基于人工智能的新诊断模型的开发和临床评估
Mustafa Alper Akay1, Ozan Can Tatar2,3, Semih Metin1
1Department of Pediatric Surgery, School of Medicine, Kocaeli University, Izmit, Turkey.
Updates in surgery
|September 5, 2025
概括
这项研究开发了一种用于诊断Hirschsprung的AI模型.
科学领域:
- 儿童胃肠病学
- 医学成像分析
- 医疗保健中的人工智能
背景情况:
- 希尔施普朗格病 (HD) 诊断传统上依赖于侵入性方法.
- 形成对比的阴道 (CE) 图像是HD的关键诊断工具.
- 提高诊断准确性和减少HD诊断的侵入性至关重要.
研究的目的:
- 开发和验证基于人工智能的深度学习模型,用于使用CE图像诊断赫施普朗格病.
- 提高诊断的准确性,减少HD诊断的侵袭性.
- 探索人工智能在儿科胃肠病学中的有用性,用于初步的HD查.
主要方法:
- 使用了725张基因病理确诊的赫斯普朗格病 (HD) 患者的对照阴道镜图像.
- 使用Python和PyTorch进行了深度学习模型YOLOv8的训练和验证.
- 使用包括平均精度 (mAP),精度,回忆和F1分数在内的指标来评估性能.
主要成果:
- 人工智能模型实现了高精度 (0.87477) 和回忆 (0.87317) 的mAP50得分为0.91.
- 外部验证显示灵敏度为86. 96%,特异性为72. 22%,整体准确度为80. 49%.
- 这种模型显示出精确且不太侵袭的HD诊断的巨大潜力.
结论:
- 一个使用CE图像的人工智能驱动的深度学习模型为希尔施普朗格病提供了有希望的,不那么侵袭的诊断方法.
- 这种人工智能模型可以作为儿童胃肠病的初步查的有效工具.
- 在医疗诊断中整合人工智能有可能改善患者的治疗结果和医疗效率.
相关概念视频
Assessment of the Rectum and Anus
399
Evaluating the rectum and anus plays a crucial role in conducting a thorough physical examination of the gastrointestinal system. Although it may be uncomfortable and often embarrassing for the patient, it holds immense diagnostic value, particularly in detecting gastrointestinal diseases and abnormalities. This guide will explain how to perform this assessment using inspection and palpation methods.
Rectal Inspection
Begin by inspecting the perianal and anal areas for color, texture, rashes,...
Rectal Inspection
Begin by inspecting the perianal and anal areas for color, texture, rashes,...
399
Irritable Bowel Syndrome II: Clinical Features and Diagnostic Evaluation
232
Irritable Bowel Syndrome II: Clinical Features and Diagnostic Evaluation
Irritable Bowel Syndrome (IBS) is classified into subtypes based on the predominant bowel habits as determined by the Bristol Stool Form Scale (BSFS). The subtypes are:
Irritable Bowel Syndrome (IBS) is classified into subtypes based on the predominant bowel habits as determined by the Bristol Stool Form Scale (BSFS). The subtypes are:
232


