Department of Orthopaedic Surgery, Bone and Joint Sports Medicine Center, Naval Medical Center Portsmouth, Portsmouth, VA, USA.
Department of Anesthesiology and Pain Medicine, Naval Medical Center Portsmouth, Portsmouth, VA, USA.
Clin Orthop Relat Res. 2022 Nov 1;480(11):2137-2145. doi: 10.1097/CORR.0000000000002276. Epub 2022 Jun 20.
Aseptic revision THA and TKA are associated with an increased risk of adverse outcomes compared with primary THA and TKA. Understanding the risk profiles for patients undergoing aseptic revision THA or TKA may provide an opportunity to decrease the risk of postsurgical complications. There are risk stratification tools for postoperative complications after aseptic revision TKA or THA; however, current tools only include nonmodifiable risk factors, such as medical comorbidities, and do not include modifiable risk factors.
QUESTIONS/PURPOSES: (1) Can machine learning predict 30-day mortality and complications for patients undergoing aseptic revision THA or TKA using a cohort from the American College of Surgeons National Surgical Quality Improvement Program database? (2) Which patient variables are the most relevant in predicting complications?
This was a temporally validated, retrospective study analyzing the 2014 to 2019 National Surgical Quality Improvement Program database, as this database captures a large cohort of aseptic revision THA and TKA patients across a broad range of clinical settings and includes preoperative laboratory values. The training data set was 2014 to 2018, and 2019 was the validation data set. Given that predictive models learn expected prevalence of outcomes, this split allows assessment of model performance in contemporary patients. Between 2014 and 2019, a total of 24,682 patients underwent aseptic revision TKA and 17,871 patients underwent aseptic revision THA. Of those, patients with CPT codes corresponding to aseptic revision TKA or THA were considered as potentially eligible. Based on excluding procedures involving unclean wounds, 78% (19,345 of 24,682) of aseptic revision TKA procedures and 82% (14,711 of 17,871) of aseptic revision THA procedures were eligible. Ten percent of patients in each of the training and validation cohorts had missing predictor variables. Most of these missing data were preoperative sodium or hematocrit (8% in both the training and validation cohorts). No patients had missing outcome data. No patients were excluded due to missing data. The mean patient was age 66 ± 12 years, the mean BMI was 32 ± 7 kg/m 2 , and the mean American Society of Anesthesiologists (ASA) Physical Score was 3 (56%). XGBoost was then used to create a scoring tool for 30-day adverse outcomes. XGBoost was chosen because it can handle missing data, it is nonlinear, it can assess nuanced relationships between variables, it incorporates techniques to reduce model complexity, and it has a demonstrated record of producing highly accurate machine-learning models. Performance metrics included discrimination and calibration. Discrimination was assessed by c-statistics, which describe the area under the receiver operating characteristic curve. This quantifies how well a predictive model discriminates between patients who have the outcome of interest versus those who do not. Relevant ranges for c-statistics include good (0.70 to 0.79), excellent (0.80 to 0.89), and outstanding (> 0.90). We estimated 95% confidence intervals (CIs) for c-statistics by 500-sample bootstrapping. Calibration curves quantify reliability of model predictions. Reliable models produce prediction probabilities for outcomes that are similar to observed probabilities of those outcomes, so a well-calibrated model should demonstrate a calibration curve that does not deviate substantially from a line of slope 1 and intercept 0. Calibration curves were generated on the 2019 validation data. Shapley Additive Explanations (SHAP) visualizations were used to investigate feature importance to gain insight into how models made predictions. The models were built into an online calculator for ongoing testing and validation. The risk calculator, which is freely available ( http://nb-group.org/rev2/ ), allows a user to input patient data to calculate postoperative risk of 30-day mortality, cardiac, and respiratory complications after aseptic revision TKA or THA. A post hoc analysis was performed to assess whether using data from 2020 would improve calibration on 2019 data.
The model accurately predicted mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA, with c-statistics of 0.88 (95% CI 0.83 to 0.93), 0.80 (95% CI 0.75 to 0.84), and 0.78 (95% CI 0.74 to 0.82), respectively, on internal validation and 0.87 (95% CI 0.77 to 0.96), 0.70 (95% CI 0.61 to 0.78), and 0.82 (95% CI 0.75 to 0.88), respectively, on temporal validation. Calibration curves demonstrated slight over-confidence in predictions (most predicted probabilities were higher than observed probabilities). Post hoc analysis of 2020 data did not yield improved calibration on the 2019 validation set. Important risk factors for all models included increased age and higher ASA, BMI, hematocrit level, and sodium level. Hematocrit and ASA were in the top three most important features for all models. The factor with the strongest association for mortality and cardiac complication models was age, and for the respiratory model, chronic obstructive pulmonary disease. Risk related to sodium followed a U-shaped curve. Preoperative hyponatremia and hypernatremia predicted an increased risk of mortality and respiratory complications, with a nadir of 138 mmol/L; hyponatremia was more strongly associated with mortality than hypernatremia. A hematocrit level less than 36% predicted an increased risk of all three adverse outcomes. A BMI less than 24 kg/m 2 -and especially less than 20 kg/m 2 -predicted an increased risk of all three adverse outcomes, with little to no effect for higher BMI.
This temporally validated model predicted 30-day mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA with c-statistics ranging from 0.78 to 0.88. This freely available risk calculator can be used preoperatively by surgeons to educate patients on their individual postoperative risk of these specific adverse outcomes. Unanswered questions that remain include whether altering the studied preoperative patient variables, such as sodium or hematocrit, would affect postoperative risk of adverse outcomes; however, a prospective cohort study is needed to answer this question.
