Bayesian neural network approach for determining the risk of re-intervention after endovascular aortic aneurysm repair

This article proposes a Bayesian neural network approach to determine the risk of re-intervention after endovascular aortic aneurysm repair surgery. The target of proposed technique is to determine which patients have high chance to re-intervention (high-risk patients) and which are not (low-risk patients) after 5 years of the surgery. Two censored datasets relating to the clinical conditions of aortic aneurysms have been collected from two different vascular centers in the United Kingdom. A Bayesian network was first employed to solve the censoring issue in the datasets. Then, a back propagation neural network model was built using the uncensored data of the first center to predict re-intervention on the second center and classify the patients into high-risk and low-risk groups. Kaplan-Meier curves were plotted for each group of patients separately to show whether there is a significant difference between the two risk groups. Finally, the logrank test was applied to determine whether the neural network model was capable of predicting and distinguishing between the two risk groups. The results show that the Bayesian network used for uncensoring the data has improved the performance of the neural networks that were built for the two centers separately. More importantly, the neural network that was trained with uncensored data of the first center was able to predict and discriminate between groups of low risk and high risk of re-intervention after 5 years of endovascular aortic aneurysm surgery at center 2 (p = 0.0037 in the logrank test).

The risk of re-intervention after endovascular aortic aneurysm repair

This thesis studies survival analysis techniques dealing with censoring to produce predictive tools that predict the risk of endovascular aortic aneurysm repair (EVAR) re-intervention. Censoring indicates that some patients do not continue follow up, so their outcome class is unknown. Methods dealing with censoring have drawbacks and cannot handle the high censoring of the two EVAR datasets collected. Therefore, this thesis presents a new solution to high censoring by modifying an approach that was incapable of differentiating between risks groups of aortic complications. Feature selection (FS) becomes complicated with censoring. Most survival FS methods depends on Cox's model, however machine learning classifiers (MLC) are preferred. Few methods adopted MLC to perform survival FS, but they cannot be used with high censoring. This thesis proposes two FS methods which use MLC to evaluate features. The two FS methods use the new solution to deal with censoring. They combine factor analysis with greedy stepwise FS search which allows eliminated features to enter the FS process. The first FS method searches for the best neural networks' configuration and subset of features. The second approach combines support vector machines, neural networks, and K nearest neighbor classifiers using simple and weighted majority voting to construct a multiple classifier system (MCS) for improving the performance of individual classifiers. It presents a new hybrid FS process by using MCS as a wrapper method and merging it with the iterated feature ranking filter method to further reduce the features. The proposed techniques outperformed FS methods based on Cox's model such as; Akaike and Bayesian information criteria, and least absolute shrinkage and selector operator in the log-rank test's p-values, sensitivity, and concordance. This proves that the proposed techniques are more powerful in correctly predicting the risk of re-intervention. Consequently, they enable doctors to set patients’ appropriate future observation plan.

A time bomb in the thorax: the giant ascending aortic aneurysm. Case report

We report the case of a 82-year-old woman, asymptomatic, subject to chest computed tomography for trauma. Then the patient underwent surgery. Before sternotomy, femoro-femoral bypass was starter in order to decompress the aneurysm; using deep hypothermia and circulatory arrest, ascending aorta and hemiarch replacement were performed with a Dacron graft. Post-operative course was uneventful.

Aorto-bronchial and aorto-pulmonary fistulation after thoracic endovascular aortic repair: an analysis from the European Registry of Endovascular Aortic Repair Complications.

