From data to artificial intelligence: evaluating the readiness of gastrointestinal endoscopy datasets

The incorporation of artificial intelligence (AI) into gastrointestinal (GI) endoscopy represents a promising advancement in gastroenterology. With over 40 published randomized controlled trials and numerous ongoing clinical trials, gastroenterology leads other medical disciplines in AI research. Computer-aided detection algorithms for identifying colorectal polyps have achieved regulatory approval and are in routine clinical use, while other AI applications for GI endoscopy are in advanced development stages. Near-term opportunities include the potential for computer-aided diagnosis to replace conventional histopathology for diagnosing small colon polyps and increased AI automation in capsule endoscopy. Despite significant development in research settings, the generalizability and robustness of AI models in real clinical practice remain inconsistent. The GI field lags behind other medical disciplines in the breadth of novel AI algorithms, with only 13 out of 882 Food and Drug Administration (FDA)-approved AI models focussed on GI endoscopy as of June 2024. Additionally, existing GI endoscopy image databases are disproportionately focussed on colon polyps, lacking representation of the diversity of other endoscopic findings. High-quality datasets, encompassing a wide range of patient demographics, endoscopic equipment types, and disease states, are crucial for developing effective AI models for GI endoscopy. This article reviews the current state of GI endoscopy datasets, barriers to progress, including dataset size, data diversity, annotation quality, and ethical issues in data collection and usage, and future needs for advancing AI in GI endoscopy. Artificial intelligence (AI) is becoming a key tool in gastrointestinal (GI) endoscopy. Over 40 clinical trials have been completed, and many more are happening now. Gastroenterology is using AI more than other medical fields. AI tools help doctors find colon polyps, which can turn into cancer. Some of these tools are already used in clinics. Researchers are also making AI tools that might diagnose colon polyps without needing a tissue sample. Other AI tools might help make capsule endoscopy easier. This is where a tiny camera is swallowed to take pictures of the digestive system. But there are still problems. AI models that work well in studies don't always work as well in real life. By June 2024, the Food and Drug Administration (FDA) approved 882 AI tools, but only 13 were for GI endoscopy. Current image databases used to train AI mostly focus on colon polyps. This means they miss other important findings and diseases in the digestive system. To make AI better in GI endoscopy, we need better datasets. These should include many different patients, types of endoscopy tools, and diseases. This article talks about the current state of GI endoscopy data, the problems we face, and what we need to improve AI in this area.