Unità Operativa Di Radiologia Diagnostica E Interventistica, IRCCS Istituto Ortopedico Galeazzi, 20161, Milan, Italy.
Dipartimento Di Scienze Biomediche Per La Salute, Università Degli Studi Di Milano, 20133, Milan, Italy.
Radiol Med. 2023 Mar;128(3):340-346. doi: 10.1007/s11547-023-01608-7. Epub 2023 Feb 14.
To investigate whether artificial intelligence (AI) can differentiate septic from non-septic total hip arthroplasty (THA) failure based on preoperative MRI features.
We included 173 patients (98 females, age: 67 ± 12 years) subjected to first-time THA revision surgery after preoperative pelvis MRI. We divided the patients into a training/validation/internal testing cohort (n = 117) and a temporally independent external-testing cohort (n = 56). MRI features were used to train, validate and test a machine learning algorithm based on support vector machine (SVM) to predict THA infection on the training-internal validation cohort with a nested fivefold validation approach. Machine learning performance was evaluated on independent data from the external-testing cohort.
MRI features were significantly more frequently observed in THA infection (P < 0.001), except bone destruction, periarticular soft-tissue mass, and fibrous membrane (P > 0.005). Considering all MRI features in the training/validation/internal-testing cohort, SVM classifier reached 92% sensitivity, 62% specificity, 79% PPV, 83% NPV, 82% accuracy, and 81% AUC in predicting THA infection, with bone edema, extracapsular edema, and synovitis having been the best predictors. After being tested on the external-testing cohort, the classifier showed 92% sensitivity, 79% specificity, 89% PPV, 83% NPV, 88% accuracy, and 89% AUC in predicting THA infection. SVM classifier showed 81% sensitivity, 76% specificity, 66% PPV, 88% NPV, 80% accuracy, and 74% AUC in predicting THA infection in the training/validation/internal-testing cohort based on the only presence of periprosthetic bone marrow edema on MRI, while it showed 68% sensitivity, 89% specificity, 93% PPV, 60% NPV, 75% accuracy, and 79% AUC in the external-testing cohort.
AI using SVM classifier showed promising results in predicting THA infection based on MRI features. This model might support radiologists in identifying THA infection.
研究人工智能（AI）是否可以根据术前 MRI 特征来区分感染性和非感染性全髋关节置换（THA）失败。
我们纳入了 173 名（98 名女性，年龄：67±12 岁）接受初次 THA 翻修手术的患者，这些患者均接受过术前骨盆 MRI 检查。我们将患者分为训练/验证/内部测试队列（n=117）和时间独立的外部测试队列（n=56）。使用机器学习算法（基于支持向量机[SVM]）基于术前 MRI 特征来训练、验证和测试，以嵌套五重验证方法来预测训练-内部验证队列中的 THA 感染。使用外部测试队列中的独立数据评估机器学习性能。
MRI 特征在 THA 感染中更频繁地出现（P<0.001），除了骨破坏、关节周围软组织肿块和纤维膜（P>0.005）。考虑到训练/验证/内部测试队列中的所有 MRI 特征，SVM 分类器在预测 THA 感染时的敏感性为 92%，特异性为 62%，阳性预测值为 79%，阴性预测值为 83%，准确率为 82%，曲线下面积（AUC）为 81%，其中骨水肿、关节外水肿和滑膜炎是最佳预测指标。在外部测试队列中进行测试后，该分类器在预测 THA 感染时的敏感性为 92%，特异性为 79%，阳性预测值为 89%，阴性预测值为 83%，准确率为 88%，AUC 为 89%。SVM 分类器在基于 MRI 中仅存在假体周围骨髓水肿的训练/验证/内部测试队列中预测 THA 感染的敏感性为 81%，特异性为 76%，阳性预测值为 66%，阴性预测值为 88%，准确率为 80%，AUC 为 74%，而在外部测试队列中的敏感性为 68%，特异性为 89%，阳性预测值为 93%，阴性预测值为 60%，准确率为 75%，AUC 为 79%。
基于 MRI 特征，使用 SVM 分类器的 AI 显示出预测 THA 感染的良好结果。该模型可能有助于放射科医生识别 THA 感染。