OBJECTIVES: To learn upon incidence, underlying mechanisms and effectiveness of treatment strategies in patients with central airway and pulmonary parenchymal aorto-bronchial fistulation after thoracic endovascular aortic repair (TEVAR). METHODS: Analysis of an international multicentre registry (European Registry of Endovascular Aortic Repair Complications) between 2001 and 2012 with a total caseload of 4680 TEVAR procedures (14 centres). RESULTS: Twenty-six patients with a median age of 70 years (interquartile range: 60-77) (35% female) were identified. The incidence of either central airway (aorto-bronchial) or pulmonary parenchymal (aorto-pulmonary) fistulation (ABPF) in the entire cohort after TEVAR in the study period was 0.56% (central airway 58%, peripheral parenchymal 42%). Atherosclerotic aneurysm formation was the leading indication for TEVAR in 15 patients (58%). The incidence of primary endoleaks after initial TEVAR was n = 10 (38%), of these 80% were either type I or type III endoleaks. Fourteen patients (54%) developed central left bronchial tree lesions, 11 patients (42%) pulmonary parenchymal lesions and 1 patient (4%) developed a tracheal lesion. The recognized mechanism of ABPF was external compression of the bronchial tree in 13 patients (50%), the majority being due to endoleak formation, further ischaemia due to extensive coverage of bronchial feeding arteries in 3 patients (12%). Inflammation and graft erosion accounted for 4 patients (30%) each. Cumulative survival during the entire study period was 39%. Among deaths, 71% were attributed to ABPF. There was no difference in survival in patients having either central airway or pulmonary parenchymal ABPF (33 vs 45%, log-rank P = 0.55). Survival with a radical surgical approach was significantly better when compared with any other treatment strategy in terms of overall survival (63 vs 32% and 63 vs 21% at 1 and 2 years, respectively), as well as in terms of fistula-related survival (63 vs 43% and 63 vs 43% at 1 and 2 years, respectively). CONCLUSIONS: ABPF is a rare but highly lethal complication after TEVAR. The leading mechanism behind ABPF seems to be a continuing external compression of either the bronchial tree or left upper lobe parenchyma. In this setting, persisting or newly developing endoleak formation seems to play a crucial role. Prognosis does not differ in patients with central airway or pulmonary parenchymal fistulation. Radical bronchial or pulmonary parenchymal repair in combination with stent graft removal and aortic reconstruction seems to be the most durable treatment strategy.

Retrograde Endovascular Treatment of Internal Iliac Aneurysm in a Patient with Marfan Syndrome

To report a technique to maintain pelvic flow to an internal iliac artery (IIA) with aneurysm in a patient with Marfan syndrome, and previously treated by infrarenal abdominal aortic aneurysm open procedure. Retrograde endovascular hypogastric artery preservation (REHAP) through flexible endograft implantation from external iliac artery (EIA) to internal iliac artery (IIA) was used. REHAP was a reasonable, minimally invasive and elegant alternative (new) to maintain pelvic arterial flow in Marfan syndrome. However, the long-term durability is unknown, and so, it should be used in selected patients.

Total Endovascular Debranching of the Aortic Arch

Background: Significant morbidity and mortality are related to conventional aortic replacement surgery. Endovascular debranching techniques, fenestrated or branched endografts are time consuming and costly.Objective: We alternatively propose to use endovascular approach with parallel grafts for debranching of aortic arch.Methods: Under general anesthesia, 12 F sheaths were inserted in the femoral, axillary and common carotid arteries for vascular accesses. ViaBahn grafts 10 - 15 cm in length were placed into the aortic arch from right common carotid, left common carotid and left axillary arteries, until the tip of each graft reached into the ascending aorta. Through one femoral artery, the aortic stent-graft was positioned and delivered. Soon after, the parallel grafts were sequentially delivered. Self-spanding Wallstents(R) were used for parallel grafts reinforcement. Ballooning was routinely used for parallel grafts and rarely for aortic graft.Results: This technique was used in 2 cases. The first one was a lady with 72 years old, with an aortic retrograde dissection from left subclavian artery and involving remaining arch branches. Through right common carotid artery a stent-graft was placed in the ascending aorta and through the left common carotid artery a ViaBahn was inserted parallel to the former. A thoracic endograft then covered all the aortic arch dissection extending into the ascending aorta close to the sinu-tubular junction. The second case was a 82 year old male patient with a 7 cm aortic arch aneurysm. Through both common carotid arteries ViaBahn grafts were introduced and positioned into the ascending aorta. Soon after, the deployment of the thoracic stent graft covered all parallel grafts of the aortic arch, excluding the aneurysm. Both cases did not have neurologic or cardiac complications and were discharged 10 days after the procedure.Conclusions: This technique may be a good minimal invasive off-the-shelf technical option for aortic arch "debranching". More data and further improvements are required before this promising technique can be widely advocated. (C) 2011 European Society for Vascular Surgery. Published by Elsevier Ltd. All rights reserved.

Endovascular repair of a juxtarenal saccular aneurysm using the Multilayer Flow Modulator: report of the first case performed in a Public Hospital in Brazil

Endovascular aortic aneurysm repair (EVAR) involving renal and visceral arteries remains a great challenge. Several techniques have been developed over the time to treat juxtarenal, pararenal and thoracoabdominal aneurysms, highlighting the fenestrated and branched endografts, parallel prostheses as Chimney, Periscope and Sandwich Techniques and the use of flow modulation by multilayer stent. We report a case of saccular juxtarenal aortic aneurysm with high surgical risk for complex airway access due to a history of radical laryngectomy for laryngeal neoplasm. Due to chronic aorto-iliac obstructive disease, ostial stenosis of renal artery and limited diameter of the suprarenal aorta, we discarded options involving fenestrated/branched endografts and involving parallel prostheses techniques. We present this case as a therapeutic challenge and a successful treatment option in the short-term evaluation.

