文献速递慢性静脉疾病

使用机器学习预测静脉曲张消融术后缺乏临床改善

Predicting lack of clinical improvement following varicose vein ablation using machine learning.
PubMed 文献 · J Vasc Surg Venous Lymphat Disord · 2024-12-26

本研究利用血管质量倡议数据库(2014–2024年)纳入33,924例因CEAP C2–C4疾病接受静脉曲张消融或手术的患者,构建6种机器学习模型预测1年缺乏临床改善(LCI)。XGBoost模型在术前特征中表现最佳,AUROC达0.94(95%CI 0.93–0.95),优于逻辑回归的0.71(95%CI 0.70–0.73),术后特征进一步将AUROC提升至0.97(95%CI 0.96–0.98)。模型校准良好,Brier评分术前0.12、术中0.11、术后0.10,各亚组性能稳健。

要点

  • XGBoost术前模型预测1年LCI的AUROC为0.94(95%CI 0.93–0.95),优于逻辑回归的0.71(95%CI 0.70–0.73)。
  • 加入术中或术后特征后XGBoost的AUROC均达0.97(95%CI 0.96–0.98),校准Brier评分分别为0.11和0.10。
  • 前10位预测因素中7项为术前特征,包括VCSS、静脉曲张症状问卷评分、CEAP分级、既往静脉曲张消融史等。

核心结论

  • 研究开发了能准确预测CEAP C2至C4疾病经腔内或手术静脉曲张治疗后结局的机器学习模型,性能优于逻辑回归。
  • 这些算法在指导患者咨询和围术期风险缓解策略以预防静脉曲张消融后LCI方面具有潜在重要用途。

研究设计与样本

  • 使用血管质量倡议数据库识别2014年至2024年间因CEAP C2至C4疾病接受腔内或手术静脉曲张治疗的患者。
  • 共识别226个预测特征:111个术前(人口学/临床)、100个术中(操作)和15个术后(术后即刻病程/并发症)特征。
  • 主要结局为1年LCI,定义为术前静脉临床严重程度评分(VCSS)减术后VCSS≤0,即静脉消融后无临床改善。
  • 数据分为训练集(70%)和测试集(30%),使用术前特征通过10折交叉验证训练6种机器学习模型:极端梯度提升(XGBoost)、随机森林、朴素贝叶斯分类器、支持向量机、人工神经网络和逻辑回归。
  • 主要模型评价指标为受试者工作特征曲线下面积(AUROC);表现最佳的算法进一步使用术中及术后特征训练。

主要发现

  • 研究期间共33,924例患者接受静脉曲张治疗(腔内30,602例[90.2%],手术3,322例[9.8%]),5,619例(16.6%)发生1年LCI。
  • 发生主要结局的患者年龄更大、更可能处于社会经济弱势、更少常规使用压力治疗,且疾病严重程度较轻(表现为术前VCSS、静脉曲张症状问卷评分和CEAP分级较低)。
  • 最佳术前预测模型为XGBoost,AUROC为0.94(95%CI 0.93–0.95);逻辑回归AUROC为0.71(95%CI 0.70–0.73)。
  • XGBoost模型在术中及术后阶段性能略有提升,两者AUROC均为0.97(95%CI 0.96–0.98)。
  • 校准图显示预测事件概率与观察事件概率一致性良好,Brier评分术前0.12、术中0.11、术后0.10。

临床怎么用

  • 作者认为这些算法在指导患者咨询和围术期风险缓解策略以预防静脉曲张消融后LCI方面具有潜在重要用途。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: Varicose vein ablation is generally indicated in patients with active/healed venous ulcers. However, patient selection for intervention in individuals without venous ulcers is less clear. Tools that predict lack of clinical improvement (LCI) after vein ablation may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year LCI after varicose vein ablation. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent endovenous or surgical varicose vein treatment for Clinical-Etiological-Anatomical-Pathophysiological (CEAP) C2 to C4 disease between 2014 and 2024. We identified 226 predictive features (111 preoperative [demographic/clinical], 100 intraoperative [procedural], and 15 postoperative [immediate postoperative course/complications]). The primary outcome was 1-year LCI, defined as a preoperative Venous Clinical Severity Score (VCSS) minus postoperative VCSS of ≤0, indicating no clinical improvement after vein ablation. The data were divided into training (70%) and test (30%) sets. Six ML models were trained using preoperative features with 10-fold cross-validation (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). The algorithm with the best performance was further trained using intraoperative and postoperative features. The focus was on preoperative features, whereas intraoperative and postoperative features were of secondary importance, because preoperative predictions offer the most potential to mitigate risk, such as deciding whether to proceed with intervention. Model calibration was assessed using calibration plots, and the accuracy of probabilistic predictions was evaluated with Brier scores. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, prior ipsilateral varicose vein ablation, location of primary vein treated, and treatment type. RESULTS: Overall, 33,924 patients underwent varicose vein treatment (30,602 endovenous [90.2%] and 3322 surgical [9.8%]) during the study period and 5619 (16.6%) experienced 1-year LCI. Patients who developed the primary outcome were older, more likely to be socioeconomically disadvantaged, and less likely to use compression therapy routinely. They also had less severe disease as characterized by lower preoperative VCSS, Varicose Vein Symptom Questionnaire scores, and CEAP classifications. The best preoperative prediction model was XGBoost, achieving an AUROC of 0.94 (95% confidence interval [CI], 0.93-0.95). In comparison, logistic regression had an AUROC of 0.71 (95% CI, 0.70-0.73). The XGBoost model had marginally improved performance at the intraoperative and postoperative stages, both achieving an AUROC of 0.97 (95% CI, 0.96-0.98). Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.12 (preoperative), 0.11 (intraoperative), and 0.10 (postoperative). Of the top 10 predictors, 7 were preoperative features including VCSS, Varicose Vein Symptom Questionnaire score, CEAP classification, prior varicose vein ablation, thrombus in the greater saphenous vein, and reflux in the deep veins. Model performance remained robust across all subgroups. CONCLUSIONS: We developed ML models that can accurately predict outcomes after endovenous and surgical varicose vein treatment for CEAP C2 to C4 disease, performing better than logistic regression. These algorithms have potential for important utility in guiding patient counseling and perioperative risk mitigation strategies to prevent LCI after varicose vein ablation.

来源:J Vasc Surg Venous Lymphat Disord,查看原文。版权归原作者所有。

引用

  1. Li B, Eisenberg N, Beaton D, et al. Predicting lack of clinical improvement following varicose vein ablation using machine learning. J Vasc Surg Venous Lymphat Disord. 2024. PMID: 39732288. doi:10.1016/j.jvsv.2024.102162

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。