首页|Southern Medical University Reports Findings in Artificial Intelligence (Artific ial intelligence-assisted system for the assessment of Forrest classification of peptic ulcer bleeding: a multicenter diagnostic study)
Southern Medical University Reports Findings in Artificial Intelligence (Artific ial intelligence-assisted system for the assessment of Forrest classification of peptic ulcer bleeding: a multicenter diagnostic study)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating from Guang zhou, People's Republic of China, by NewsRx correspondents, research stated, "In accurate Forrest classification may significantly affect clinical outcomes, espe cially in high risk patients. Therefore, this study aimed to develop a real-time deep convolutional neural network (DCNN) system to assess the Forrest classific ation of peptic ulcer bleeding (PUB)." Our news editors obtained a quote from the research from Southern Medical Univer sity, "A training dataset (3868 endoscopic images) and an internal validation da taset (834 images) were retrospectively collected from the 900th Hospital, Fuzho u, China. In addition, 521 images collected from four other hospitals were used for external validation. Finally, 46 endoscopic videos were prospectively collec ted to assess the real-time diagnostic performance of the DCNN system, whose dia gnostic performance was also prospectively compared with that of three senior an d three junior endoscopists. The DCNN system had a satisfactory diagnostic perfo rmance in the assessment of Forrest classification, with an accuracy of 91.2 % (95%CI 89.5%-92.6%) and a macro-average a rea under the receiver operating characteristic curve of 0.80 in the validation dataset. Moreover, the DCNN system could judge suspicious regions automatically using Forrest classification in real-time videos, with an accuracy of 92.0% (95%CI 80.8%-97.8%). The DCNN system show ed more accurate and stable diagnostic performance than endoscopists in the pros pective clinical comparison test. This system helped to slightly improve the dia gnostic performance of senior endoscopists and considerably enhance that of juni or endoscopists. The DCNN system for the assessment of the Forrest classificatio n of PUB showed satisfactory diagnostic performance, which was slightly superior to that of senior endoscopists."
GuangzhouPeople's Republic of ChinaA siaArtificial IntelligenceDigestive System Diseases and ConditionsEmerging TechnologiesGastroenterologyGastrointestinal Diseases and ConditionsHealt h and MedicineMachine LearningPeptic UlcersStomach Diseases and Conditions
NETL
NSTL
