Background: Several artificial intelligence systems based on large language models (LLMs) have been commercially developed, with recent interest in integrating them for clinical questions. Recent versions now include image analysis capacity, but their performance in gastroenterology remains untested. This study assesses ChatGPT-4’s performance in interpreting gastroenterology images. Methods: A total of 740 images from five procedures—capsule endoscopy (CE), device-assisted enteroscopy (DAE), endoscopic ultrasound (EUS), digital single-operator cholangioscopy (DSOC), and high-resolution anoscopy (HRA)—were included and analyzed by ChatGPT-4 using a predefined prompt for each. ChatGPT-4 predictions were compared to gold standard diagnoses. Statistical analyses included accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC). Results: For CE, ChatGPT-4 demonstrated accuracies ranging from 50.0% to 90.0%, with AUCs of 0.50–0.90. For DAE, the model demonstrated an accuracy of 67.0% (AUC 0.670). For EUS, the system showed AUCs of 0.488 and 0.550 for the differentiation between pancreatic cystic and solid lesions, respectively. The LLM differentiated benign from malignant biliary strictures with an AUC of 0.550. For HRA, ChatGPT-4 showed an overall accuracy between 47.5% and 67.5%. Conclusions: ChatGPT-4 demonstrated suboptimal diagnostic accuracies for image interpretation across several gastroenterology techniques, highlighting the need for continuous improvement before clinical adoption.

Background/Objectives: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. Methods: A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models’ performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. Results: The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. Conclusions: To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery.

Rectal cancer is a highly prevalent disease. Evidence presented in the 2025 phase-III OPERA randomised trial suggests that Contact X-ray Brachytherapy (CXB), with external beam chemoradiotherapy, is a viable organ-preserving alternative to radical surgery. We conducted a systematic review and meta-analysis to assess the clinical effectiveness of CXB in the treatment of rectal cancer. This systematic review was prospectively registered (CRD42021284969) and reported following PRISMA guidelines. Multiple electronic databases were interrogated using the search terms "Rectal cancer", "Contact Brachytherapy", and synonym terms. Clinical complete response (cCR) was the primary outcome. Proportional meta-analyses were conducted and presented as forest plots with summary proportions and 95 % confidence intervals. The literature search identified 973 studies, of which 52 studies encompassing 5447 patients met the inclusion and exclusion criteria and were included in the meta-analysis. Pooled estimates of outcomes were as follows: cCR rate = 82 % (95 % CI 76-88 %), Local Regrowth rate = 20 % (95 % CI 15-25 %), regional metastasis rate = 3 % (95 % CI 2-4 %), salvage surgery rate = 14 % (95 % CI 11-18 %), long-term disease control post-salvage surgery rate = 88 % (95 % CI 78-96 %) and organ preservation = 81 % (95 % CI 74-88 %). CXB in the appropriately selected patient population can achieve long-term disease control and organ preservation whilst avoiding major surgery. Salvage surgery remains a viable option for patients who experience disease regrowth with excellent long-term disease control. Clinicians should discuss CXB with rectal cancer patients, presenting it as a viable and safe alternative to radical surgery. This is particularly pertinent for patients who are stoma-averse or older patients in frail health.

Introduction: Following the rapid advances in minimally invasive surgery, there are a multitude of surgical modalities available for resecting rectal cancers. Robotic resections represent the current pinnacle of surgical approaches. Currently, decisions on the surgical modality depend on local resources and the expertise of the surgical team. Given limited access to robotic surgery, developing tools based on pre-operative data that can predict the difficulty of surgery would streamline the efficient utilisation of resources. This systematic review aims to appraise the existing literature on artificial intelligence (AI)-driven preoperative MRI analysis for surgical difficulty prediction to identify knowledge gaps and promising models warranting further clinical evaluation. Methods: A systematic review and narrative synthesis were undertaken in accordance with PRISMA and SWiM guidelines. Systematic searches were performed on Medline, Embase, and the CENTRAL Trials register. Studies published between 2012 and 2024 were included where AI was applied to preoperative MRI imaging of adult rectal cancer patients undergoing surgeries, of any approach, for the purpose of stratifying surgical difficulty. Data were extracted according to a pre-specified protocol to capture study characteristics and AI design; the objectives and performance outcome metrics were summarised. Results: Systematic database searches returned 568 articles, 40 ultimately included in this review. AI to support preoperative difficulty assessments were identified across eight domains (direct surgical difficulty grading, extramural vascular invasion (EMVI), lymph node metastasis (LNM), lymphovascular invasion (LVI), perineural invasion (PNI), T staging, and the requirement for multiple linear stapler firings. For each, at least one model was identified with very good performance (AUC scores of >0.80), with several showing excellent performance considerably above this threshold. Conclusions: AI tools applied to preoperative rectal MRI to support preoperative difficulty assessment for rectal cancer surgeries are emerging, with the progressing development and strong performance of many promising models. These warrant further clinical evaluation, which can aid personalised surgical approaches and ensure the adequate utilisation of limited resources.

Local excision can be a definitive treatment for T1 SM1 N0 rectal adenocarcinomas, but post-excision histology may reveal adverse features or more advanced tumour stage, requiring adjuvant treatment. For patients who are unfit or unwilling to undergo invasive surgery, Contact X-ray Brachytherapy (CXB) boost and external beam (chemo)radiotherapy [EB(C)RT] can be used as an alternative option to reduce recurrence risk. This study reports on patients who received post excision CXB with EB(C)RT between 2003 and 2020. It reports on lesion characteristics, excision techniques, and adjuvant treatment characteristics. Survival outcomes were compared across local excision techniques and radiotherapy schedules. Regression analysis was conducted to identify factors predictive of (local and distant) recurrence. In this cohort of 323 patients 5-year overall survival (OS) was 84.2 %, 3-year recurrence free survival (RFS) was 91.6 %, with 94.7 % disease-free and 95 % stoma-free. No significant differences were observed for 5-year OS and 3-year RFS between excision types (p = 0.10, p = 0.56) or radiotherapy schedules (p = 0.90, p = 0.13) respectively. Resection margin involvement tripled recurrence risk compared to R0 resections (OR = 3.67, 95 % CI: 1.13-16.42, p = 0.048). For high-risk pT1 tumours, post-excision treatment with EB(C)RT and CXB boost resulted in survival outcomes comparable to those reported with conversion to radical surgery. There were no significant differences in survival outcomes between radiotherapy schedules and local excision techniques. Involved resection margins were associated with a significantly increased recurrence risk. The clinical benefit of CXB should be formally evaluated in large, prospective studies.