The Central European Journal of Urology is an open access quarterly-issued journal, which provides a forum for the presentation of original clinical, experimental and other research studies...
Perianal fistulizing Crohn’s disease (pfCD) represents a severe manifestation of Crohn’s disease (CD) that often leads to significant morbidity. Clinical examination alone of perianal fistulae is unlikely to be sufficient in the context of complex pfCD, as patients are likely to have complex disease and are more likely to experience complications, treatment failure, and recurrent disease. Furthermore, the relapsing–remitting nature of Crohn’s disease and our limited understanding of the pathogenesis of this potentially destructive disease necessitate regular examination and radiological assessment, often in the form of magnetic resonance imaging (MRI). Recent advancements in diagnostic techniques have enhanced the accuracy and timeliness of pfCD diagnosis, facilitating better patient outcomes. A growing appreciation of isolated perianal Crohn’s disease has prompted a recent attempt to develop consensus recommendations on diagnosing and treating this group of patients who would previously not have been offered CD medications. This narrative review aims to summarize current practice and the latest developments in the diagnosis of pfCD, highlighting: Clinical examination and assessment tools Current imaging practices Innovations in imaging and biomarkers The diagnosis of isolated perianal Crohn’s disease.
Perianal Crohn’s disease (pCD) is a complex manifestation of Crohn’s disease. Classifying this patient cohort for both clinical purposes and for inclusion into research trials is challenging but crucial in order to improve outcomes. This review provides an overview of historical classifications of both fistulising and non-fistulising pCD, including the Park’s, Cardiff–Hughes and American Gastroenterological Association (AGA) classifications, as well as recent advances including the Treatment Optimisation and CLASSification of perianal Crohn’s disease (TOpClass) classification of fistulising pCD. Secondly, this article provides a scoping review of recent trials in pCD and describes how the cohorts in these trials relate to the TOpClass classification. Of the 19 studies relating to pCD that were identified, four could be confidently classified as class 2a. Seven could be classified as class 2a or 2b, but it was not possible to subdivide further, and seven to class 2a, 2b or 2c, but it was not possible to subdivide further. One study population was classified as class 2a or 2c. In eight studies, it was not specified whether patients with a defunctioning stoma were included or excluded. This review demonstrates the heterogeneous nature of some patient cohorts in previous clinical trials, and how the TOpClass classification may be used to group patients more accurately for clinical use and inclusion in research trials.
Background/Objectives: Large Language Models (LLMs) may help translate complex Magnetic Resonance Imaging (MRI) fistula reports into accessible, patient-friendly summaries. This study evaluated the clinical utility, safety, and patient acceptability of Generative Pre-trained Transformer (GPT-4o) in generating such reports. Methods: A three-phase study was conducted at a single centre. Phase I involved prompt engineering and pilot testing of GPT-4o outputs for feasibility. Phase II assessed 250 consecutive MRI fistula reports from September 2024 to November 2024, each reviewed by a multi-disciplinary panel to determine hallucinations and thematic content. Phase III randomised patients to review either a simple or complex fistula case, each containing an original report and an Artificial Intelligence (AI)-generated summary (order randomised, origin blinded), and rate readability, trustworthiness, usefulness and comprehension. Results: Sixteen patients participated in Phase I pilot testing. In Phase II, hallucinations occurred in 11% of outputs, with unverified recommendations also identified. In Phase III, 61 patients (mean age 48, 41% female) evaluated paired original and AI-generated summaries. AI summaries scored significantly higher for readability, comprehension, and usefulness than original reports (all p < 0.001), with equivalent trust ratings. Mean Flesch-Kincaid scores were markedly higher for AI-generated summaries (66 vs. 26; p < 0.001). Clinicians highlighted improved anatomical structuring and accessible language, but emphasised risks of inaccuracies. A revised template incorporating Multi-Disciplinary Team (MDT)-focused action points and a lay summary section was co-developed. Conclusions: LLMs can enhance the readability and patient understanding of complex MRI reports but remain limited by hallucinations and inconsistent terminology. Safe implementation requires structured oversight, domain-specific refinement, and clinician validation. Future development should prioritise standardised reporting templates incorporating clinician-approved lay summaries.