and quality. Chatbot-generated text was indistinguishable from expert-authored consensus to subject matter experts. Large language models, as an early-stage research tool, may be viable for future consensus working groups, provided transparent disclosure and rigorous oversight. See Video Abstract . ¿PUEDEN LOS MODELOS LINGÜÍSTICOS DE GRAN TAMAÑO SER UNA HERRAMIENTA VIABLE PARA LOS GRUPOS DE TRABAJO DE CONSENSO? LA EXPERIENCIA DEL GRUPO DE CONSENSO DE EXPERTOS EN RECTOPEXIA VENTRAL ANTECEDENTES: El Panel Internacional de Expertos en Rectopexia Ventral publicó recientemente una actualización consensuada sobre la rectopexia ventral. Antes de la publicación del consenso, se estudió la capacidad de los grandes modelos lingüísticos para sintetizar la bibliografía sobre la rectopexia ventral sin una base de conocimientos explícita. Objetivo: Comparar las respuestas y citas de diferentes grandes modelos lingüísticos sobre la rectopexia ventral utilizando el consenso del panel de expertos como estándar de referencia. DISEÑO: Se compararon ChatGPT-4o, Gemini 1.5 Pro y OpenEvidence en cuanto a la idoneidad del contenido (1 = inadecuado a 5 = adecuado), la legibilidad (índice de legibilidad de Flesch), la longitud de la respuesta, la fabricación de citas y la calidad de las citas según los niveles de evidencia de Oxford. La respuesta del chatbot más adecuada en cuanto al contenido seleccionada por el panel de expertos se anonimizó y se presentó junto con el texto del consenso a 15 cirujanos colorrectales que intentaron identificar el texto generado por el chatbot. ENTORNO: Las preguntas se enviaron los días 18 y 19 de septiembre de 2024. El análisis se realizó antes de la publicación del consenso en línea el 30 de enero de 2025. PRINCIPALES MEDIDAS DE RESULTADOS: Adecuación del contenido, tasa de citas inventadas, calidad de las citas, precisión en la identificación del texto humano frente al del chatbot por parte de los cirujanos colorrectales. RESULTADOS: OpenEvidence obtuvo la puntuación más alta en cuanto a la adecuación del contenido (media de 3,5/5), por encima de Gemini (3,0/5) y ChatGPT (2,8/5) (p<0,001). ChatGPT fue el más prolijo, con las puntuaciones más altas en legibilidad (p = 0,021). ChatGPT inventó el 53% de las citas; Gemini inventó el 12 %; OpenEvidence inventó el 0 % (p < 0,001). Todas las citas de OpenEvidence fueron revisadas por pares, con 40/117 (34 %) que citaban estudios de nivel I-III frente a 46/94 (49 %) de las referencias citadas en el consenso (p = 0,043). Las respuestas generadas por el chatbot se identificaron con una precisión del 28/51 (55 %). LIMITACIONES: Reproducibilidad debido a la naturaleza de los modelos de lenguaje grandes y a la disponibilidad del consenso tras la publicación. CONCLUSIONES: OpenEvidence superó a Gemini 1.5 Pro y ChatGPT-4o en cuanto a la idoneidad del contenido y la cantidad y calidad de las citas revisadas por pares. El texto generado por el chatbot era indistinguible del consenso redactado por expertos para los expertos en la materia. Los modelos de lenguaje grandes como herramienta de investigación en fase inicial pueden ser viables para futuros grupos de trabajo de consenso, siempre que se garantice una divulgación transparente y una supervisión rigurosa. ( AI-generated translation )

Abstract Background Recent evidence challenges the current standard of offering surgery to patients with ileocecal Crohn’s disease only when they present complications of the disease. Methods A retrospective, multicenter comparative analysis was performed including patients operated for primary ileocecal CD at 12 referral centers. Patients were divided in 2 groups, according to indication of surgery for inflammatory (ICD) or complicated (CCD) phenotype. Short-term results were compared. Patients operated on for primary isolated ileocaecal CD (last 50 cm of the terminal ileum and cecum), either for predominantly inflammatory phenotype or for complications of the disease (stricturing or fistulizing pattern), between January 2012 - December 2021 were considered eligible to participate in this study. Patients with previous abdominal procedures for CD, and patients who had activity of the disease in other intestinal segments other than the ileocaecal region at the time of surgery, were excluded from the study. Results 2013 patients were included, 291 (14.5%) in the ICD group. No differences were found between groups in time from diagnosis to surgery or in the levels of exposure to biologic drugs before indication of surgery. CCD patients had higher rates of low BMI, anemia (40.9 vs. 27%, p: &lt; 0.001), and low albumin (11.3 vs. 2.6%, p: &lt; 0.001). CCD patients had longer operations, lower rates of laparoscopic approach (84.3 vs. 93.1%, p: 0.001), and higher conversion rates (9.3 vs. 1.9%, p: &lt; 0.001). CCD had longer hospital stay and higher postoperative complication rates (26.1 vs. 21.3%, p: 0.083). Anastomotic leakage and reoperations were also more frequent in this group. More patients in the CCD group required an extended bowel resection (14.1 vs. 8.3%, p: 0.017). In multivariate analysis, CCD was associated with prolonged surgeries (OR: 3.44, p: 0.001) and requirements of multiple intraoperative procedures (OR: 8.39, p: 0.030). Conclusion Indication of surgery in patients who present an inflammatory phenotype of CD was associated with better outcomes when compared to patients operated on for complications of the disease, without a difference between groups in time from diagnosis to surgery.

Abstract Background Small bowel fibrostenotic strictures are common in patients with Crohn’s disease (CD). No global consensus recommendations on definitions, diagnosis and clinical management are available. Methods Several systematic reviews followed by a RAND/University of California Los Angeles appropriateness study on the definitions, diagnosis and clinical management of fibrostenosing CD in clinical practice were performed. A panel of 28 global experts and a patient representative were convened. They assessed a total of 152 candidate items. The items were subsequently evaluated for appropriateness. Results No accurate predictive biomarkers are available for naïve or anastomotic fibrostenosing strictures. Accurate diagnosis of fibrostenosing CD requires cross-sectional imaging which should evaluate bowel wall thickness, luminal narrowing and prestenotic dilatation. A potential inflammatory component should be assessed. Abdominal cross-sectional imaging was considered necessary prior to any treatment decision. The panel proposed an approach to medical, endoscopic, and surgical therapies (Figure 1 and Table 1). Technical characteristics for endoscopic balloon dilation and follow up strategies after successful dilation therapy were identified. Appropriateness, types and performance of different surgical approaches in various settings were evaluated. Conclusion This global consensus provides clinical guidance for the diagnostic and therapeutic management of patients with fibrostenotic CD.