Meetschen Mathias, Salhöfer Luca, Beck Nikolas, Kroll Lennard, Ziegenfuß Christoph David, Schaarschmidt Benedikt Michael, Forsting Michael, Mizan Shamoun, Umutlu Lale, Hosch René, Nensa Felix, Haubold Johannes
Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, 45147 Essen, Germany.
Institute for Artificial Intelligence in Medicine, University Hospital Essen, 45131 Essen, Germany.
Diagnostics (Basel). 2024 Mar 11;14(6):596. doi: 10.3390/diagnostics14060596.
: This study aimed to evaluate the impact of an AI-assisted fracture detection program on radiology residents' performance in pediatric and adult trauma patients and assess its implications for residency training. : This study, conducted retrospectively, included 200 radiographs from participants aged 1 to 95 years (mean age: 40.7 ± 24.5 years), encompassing various body regions. Among these, 50% (100/200) displayed at least one fracture, totaling one hundred thirty-five fractures, assessed by four radiology residents with different experience levels. A machine learning algorithm was employed for fracture detection, and the ground truth was established by consensus among two experienced senior radiologists. Fracture detection accuracy, reporting time, and confidence were evaluated with and without AI support. : Radiology residents' sensitivity for fracture detection improved significantly with AI support (58% without AI vs. 77% with AI, < 0.001), while specificity showed minor improvements (77% without AI vs. 79% with AI, = 0.0653). AI stand-alone performance achieved a sensitivity of 93% with a specificity of 77%. AI support for fracture detection significantly reduced interpretation time for radiology residents by an average of approximately 2.6 s ( = 0.0156) and increased resident confidence in the findings ( = 0.0013). : AI support significantly enhanced fracture detection sensitivity among radiology residents, particularly benefiting less experienced radiologists. It does not compromise specificity and reduces interpretation time, contributing to improved efficiency. This study underscores AI's potential in radiology, emphasizing its role in training and interpretation improvement.
本研究旨在评估人工智能辅助骨折检测程序对放射科住院医师在儿科和成人创伤患者中的表现的影响，并评估其对住院医师培训的意义。本研究为回顾性研究，纳入了年龄在1至95岁（平均年龄：40.7±24.5岁）的参与者的200张X光片，涵盖身体各个部位。其中，50%（100/200）显示至少一处骨折，共计135处骨折，由四名经验水平不同的放射科住院医师进行评估。采用机器学习算法进行骨折检测，由两名经验丰富的资深放射科医生达成共识确定真实情况。在有无人工智能支持的情况下，对骨折检测准确性、报告时间和信心进行了评估。放射科住院医师在人工智能支持下骨折检测的敏感性显著提高（无人工智能时为58%，有人工智能时为77%，<0.001），而特异性略有提高（无人工智能时为77%，有人工智能时为79%，=0.0653）。人工智能单独的表现达到了93%的敏感性和77%的特异性。人工智能对骨折检测的支持显著减少了放射科住院医师的平均解读时间约2.6秒（=0.0156），并提高了住院医师对检查结果的信心（=0.0013）。人工智能支持显著提高了放射科住院医师的骨折检测敏感性，尤其使经验不足的放射科医生受益。它不会损害特异性，还能减少解读时间，有助于提高效率。本研究强调了人工智能在放射学中的潜力，突出了其在培训和解读改进方面的作用。
