脊柱结核病灶清除融合内固定术后住院时间延长的危险因素分析及预测模型构建

Analysis of risk factors for prolonged postoperative hospital stay in patients after spinal tuberculosis lesion removal and fusion with internal fixation and development of a predictive model

中文关键词:  脊柱结核  住院时间  危险因素  预测模型  列线图

英文关键词:Spinal tuberculosis  Length of hospital stay  Risk factors  Predictive model  Nomogram

中文摘要:

  【摘要】 目的：探究脊柱结核患者病灶清除融合内固定术后住院时间延长的相关危险因素，构建列线图预测模型，为脊柱结核患者快速康复管理提供理论依据。方法：回顾性分析2018年12月~2023年6月遵义医科大学附属医院骨科收治的142例脊柱结核行病灶清除融合内固定术治疗的患者，按2∶1比例分为建模组（n=96）及验证组（n=46）。将住院时间>21d作为住院时间延长的结局变量，以两组患者的年龄、性别、饮酒史、吸烟史、高血压、冠心病、糖尿病、贫血、术后是否有低蛋白血症、是否合并脊髓损伤、是否并发其他部位结核、是否合并骨质破坏、是否输血、拔出引流管时间、术后并发症、手术时长、出血量、术前美国麻醉医师协会（American Society of Aneshesiologists，ASA）评分、术后ASA评分、手术切口长度、是否有脓液形成、术前是否进行化疗、化疗方案等分别作为自变量，建立单因素Logistic回归模型，单因素分析筛选出的危险因素纳入多因素Logistic回归模型分析脊柱结核患者病灶清除融合内固定术后住院时间>21d的独立危险因素并构建风险预测模型。采用受试者操作特征（receiver operating characteristics，ROC）曲线下面积（area under curve，AUC）对模型的区分度进行评价；采用校准曲线评价模型校准度；采用决策曲线（decision curve analysis，DCA）评价模型的临床价值及其对实际决策的影响。利用验证组数据绘制ROC曲线、校准曲线，进行外部验证。结果：建模组中单因素与多因素分析结果提示，脊柱结核患者病灶清除融合内固定术后住院时间延长的独立危险因素包括年龄（OR＝1.040，95%CI：1.011~1.069）、合并其他部位结核（OR=2.867，95%CI：1.157~7.106）、术前ASA评分（OR=1.543，95%CI：1.015~2.347）。建模组与验证组模型的ROC曲线AUC分别为0.767（95%CI：0.671~0.863）和0.720（95%CI：0.569~0.871），表明预测模型具有较好的预测效能。校准曲线分析结果显示实际曲线与理想曲线拟合较好，DCA曲线分析显示，列线图在建模组与验证组有较好的临床获益性。结论：高龄、合并其他部位结核、术前ASA评分等级高的脊柱结核患者病灶清除融合内固定术后易发生住院时间延长，基于此建立的风险预测列线图模型具有良好的预测效能。

英文摘要:

  【Abstract】 Objectives: To explore the risk factors related to the prolonged postoperative length of hospital stay(LOS) in patients after spinal tuberculosis lesion removal and fusion with internal fixation, and to construct a nomogram prediction model, so as to provide a theoretical basis for the enhanced recovery management of spinal tuberculosis patients.　Methods: The clinical data of 142 patients with spinal tuberculosis who underwent lesion removal and fusion with internal fixation in the Department of Orthopedics of the Affiliated Hospital of Zunyi Medical University between December 2018 and June 2023 were retrospectively analyzed. The patients were randomly divided into modeling group(n=96) and validation group(n=46) in a 2∶1 ratio. Setting the postoperative LOS>21d as the outcome variable for prolonged LOS, and taking age, gender, alcohol history, smoking history, hypertension, coronary heart disease, diabetes, anemia, postoperative hypoproteinemia, spinal cord injury, tuberculosis in other parts, bone destruction, blood transfusion, removal time of drainage, postoperative complications, operative time, blood loss, preoperative American Society of Anesthesiologists(ASA) score, postoperative ASA score, surgical incision length, pus formation, chemotherapy before surgery, and chemotherapy regimens as independent variables to develop univariate logistic regression model. The risk factors screened after univariate analysis were included for multivariate logistic regression model to determine the independent risk factors for LOS>21d after lesion removal and fusion with internal fixation in patients with spinal tuberculosis and to construct a predictive model for risk factors. The area under the curve(AUC) of receiver operating characteristics(ROC) curve was used to assess the the differentiation of the model; Calibration curve was used to assess the calibration situation of the model; Decision curve analysis(DCA) was used to assess the clinical value and influence of the model on actual decision-making process. Data of validation group was applied to draw ROC curve and calibration curve for external verification. Results: Univariate and multivariate analyses revealed that age(OR=1.040, 95% CI: 1.011-1.069), tuberculosis at other sites(OR=2.867, 95% CI: 1.157-7.106), and preoperative ASA score(OR=1.543, 95% CI: 1.015-2.347) were the independent risk factors for prolonged postoperative hospitalization in patients with spinal tuberculosis after lesion removal and fusion with internal fixation. The AUC of ROC curves of modeling group and validation group were 0.767(95% CI: 0.671-0.863) and 0.720(95% CI: 0.569-0.871), respectively, suggesting the predictive model had good predictive efficiency. The results of the calibration curve analysis demonstrated that the actual curve roughly resembled the ideal curve, and DCA curve revealed that the nomogram had superior clinical benefits. Conclusions: The spinal tuberculosis patients who are at older age, combined with other sites of tuberculosis, and with high preoperative ASA score are prone to prolonged LOS after lesion removal and fusion with internal fixation, and the risk prediction nomogram model developed accordingly has great predictive efficiency.