Machine Learning Based Prediction of Post-operative Infrarenal Endograft Apposition for Abdominal Aortic Aneurysms

IF 5.7 1区医学 Q1 PERIPHERAL VASCULAR DISEASE

European Journal of Vascular and Endovascular Surgery Pub Date : 2024-11-01 DOI:10.1016/j.ejvs.2024.07.003

Willemina A. van Veldhuizen , Jean-Paul P.M. de Vries , Annemarij Tuinstra , Roy Zuidema , Frank F.A. IJpma , Jelmer M. Wolterink , Richte C.L. Schuurmann

{"title":"Machine Learning Based Prediction of Post-operative Infrarenal Endograft Apposition for Abdominal Aortic Aneurysms","authors":"Willemina A. van Veldhuizen , Jean-Paul P.M. de Vries , Annemarij Tuinstra , Roy Zuidema , Frank F.A. IJpma , Jelmer M. Wolterink , Richte C.L. Schuurmann","doi":"10.1016/j.ejvs.2024.07.003","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>Challenging infrarenal aortic neck characteristics have been associated with an increased risk of type Ia endoleak after endovascular aneurysm repair (EVAR). Short apposition (< 10 mm circumferential shortest apposition length [SAL]) on the first post-operative computed tomography angiography (CTA) has been associated with type Ia endoleak. Therefore, this study aimed to develop a model to predict post-operative SAL in patients with an abdominal aortic aneurysm based on the pre-operative shape.</div></div><div><h3>Methods</h3><div>A statistical shape model was developed to obtain principal component scores. The dataset comprised patients treated by standard EVAR without complications (<em>n</em> = 93) enriched with patients with a late type Ia endoleak (<em>n</em> = 54). The infrarenal SAL was obtained from the first post-operative CTA and subsequently binarised (< 10 mm and ≥ 10 mm). The principal component scores that were statistically different between the SAL groups were used as input for five classification models, and evaluated by means of leave one out cross validation. Area under the receiver operating characteristic curves (AUC), accuracy, sensitivity, and specificity were determined for each classification model.</div></div><div><h3>Results</h3><div>Of the 147 patients, 24 patients had an infrarenal SAL < 10 mm and 123 patients had a SAL ≥ 10 mm. The gradient boosting model resulted in the highest AUC of 0.77. Using this model, 114 patients (77.6%) were correctly classified; sensitivity (< 10 mm apposition was correctly predicted) and specificity (≥ 10 mm apposition was correctly predicted) were 0.70 and 0.79 based on a threshold of 0.21, respectively.</div></div><div><h3>Conclusion</h3><div>A model was developed to predict which patients undergoing EVAR will achieve sufficient graft apposition (≥ 10 mm) in the infrarenal aortic neck based on a statistical shape model of pre-operative CTA data. This model can help vascular specialists during the planning phase to accurately identify patients who are unlikely to achieve sufficient apposition after standard EVAR.</div></div>","PeriodicalId":55160,"journal":{"name":"European Journal of Vascular and Endovascular Surgery","volume":"68 5","pages":"Pages 568-576"},"PeriodicalIF":5.7000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Vascular and Endovascular Surgery","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1078588424005677","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

Challenging infrarenal aortic neck characteristics have been associated with an increased risk of type Ia endoleak after endovascular aneurysm repair (EVAR). Short apposition (< 10 mm circumferential shortest apposition length [SAL]) on the first post-operative computed tomography angiography (CTA) has been associated with type Ia endoleak. Therefore, this study aimed to develop a model to predict post-operative SAL in patients with an abdominal aortic aneurysm based on the pre-operative shape.

Methods

A statistical shape model was developed to obtain principal component scores. The dataset comprised patients treated by standard EVAR without complications (n = 93) enriched with patients with a late type Ia endoleak (n = 54). The infrarenal SAL was obtained from the first post-operative CTA and subsequently binarised (< 10 mm and ≥ 10 mm). The principal component scores that were statistically different between the SAL groups were used as input for five classification models, and evaluated by means of leave one out cross validation. Area under the receiver operating characteristic curves (AUC), accuracy, sensitivity, and specificity were determined for each classification model.

Results

Of the 147 patients, 24 patients had an infrarenal SAL < 10 mm and 123 patients had a SAL ≥ 10 mm. The gradient boosting model resulted in the highest AUC of 0.77. Using this model, 114 patients (77.6%) were correctly classified; sensitivity (< 10 mm apposition was correctly predicted) and specificity (≥ 10 mm apposition was correctly predicted) were 0.70 and 0.79 based on a threshold of 0.21, respectively.

Conclusion

A model was developed to predict which patients undergoing EVAR will achieve sufficient graft apposition (≥ 10 mm) in the infrarenal aortic neck based on a statistical shape model of pre-operative CTA data. This model can help vascular specialists during the planning phase to accurately identify patients who are unlikely to achieve sufficient apposition after standard EVAR.

查看原文本刊更多论文

基于机器学习的腹主动脉瘤术后肾下内移植物贴壁预测。

目的：具有挑战性的肾下主动脉颈部特征与血管内动脉瘤修补术（EVAR）后发生Ia型内漏的风险增加有关。术后首次计算机断层扫描血管造影（CTA）显示的短贴壁（周向最短贴壁长度 [SAL] < 10 mm）与 Ia 型内漏有关。因此，本研究旨在建立一个模型，根据术前形状预测腹主动脉瘤患者术后的 SAL：方法：建立了一个统计形状模型，以获得主成分得分。数据集包括接受标准EVAR治疗且无并发症的患者（n = 93）和晚期Ia型内漏患者（n = 54）。术后第一次 CTA 获取了肾下 SAL，随后对其进行了二值化（< 10 mm 和 ≥ 10 mm）。SAL组间存在统计学差异的主成分得分被用作五个分类模型的输入，并通过逐一交叉验证进行评估。每个分类模型的接收者操作特征曲线下面积（AUC）、准确性、灵敏度和特异性均已确定：结果：在 147 名患者中，24 名患者的肾下 SAL 小于 10 毫米，123 名患者的 SAL ≥ 10 毫米。梯度增强模型的 AUC 最高，为 0.77。使用该模型，114 例（78.0%）患者被正确分类；灵敏度（< 10 毫米贴壁被正确预测）和特异度（≥ 10 毫米贴壁被正确预测）分别为 0.70 和 0.79，阈值为 0.21：根据术前CTA数据的统计形状模型，建立了一个模型来预测哪些接受EVAR手术的患者能在主动脉颈下获得足够的移植物贴壁（≥ 10 mm）。该模型可帮助血管专家在计划阶段准确识别在标准 EVAR 术后不太可能达到充分贴壁的患者。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

European Journal of Vascular and Endovascular Surgery 医学-外科

CiteScore

6.80

自引率

15.80%

发文量

471

审稿时长

66 days

期刊介绍： The European Journal of Vascular and Endovascular Surgery is aimed primarily at vascular surgeons dealing with patients with arterial, venous and lymphatic diseases. Contributions are included on the diagnosis, investigation and management of these vascular disorders. Papers that consider the technical aspects of vascular surgery are encouraged, and the journal includes invited state-of-the-art articles. Reflecting the increasing importance of endovascular techniques in the management of vascular diseases and the value of closer collaboration between the vascular surgeon and the vascular radiologist, the journal has now extended its scope to encompass the growing number of contributions from this exciting field. Articles describing endovascular method and their critical evaluation are included, as well as reports on the emerging technology associated with this field.