Level III, therapeutic study.
与初次全髋关节置换术（THA）和初次全膝关节置换术（TKA）相比，无菌性翻修 THA 和 TKA 与不良结局的风险增加相关。了解无菌性翻修 THA 或 TKA 患者的风险特征，可能有助于降低术后并发症的风险。目前已有用于预测无菌性翻修 TKA 或 THA 术后并发症的风险分层工具；然而，目前的工具仅包括不可改变的风险因素，如合并症，且不包括可改变的风险因素。
问题/目的：（1）能否使用美国外科医师学会国家手术质量改进计划数据库中的队列，通过机器学习预测无菌性翻修 THA 或 TKA 患者的 30 天死亡率和并发症？（2）哪些患者变量与预测并发症最相关？
这是一项经过时间验证的回顾性研究，分析了 2014 年至 2019 年美国外科医师学会国家手术质量改进计划数据库，因为该数据库涵盖了广泛的临床环境和术前实验室值，可获取大量无菌性翻修 THA 和 TKA 患者的数据。训练数据集为 2014 年至 2018 年，2019 年为验证数据集。由于预测模型学习预期结果的发生率，因此这种划分允许评估模型在当代患者中的表现。在 2014 年至 2019 年期间，共有 24682 例患者接受了无菌性翻修 TKA，17871 例患者接受了无菌性翻修 THA。在这些患者中，将接受对应于无菌性翻修 TKA 或 THA 的 CPT 编码的患者视为潜在合格患者。基于排除涉及不洁伤口的手术，78%（19345 例中的 24682 例）的无菌性翻修 TKA 手术和 82%（14711 例中的 17871 例）的无菌性翻修 THA 手术符合条件。培训和验证队列中各有 10%的患者存在缺失预测变量。这些缺失数据大部分是术前钠或血细胞比容（训练和验证队列中均为 8%）。没有患者缺失结局数据。由于没有缺失数据，因此没有患者被排除。患者平均年龄为 66±12 岁，平均 BMI 为 32±7kg/m 2 ，平均美国麻醉医师协会（ASA）身体状况评分为 3（56%）。然后，XGBoost 被用来创建一个用于 30 天不良结局的评分工具。选择 XGBoost 的原因是它可以处理缺失数据，它是非线性的，它可以评估变量之间的细微关系，它采用了减少模型复杂性的技术，并且它在生成高度准确的机器学习模型方面有着良好的记录。性能指标包括判别和校准。判别通过 C 统计量进行评估，该统计量描述了接收器操作特征曲线下的面积。这量化了预测模型在具有感兴趣结局的患者与不具有该结局的患者之间的区分能力。C 统计量的良好范围包括 0.70 至 0.79、优秀 0.80 至 0.89 和出色 0.90 以上。我们通过 500 个样本的自举法估计了 C 统计量的 95%置信区间。校准曲线量化了模型预测结果的可靠性。可靠的模型对结局的预测概率与这些结局的实际概率相似，因此校准良好的模型应显示出一条与斜率为 1 和截距为 0 的线没有明显偏差的校准曲线。在 2019 年的验证数据上生成了校准曲线。使用 Shapley 加性解释（SHAP）可视化来研究特征重要性，以深入了解模型的预测方式。该模型被构建到一个在线计算器中，以便进行持续的测试和验证。风险计算器（http://nb-group.org/rev2/）是免费提供的，允许用户输入患者数据来计算无菌性翻修 TKA 或 THA 后 30 天的死亡率、心脏和呼吸系统并发症的风险。进行了一项事后分析，以评估 2020 年的数据是否会改善对 2019 年数据的校准。
该模型在内部验证中对无菌性翻修 THA 或 TKA 后死亡率、心脏并发症和呼吸系统并发症的预测准确率为 0.88（95%CI 0.83 至 0.93）、0.80（95%CI 0.75 至 0.84）和 0.78（95%CI 0.74 至 0.82），在时间验证中分别为 0.87（95%CI 0.77 至 0.96）、0.70（95%CI 0.61 至 0.78）和 0.82（95%CI 0.75 至 0.88）。校准曲线显示出轻微的过度自信（大多数预测概率高于实际概率）。对 2019 年验证集的事后分析并没有改善 2020 年数据的校准。所有模型的重要风险因素均包括年龄增加和 ASA 升高、BMI、血细胞比容和钠水平升高。血细胞比容和 ASA 是所有模型中最重要的三个特征。对于所有模型，与死亡率和心脏并发症模型关联最强的因素是年龄，而对于呼吸系统模型，则是慢性阻塞性肺疾病。与死亡率和心脏并发症模型相关的钠呈 U 形曲线。术前低钠血症和高钠血症预测死亡率和呼吸系统并发症的风险增加，最佳钠水平为 138mmol/L；低钠血症与死亡率的相关性强于高钠血症。血细胞比容水平低于 36%预示着所有三种不良结局的风险增加。BMI 低于 24kg/m 2 -尤其是低于 20kg/m 2 -预示着所有三种不良结局的风险增加，而 BMI 较高则风险较小。
该经时间验证的模型预测无菌性翻修 THA 或 TKA 后 30 天的死亡率、心脏并发症和呼吸系统并发症的 C 统计量范围为 0.78 至 0.88。该免费风险计算器可在术前由外科医生使用，以便向患者提供有关其对这些特定不良结局的术后风险的个人信息。仍然存在未解决的问题，包括是否改变研究中的术前患者变量，如钠或血细胞比容，会影响术后不良结局的风险；然而，需要进行前瞻性队列研究来回答这个问题。
III 级，治疗性研究。