Huge aneurysm of the ascending aorta in a patient with adult-type Pompe's disease: histological findings mimicking fibrillinopathy

Adult-type Pompe's disease (glycogen storage disease type II) has rarely been shown to present with dilatative arteriopathy, suggesting potential smooth muscle involvement in addition to lysosomal glycogen deposits usually restricted to skeletal muscle tissue. We report the case of a middle-aged man under enzyme replacement therapy presenting with an exceedingly large thoracic aortic aneurysm. Surprisingly, the histological work-up of resected aortic tissue revealed changes mimicking those observed in patients with classic connective tissue diseases. Enzyme replacement therapy, in addition to musculoskeletal and pulmonary treatment for patients with Pompe's disease, may prolong survival and lead to patients presenting with vascular alterations that may pose surgical and potential diagnostic challenges in the future.

Influence of pulmonary status and diabetes mellitus on aortic neck dilatation following endovascular repair of abdominal aortic aneurysms: a EUROSTAR report

PURPOSE: To elucidate the association of impaired pulmonary status (IPS) and diabetes mellitus (DM) with clinical outcome and the incidences of aortic neck dilatation and type I endoleak after elective endovascular infrarenal aortic aneurysm repair (EVAR). METHODS: In 164 European institutions participating in the EUROSTAR registry, 6383 patients (5985 men; mean age 72.4+/-7.6 years) underwent EVAR. Patients were divided into patients without versus with IPS or with/without DM. Clinical assessment and contrast-enhanced computed tomography (CT) were performed at 1, 3, 6, 12, 18, and 24 months and annually thereafter. Cumulative endpoint analysis comprised death, aortic rupture, type I endoleak, endovascular reintervention, and surgical conversion. RESULTS: Prevalence of IPS was 2733/6383 (43%) and prevalence of DM was 810/6383 (13%). Mean follow-up was 21.1+/-18.4 months. Thirty-day mortality, AAA rupture, and conversion rates did not differ between patients with versus without IPS and between patients with versus without DM. All-cause and AAA-related mortality, respectively, were significantly higher in patients with IPS compared to patients with normal pulmonary status (31.0% versus 19.0%, p<0.0001 and 6.8% versus 3.3%, p = 0.0057) throughout follow-up. In multivariate analysis adjusted for smoking, age, gender, comorbidities, fitness for open repair, co-existing common iliac aneurysm, neck and aneurysm size, arterial angulations, aneurysm classification, endograft oversizing >or=15%, and type of stent-graft, the presence of IPS was not associated with significantly higher rates of aortic neck dilatation (30.6% versus 38.0%, p>0.05) and did not influence cumulative rates of type I endoleak, endovascular reintervention, or conversion to open surgery (p>0.05). Similarly, the presence of DM did not influence the above-mentioned study endpoints. CONCLUSION: In contrast to observations regarding the natural course of AAAs, impaired pulmonary status does not negatively influence aortic neck dilatation, while the presence of diabetes does not protect from these dismal events after EVAR.

Sixty-four-detector CT angiography of infrarenal aortic neck length and angulation: prospective analysis of interobserver variability

PURPOSE: To quantify the interobserver variability of abdominal aortic aneurysm (AAA) neck length and angulation measurements. MATERIALS AND METHODS: A total of 25 consecutive patients scheduled for endovascular AAA repair underwent follow-up 64-row computed tomographic (CT) angiography in 0.625-mm collimation. AAA neck length and angulation were determined by four blinded, independent readers. AAA neck length was defined as the longitudinal distance between the first transverse CT slice directly distal to the lowermost renal artery and the first transverse CT slice that showed at least a 15% larger outer aortic wall diameter versus the diameter measured directly below the lowermost renal artery. Infrarenal AAA neck angulation was defined as the true angle between the longitudinal axis of the proximal AAA neck and the longitudinal axis of the AAA lumen as analyzed on three-dimensional CT reconstructions. RESULTS: Mean deviation in aortic neck length determination was 32.3% and that in aortic neck angulation was 32.1%. Interobserver variability of aortic neck length and angulation measurements was considerable: in any reader combination, at least one measurement difference was outside the predefined limits of agreement. CONCLUSIONS: Assessment of the longitudinal extension and angulation of the infrarenal aortic neck is associated with substantial observer variability, even if measurement is carried out according to a standardized protocol. Further studies are mandatory to assess dedicated technical approaches to minimize variance in the determination of the longitudinal extension and angulation of the infrarenal aortic neck.