Background:Most clinical machine learning applications use a supervised learning approach using labeled variables. In contrast, unsupervised learning enables pattern detection without a prespecified outcome.Purpose/Hypothesis:The purpose of this study was to apply unsupervised learning to the combined Danish and Norwegian knee ligament register (KLR) with the goal of detecting distinct subgroups. It was hypothesized that resulting groups would have differing rates of subsequent anterior cruciate ligament reconstruction (ACLR) revision.Study Design:Cohort study; Level of evidence, 3.Methods:K-prototypes clustering was performed on the complete case KLR data. After performing the unsupervised learning analysis, the authors defined clinically relevant characteristics of each cluster using variable summaries, surgeons’ domain knowledge, and Shapley Additive exPlanations analysis.Results:Five clusters were identified. Cluster 1 (revision rate, 9.9%) patients were young (mean age, 22 years; SD, 6 years), received hamstring tendon (HT) autograft (91%), and had lower baseline Knee injury and Osteoarthritis Outcome Score (KOOS) Sport and Recreation (Sports) scores (mean, 25.0; SD, 15.6). Cluster 2 (revision rate, 6.9%) patients received HT autograft (89%) and had higher baseline KOOS Sports scores (mean, 67.2; SD, 16.5). Cluster 3 (revision rate, 4.7%) patients received bone–patellar tendon–bone (BPTB) or quadriceps tendon (QT) autograft (94%) and had higher baseline KOOS Sports scores (mean, 65.8; SD, 16.4). Cluster 4 (revision rate, 4.1%) patients received BPTB or QT autograft (88%) and had low baseline KOOS Sports scores (mean, 20.5; SD, 14.0). Cluster 5 (revision rate, 3.1%) patients were older (mean age, 42 years; SD, 7 years), received HT autograft (89%), and had low baseline KOOS Sports scores (mean, 23.4; SD, 17.6).Conclusion:Unsupervised learning identified 5 distinct KLR patient subgroups and each grouping was associated with a unique ACLR revision rate. Patients can be approximately classified into 1 of the 5 clusters based on only 3 variables: age, graft choice (HT, BPTB, or QT autograft), and preoperative KOOS Sports subscale score. If externally validated, the resulting groupings may enable quick risk stratification for future patients undergoing ACLR in the clinical setting. Patients in cluster 1 are considered high risk (9.9%), cluster 2 patients medium risk (6.9%), and patients in clusters 3 to 5 low risk (3.1%-4.7%) for revision ACLR.

中文翻译：

---

丹麦和挪威联合膝关节韧带登记的无监督机器学习：识别具有不同 ACL 修复率的 5 个不同患者组

背景：大多数临床机器学习应用都使用使用标记变量的监督学习方法。相比之下，无监督学习可以在没有预先指定结果的情况下进行模式检测。 目的/假设：本研究的目的是将无监督学习应用于丹麦和挪威的膝关节韧带登记（KLR），目的是检测不同的亚组。假设所得组的后续前交叉韧带重建 (ACLR) 翻修率不同。 研究设计：队列研究；证据级别，3。方法：对完整病例KLR数据进行K原型聚类。在进行无监督学习分析后，作者使用变量摘要、外科医生的领域知识和 Shapley 加性解释分析来定义每个簇的临床相关特征。结果：识别出五个簇。第 1 类（翻修率，9.9%）患者很年轻（平均年龄，22 岁；标准差，6 岁），接受了自体腘绳肌腱 (HT) 移植 (91%)，膝关节损伤和骨关节炎结果评分 (KOOS) 基线较低体育和休闲（体育）得分（平均值，25.0；标准差，15.6）。第 2 类（修正率，6.9%）患者接受了自体 HT 移植（89%），并且具有较高的基线 KOOS 运动评分（平均值，67.2；SD，16.5）。第 3 类（修正率，4.7%）患者接受了骨-髌腱-骨（BPTB）或股四头肌腱（QT）自体移植（94%），并且具有较高的基线 KOOS 运动评分（平均值，65.8；SD，16.4）。第 4 组（修正率，4.1%）患者接受 BPTB 或 QT 自体移植（88%），并且基线 KOOS 运动评分较低（平均值，20.5；SD，14.0）。第 5 组（翻修率，3.1%）患者年龄较大（平均年龄，42 岁；标准差，7 岁），接受自体 HT 移植（89%），并且基线 KOOS 运动评分较低（平均年龄，23.4；标准差，17.6）。结论：无监督学习确定了 5 个不同的 KLR 患者亚组，每个组都与独特的 ACLR 修订率相关。仅根据 3 个变量，即可将患者大致分为 5 个组中的 1 个：年龄、移植物选择（HT、BPTB 或 QT 自体移植物）和术前 KOOS 运动子量表评分。如果经过外部验证，所得分组可能能够对未来在临床环境中接受 ACLR 的患者进行快速风险分层。对于修订 ACLR，聚类 1 中的患者被认为是高风险 (9.9%)，聚类 2 中的患者被认为是中等风险 (6.9%)，聚类 3 至 5 中的患者被认为是低风险 (3.1%-4.7%)。