South West London Elective Orthopaedic Centre, Epsom, UK.
Barzilai Medical Centre, Ashkelon, Israel.
Bone Joint J. 2022 Aug;104-B(8):929-937. doi: 10.1302/0301-620X.104B8.BJJ-2022-0120.R2.
Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are.
The Embase, MEDLINE, and PubMed libraries were systematically searched to identify relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews and Arksey and O'Malley framework were followed. Study quality was assessed using a modified Methodological Index for Non-Randomized Studies tool. AI performance was reported using either the area under the curve (AUC) or accuracy.
Of the 455 studies identified, only 12 were suitable for inclusion. Nine reported implant identification and three described predicting risk of implant failure. Of the 12, three studies compared AI performance with orthopaedic surgeons. AI-based implant identification achieved AUC 0.992 to 1, and most algorithms reported an accuracy > 90%, using 550 to 320,000 training radiographs. AI prediction of dislocation risk post-THA, determined after five-year follow-up, was satisfactory (AUC 76.67; 8,500 training radiographs). Diagnosis of hip implant loosening was good (accuracy 88.3%; 420 training radiographs) and measurement of postoperative acetabular angles was comparable to humans (mean absolute difference 1.35° to 1.39°). However, 11 of the 12 studies had several methodological limitations introducing a high risk of bias. None of the studies were externally validated.
These studies show that AI is promising. While it already has the ability to analyze images with significant precision, there is currently insufficient high-level evidence to support its widespread clinical use. Further research to design robust studies that follow standard reporting guidelines should be encouraged to develop AI models that could be easily translated into real-world conditions. Cite this article: 2022;104-B(8):929-937.
全髋关节置换术（THA）和全膝关节置换术（TKA）是常见的骨科手术，需要术后 X 光片来确认植入物的位置和识别并发症。基于人工智能（AI）的图像分析有可能实现这种术后监测的自动化。本研究旨在进行范围综述，以调查 AI 在 THA 和 TKA 术后 X 光片分析中的应用，以及这些工具的准确性如何。
系统检索了 Embase、MEDLINE 和 PubMed 数据库，以确定相关文章。遵循扩展后的系统综述和 Meta 分析首选报告项目和 Arksey 和 O'Malley 框架。使用改良的非随机研究方法学指数工具评估研究质量。使用曲线下面积（AUC）或准确性报告 AI 性能。
在 455 项研究中，只有 12 项适合纳入。其中 9 项报告了植入物的识别，3 项描述了预测植入物失败的风险。在这 12 项研究中，有 3 项研究将 AI 性能与骨科医生进行了比较。基于 AI 的植入物识别的 AUC 为 0.992 至 1，大多数算法报告的准确性>90%，使用了 550 至 32000 张训练 X 光片。THA 后五年随访时，对脱位风险的 AI 预测是令人满意的（AUC 为 76.67；8500 张训练 X 光片）。髋关节植入物松动的诊断准确性较高（准确性为 88.3%；420 张训练 X 光片），术后髋臼角度的测量与人工测量相当（平均绝对差异为 1.35°至 1.39°）。然而，这 12 项研究中有 11 项存在几个方法学局限性，存在较高的偏倚风险。没有一项研究进行了外部验证。
这些研究表明 AI 具有广阔的前景。虽然它已经具备了高精度分析图像的能力，但目前还没有足够的高级别证据支持其广泛的临床应用。应鼓励进一步开展设计稳健的研究，遵循标准报告指南，以开发易于转化为实际情况的 AI 模型。
