While AI-assisted colonoscopy promises improved colorectal cancer screening, its success relies on effective integration into clinical practice, not just algorithmic accuracy. This paper, based on an Australian field study (observations and gastroenterologist interviews), highlights a critical disconnect: current development prioritizes machine learning model performance, overlooking essential aspects of user interface design, workflow integration, and overall user experience. Industry interactions reveal a similar emphasis on data and algorithms. To realize AI's full potential, the HCI community must champion user-centered design, ensuring these systems are usable, support endoscopist expertise, and enhance patient outcomes.

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.

The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text colonoscopy records from routine clinical practice, comprising millions of images and text reports, serve as a valuable data source, though annotating them is labour-intensive. Here we leverage recent advancements in large language and vision models and propose EndoKED, a data mining paradigm for deep knowledge extraction and distillation. EndoKED automates the transformation of raw colonoscopy records into image datasets with pixel-level annotation. We validate EndoKED using multi-centre datasets of raw colonoscopy records (~1 million images), demonstrating its superior performance in training polyp detection and segmentation models. Furthermore, the EndoKED pre-trained vision backbone enables data-efficient and generalisable learning for optical biopsy, achieving expert-level performance in both retrospective and prospective validation.

Early detection of colon cancer thanks to funds provided by the State Research Agency (AEI), an agency of the Ministry of Science and Innovation, which promotes scientific and technological research in all areas of knowledge through efficient allocation of public resources Leading project to install . Researchers from the University of Vigo and the Hospital Universitario de Ourense have developed an innovative detection system for colorectal polyps that uses artificial intelligence (AI) to detect them, as well as diagnose their degree of malignancy in real time, whether they are benign or tumor. The PolyDeep project started in 2018, promoted by the State Program Oriented to Society's Challenges, and ends in 2021. In total, the budget given to the project is 127,171 Euros and it is co-financed with the European Federated Fund and the Recovery, Transformation and Resilience Plan. The initiative is led by researchers Miguel Rebeiro Jato and Daniel González Peña from the New Generation Computer Systems (SING) group of Ourense Higher School of Computer Engineering, University of Vigo, in collaboration with the Research Group in Digestive Oncology.

We are surrounded by AI in our daily life whether it is the'Siri', 'Alexa', or the Google search engine. We have certainly come a long way from the'Turing test' in the 1950s, wherein the intelligent behaviour of computers was conceptualized leading to the present-day AI. The use of AI in Medicine (AIM) gained traction in the past decade and has met with both excitement in the scope of its use and also trepidation fearing the loss of the human element in the Art and Science of Medicine. Similar, to various subfields of Medicine the AI has its subfields of Machine learning (ML), Deep learning (DL) with Artificial Neural Network (ANN), Natural Language Processing (NLP), Computer Vision (CV). The use of AI in healthcare was slow to take off when compared to the non-medical commercial applications.

Laird Harrison writes about science, health and culture. His work has appeared in national magazines, in newspapers, on public radio and on websites. He is at work on a novel about alternate realities in physics. Harrison teaches writing at the Writers Grotto.

In mid-February, the Centre Hospitalier de Bigorre in Tarbes (Hautes-Pyrénées) organized the inauguration of an Artificial Intelligence module for digestive endoscopy, in order to optimize colorectal cancer screening: CAD EYE by Fujifilm. The hospital's endoscopy department has already been using it for a year and is witnessing the benefits of such a technological innovation for the care of patients in the Hautes Pyrénées. Colorectal cancer is the 3rd most common cancer after lung cancer and breast cancer, and the second most common cause of death by cancer after lung cancer. However, if detected at an early stage, colorectal cancer can be cured in 9 out of 10 cases, which is possible with colonoscopy (lower digestive endoscopy) for the detection of colon tumors. On the other hand, an accurate endoscopic diagnosis of colon polyps could reduce the number of unnecessary polypectomies. In March 2021, the endoscopy department was able to acquire the Fujifilm CAD EYE box equipped with artificial intelligence thanks to the financing and the important mobilization of the League against Cancer of the Hautes Pyrénées, the Departmental Council, the Lions Club and the Rotary Club, organizers of the Maxi Loto of Lourdes, for the benefit of cancer research.

Assessments of patients with ulcerative colitis (UC), which is a type of inflammatory bowel disease, are usually conducted via endoscopy and histology. But now, researchers from Japan have developed a system that may be more accurate than existing methods and may reduce the need for these patients to undergo invasive medical procedures. In a study published this February in Gastroenterology, researchers from Tokyo Medical and Dental University (TMDU) have revealed a newly developed artificial intelligence (AI) system that can evaluate endoscopic findings of UC with an accuracy equivalent to that of expert endoscopists. Accurate evaluations are critical in providing optimal care for patients with UC. Previous studies have indicated that both endoscopic remission, evaluated via assessment of endoscopic procedure, and histological remission, as indicated by the degree of microscopic inflammation, can predict patient outcomes, and are thus frequently used as treatment goals.

Researchers from Tokyo Medical and Dental University (TMDU) have developed an artificial intelligence system that effectively evaluates endoscopic mucosal findings from patients with ulcerative colitis without the need for biopsy collection. Assessments of patients with ulcerative colitis (UC), which is a type of inflammatory bowel disease, are usually conducted via endoscopy and histology. But now, researchers from Japan have developed a system that may be more accurate than existing methods and may reduce the need for these patients to undergo invasive medical procedures. In a study published this February in Gastroenterology, researchers from Tokyo Medical and Dental University (TMDU) have revealed a newly developed artificial intelligence (AI) system that can evaluate endoscopic findings of UC with an accuracy equivalent to that of expert endoscopists. Accurate evaluations are critical in providing optimal care for patients with UC.

I've been talking in recent posts about how our typical methods of testing AI systems are inadequate and potentially unsafe. In particular, I've complained that all of the headline-grabbing papers so far only do controlled experiments, so we don't how the AI systems will perform on real patients. Today I am going to highlight a piece of work that has not received much attention, but actually went "all the way" and tested an AI system in clinical practice, assessing clinical outcomes. They did an actual clinical trial! Big news … so why haven't you heard about it?