Background: Colonoscopy, a crucial diagnostic tool in gastroenterology, depends heavily on superior bowel preparation. ChatGPT, a large language model with emergent intelligence which also exhibits potential in medical applications. This study aims to assess the accuracy and consistency of ChatGPT in using the Boston Bowel Preparation Scale (BBPS) for colonoscopy assessment. Methods: We retrospectively collected 233 colonoscopy images from 2020 to 2023. These images were evaluated using the BBPS by 3 senior endoscopists and 3 novice endoscopists. Additionally, ChatGPT also assessed these images, having been divided into three groups and undergone specific Fine-tuning. Consistency was evaluated through two rounds of testing. Results: In the initial round, ChatGPT's accuracy varied between 48.93% and 62.66%, trailing the endoscopists' accuracy of 76.68% to 77.83%. Kappa values for ChatGPT was between 0.52 and 0.53, compared to 0.75 to 0.87 for the endoscopists. Conclusion: While ChatGPT shows promise in bowel preparation scoring, it currently does not match the accuracy and consistency of experienced endoscopists. Future research should focus on in-depth Fine-tuning.

Optimal bowel preparation is a prerequisite for a successful colonoscopy; however, the rate of inadequate bowel preparation remains relatively high. In this study, we establish a smartphone app that assesses patient bowel preparation using an artificial intelligence (AI)-based prediction system trained on labeled photographs of feces in the toilet and evaluate its impact on bowel preparation quality in colonoscopy outpatients. We conduct a prospective, single-masked, multicenter randomized clinical trial, enrolling outpatients who own a smartphone and are scheduled for a colonoscopy. We screen 578 eligible patients and randomize 524 in a 1:1 ratio to the control or AI-driven app group for bowel preparation. The study endpoints are the percentage of patients with adequate bowel preparation and the total BBPS score, compliance with dietary restrictions and purgative instructions, polyp detection rate, and adenoma detection rate (secondary). The prediction system has an accuracy of 95.15%, a specificity of 97.25%, and an area under the curve of 0.98 in the test dataset. In the full analysis set (n = 500), adequate preparation is significantly higher in the AI-driven app group (88.54 vs. 65.59%; P < 0.001). The mean BBPS score is 6.74 ± 1.25 in the AI-driven app group and 5.97 ± 1.81 in the control group (P < 0.001). The rates of compliance with dietary restrictions (93.68 vs. 83.81%, P = 0.001) and purgative instructions (96.05 vs. 84.62%, P < 0.001) are significantly higher in the AI-driven app group, as is the rate of additional purgative intake (26.88 vs. 17.41%, P = 0.011). Thus, our AI-driven smartphone app significantly improves the quality of bowel preparation and patient compliance.

For our HTN Now: Citizen Transformation event we were joined by Ben Panton, Senior Digital Partnership Manager for NHS Arden and GEM Commissioning Support Unit, for a discussion on developments in home diagnostics, with focus on the latest trial plans and patient reactions and perceptions around remote diagnostics and artificial intelligence. Ben began by establishing some background information on NHS Arden and GEM CSU, explaining that they work with over 90 organisations across health and care systems such as local authorities, ICBs, trusts and primary care services. "I'm particularly focused on the digital transformation side of things," he said. "I've been in post for around six months now, working with colleagues across our digital and IT teams. Our particular focus within digital transformation service redesign has been working with potential partners such as the ICBs, to really understand their digital priorities and challenges, and how digital solutions can potentially mitigate some of the challenges that are being faced by the NHS, social care, and local authorities."