M Yogendra Praveen, Goh Adriel Guang Wei, Yee Sze Ying, Jawan Freda, Koh Kelvin Kay Nguan, Tan Timothy Shao Ern, Woon Tian Kai, Yeap Phey Ming, Tan Min On
Department of Radiology, Sengkang General Hospital, Singapore, Singapore
Department of Radiology, Sengkang General Hospital, Singapore, Singapore.
BMJ Health Care Inform. 2024 Dec 5;31(1):e101091. doi: 10.1136/bmjhci-2024-101091.
We aim to evaluate the accuracy of radiologists and radiology residents in the detection of paediatric appendicular fractures with and without the help of a commercially available fracture detection artificial intelligence (AI) solution in the hopes of showing potential clinical benefits in a general hospital setting.
This was a retrospective study involving three associate consultants (AC) and three senior residents (SR) in radiology, who acted as readers. One reader from each human group interpreted the radiographs with the aid of AI. Cases were categorised into concordant and discordant cases between each interpreting group. Discordant cases were further evaluated by three independent subspecialty radiology consultants to determine the final diagnosis. A total of 500 anonymised paediatric patient cases (aged 2-15 years) who presented to a tertiary general hospital with a Children's emergency were retrospectively collected. Main outcome measures include the presence of fracture, accuracy of readers with and without AI, and total time taken to interpret the radiographs.
The AI solution alone showed the highest accuracy (area under the receiver operating characteristic curve 0.97; AC: 95% CI -0.055 to 0.320, p=0; SR: 95% CI 0.244 to 0.598, p=0). The two readers aided with AI had higher area under curves compared with readers without AI support (AC: 95% CI -0.303 to 0.465, p=0; SR: 95% CI -0.154 to 0.331, p=0). These differences were statistically significant.
Our study demonstrates excellent results in the detection of paediatric appendicular fractures using a commercially available AI solution. There is potential for the AI solution to function autonomously.
我们旨在评估放射科医生和放射科住院医师在有无市售骨折检测人工智能（AI）解决方案帮助的情况下检测小儿四肢骨折的准确性，以期在综合医院环境中展现潜在的临床益处。
这是一项回顾性研究，涉及三名放射科副顾问（AC）和三名放射科高级住院医师（SR）作为阅片者。每组中的一名阅片者借助AI解读X光片。将每组解读结果分为一致和不一致的病例。不一致的病例由三名独立的放射科亚专业顾问进一步评估以确定最终诊断。回顾性收集了500例匿名的儿科患者病例（年龄2至15岁），这些病例因儿童急诊就诊于一家三级综合医院。主要观察指标包括骨折的存在情况、有无AI辅助时阅片者的准确性以及解读X光片所需的总时间。
单独使用AI解决方案时显示出最高的准确性（受试者工作特征曲线下面积为0.97；AC：95%置信区间-0.055至0.320，p = 0；SR：95%置信区间0.244至0.598，p = 0）。与没有AI支持的阅片者相比，两名有AI辅助的阅片者曲线下面积更高（AC：95%置信区间-0.303至0.465，p = 0；SR：95%置信区间-0.154至0.331，p = 0）。这些差异具有统计学意义。
我们的研究表明，使用市售AI解决方案检测小儿四肢骨折取得了优异结果。该AI解决方案有自主发挥作用的潜力。
