数据驱动模型融合几何、生物力学与临床数据评估腹主动脉瘤破裂
结果显示直径阈值55 mm(男)/50 mm(女)准确率58.0%、敏感性99.1%、特异性36.0%,机器学习模型准确率更高(LogR 90.2%,SVM-Lin 89.5%,SVM-Nlin 88.7%,GNB 86.4%),在≤70 mm组准确率下降(直径阈值44.2%,LogR 82.5%,SVM-Lin 83.6%,SVM-Nlin 65.9%,GNB 84.7%)。SHAP分析将生物力学参数(而非直径)列为最相关因素。
要点
- 直径阈值55 mm(男)/50 mm(女)分类破裂的准确率58.0%,敏感性99.1%,特异性36.0%。
- 全数据集机器学习模型准确率:LogR 90.2%、SVM-Lin 89.5%、SVM-Nlin 88.7%、GNB 86.4%。
- ≤70 mm组准确率下降:直径阈值44.2%,LogR 82.5%,SVM-Lin 83.6%,SVM-Nlin 65.9%,GNB 84.7%。
核心结论
- 多参数估计优于单纯基于直径的方法。
- 所提出的可预测性方法应在纵向研究中进一步测试。
研究设计与样本
- 将临床患者数据及腹主动脉瘤几何与生物力学属性输入机器学习模型(LogR、SVM-Lin、SVM-Nlin、GNB),采用五折交叉验证进行训练与验证。
- 分类分析覆盖全部病例及直径低于70 mm的病例,并用SHAP分析对破裂识别因素进行排序。
主要发现
- 破裂组女性20.6%、平均年龄77岁、平均直径86.3 mm;未破裂组女性21.5%、平均年龄74岁、平均直径57 mm。
- 全数据集直径阈值55 mm(男)/50 mm(女)的破裂分类准确率58.0%,敏感性99.1%,特异性36.0%。
- 全数据集机器学习模型准确率:LogR 90.2%、SVM-Lin 89.5%、SVM-Nlin 88.7%、GNB 86.4%。
- ≤70 mm组准确率:直径阈值44.2%、LogR 82.5%、SVM-Lin 83.6%、SVM-Nlin 65.9%、GNB 84.7%。
- SHAP将生物力学参数(而非直径)列为最相关的破裂识别因素。
关键数值与推荐
- 全数据集直径阈值55 mm(男)/50 mm(女)分类准确率58.0%、敏感性99.1%、特异性36.0%。
- 全数据集机器学习模型准确率:LogR 90.2%、SVM-Lin 89.5%、SVM-Nlin 88.7%、GNB 86.4%。
- ≤70 mm组准确率:直径阈值44.2%、LogR 82.5%、SVM-Lin 83.6%、SVM-Nlin 65.9%、GNB 84.7%。
局限性
- 原文未述局限性
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: Despite elective repair of a large portion of stable abdominal aortic aneurysms (AAAs), the diameter criterion cannot prevent all small AAA ruptures. Since rupture depends on many factors, this study explored whether machine learning (ML) models (logistic regression [LogR], linear and non-linear support vector machine [SVM-Lin and SVM-Nlin], and Gaussian Naïve Bayes [GNB]) might improve the diameter based risk assessment by comparing already ruptured (diameter 52.8 - 174.5 mm) with asymptomatic (diameter 40.4 - 95.5 mm) aortas. METHODS: A retrospective case-control observational study included ruptured AAAs from two centres (2010 - 2012) with computed tomography angiography images for finite element analysis. Clinical patient data and geometric and biomechanical AAA properties were fed into ML models, whose output was compared with the results from intact cases. Classifications were explored for all cases and those having diameters below 70 mm. All data trained and validated the ML models, with a five-fold cross-validation. SHapley Additive exPlanations (SHAP) analysis ranked the factors for rupture identification. RESULTS: One hundred and seven ruptured (20.6% female, mean age 77 years, mean diameter 86.3 mm) and 200 non-ruptured aneurysmal infrarenal aortas (21.5% female, mean age 74 years, mean diameter 57 mm) were investigated through cross-validation methods. Given the entire dataset, the diameter threshold of 55 mm in males and 50 mm in females provided a 58.0% accurate rupture classification. It was 99.1% sensitive (AAA rupture identified correctly) and 36.0% specific (intact AAAs identified correctly). ML models improved accuracy (LogR 90.2%, SVM-Lin 89.5%, SVM-Nlin 88.7%, and GNB 86.4%); accuracy decreased when trained on the ≤ 70 mm group (55/50 mm diameter threshold 44.2%, LogR 82.5%, SVM-Lin 83.6%, SVM-Nlin 65.9%, and GNB 84.7%). SHAP ranked biomechanical parameters other than the diameter as the most relevant. CONCLUSION: A multiparameter estimate enhanced the purely diameter-based approach. The proposed predictability method should be further tested in longitudinal studies.
引用
- Alloisio M, Siika A, Roy J, et al. Data Driven Models Merging Geometric, Biomechanical, and Clinical Data to Assess the Rupture of Abdominal Aortic Aneurysms. Eur J Vasc Endovasc Surg. 2025. PMID: 40484216. doi:10.1016/j.ejvs.2025.06.002
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。