预测10年全髋关节置换风险的可用可解释机器学习模型
研究基于骨关节炎倡议队列的4796例患者(9592髋,230例THA,2.4%),开发并验证预测10年内全髋关节置换(THA)的机器学习模型。仅用人口学与临床变量时AUROC为0.68,仅用深度学习自动测量的26项髋部影像学变量时AUROC为0.77,联合所有变量后AUROC提升至0.81;联合模型中前5位预测特征有3项为影像学变量,包括最小关节间隙、髋部疼痛和镇痛药使用。
要点
- 联合人口学、临床和深度学习影像学变量预测10年THA的AUROC为0.81。
- 仅用影像学变量时AUROC为0.77,优于仅用人口学与临床变量的0.68。
- 联合模型前5位预测特征中3项为影像学变量,包括最小关节间隙。
核心结论
- 使用深度学习影像学测量时,预测10年THA的机器学习模型表现更准确。
- 模型对预测变量的权重与临床THA病理评估一致。
研究设计与样本
- 纳入骨关节炎倡议队列的患者,共4796例患者(9592髋;58%女性;230例THA,2.4%)。
- 开发深度学习算法在基线骨盆X线片上测量骨关节炎和髋发育不良相关参数。
- 使用人口学、临床和影像学测量变量训练广义相加模型,预测自基线起10年内THA。
- 比较仅人口学与临床变量、仅影像学变量及联合所有变量三种模型的性能。
主要发现
- 使用110个人口学与临床变量时,基线AUROC为0.68,AUPRC为0.08。
- 使用26项深度学习自动髋部测量时,AUROC为0.77,AUPRC为0.22。
- 联合所有变量时,模型AUROC提升至0.81,AUPRC为0.28。
- 联合模型前5位预测特征中有3项为影像学变量,包括最小关节间隙、髋部疼痛和镇痛药使用。
- 偏依赖图显示影像学测量存在预测不连续点,与文献中骨关节炎进展和髋发育不良的阈值一致。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: As the demand for total hip arthroplasty (THA) rises, a predictive model for THA risk may aid patients and clinicians in augmenting shared decision-making. We aimed to develop and validate a model predicting THA within 10 years in patients using demographic, clinical, and deep learning (DL)-automated radiographic measurements. METHODS: Patients enrolled in the osteoarthritis initiative were included. DL algorithms measuring osteoarthritis- and dysplasia-relevant parameters on baseline pelvis radiographs were developed. Demographic, clinical, and radiographic measurement variables were then used to train generalized additive models to predict THA within 10 years from baseline. A total of 4,796 patients were included [9,592 hips; 58% female; 230 THAs (2.4%)]. Model performance using 1) baseline demographic and clinical variables 2) radiographic variables, and 3) all variables was compared. RESULTS: Using 110 demographic and clinical variables, the model had a baseline area under the receiver operating curve (AUROC) of 0.68 and area under the precision recall curve (AUPRC) of 0.08. Using 26 DL-automated hip measurements, the AUROC was 0.77 and AUPRC was 0.22. Combining all variables, the model improved to an AUROC of 0.81 and AUPRC of 0.28. Three of the top five predictive features in the combined model were radiographic variables, including minimum joint space, along with hip pain and analgesic use. Partial dependency plots revealed predictive discontinuities for radiographic measurements consistent with literature thresholds of osteoarthritis progression and hip dysplasia. CONCLUSION: A machine learning model predicting 10-year THA performed more accurately with DL radiographic measurements. The model weighted predictive variables in concordance with clinical THA pathology assessments.
引用
- Jang SJ, Fontana MA, Kunze KN, et al. An Interpretable Machine Learning Model for Predicting 10-Year Total Hip Arthroplasty Risk. J Arthroplasty. 2023. PMID: 37019312. doi:10.1016/j.arth.2023.03.087
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。