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.

CO2-EVAR: An innovative approach to Automated Carbon Dioxide Angiography during Endovascular Abdominal Aortic Aneurysm repair

Objectives CO2-EVAR was proposed for treatment of AAA especially in patients with CKD. Issues regarding standardization, such as visualization of lowest renal artery (LoRA) and quality image in angiographies performed from pigtail or introducer-sheath, are still unsolved. Aim of the study was to analyze different steps of CO2-EVAR to create an operative protocol to standardize the procedure. Methods Patients undergoing CO2-EVAR were prospectively enrolled in 5 European centers (2018-2021). CO2-EVAR was performed using an automated injector. LoRA visualization and image quality (1-4) were analyzed and compared at different procedure steps: preoperative CO2-angiography from Pigtail/Introducer-sheath (1st Step), angiographies from Pigtail at 0%,50%,100% main body (MB) deployment (2nd Step), contralateral hypogastric artery (CHA) visualization with CO2 injection from femoral Introducer-sheath (3rd Step) and completion angiogram from Pigtail/Introducer-sheath (4th Step). Intra-/postoperative adverse events were evaluated. Results Sixty-five patients undergoing CO2-EVAR were enrolled, 55/65(84.5%) male, median age 75(11.5) years. Median ICM was 20(54)cc; 19/65(29.2%) procedures were performed with 0-iodine. 1st Step: median image quality was significantly higher with CO2 injected from femoral introducer [Pigtail2(3)vs.3(3)Introducer,p=.008]. 2nd Step: LoRA was more frequently detected at 50% (93%vs.73.2%, p=.002) and 100% (94.1%vs.78.4%, p=.01) of MB deployment compared with first angiography from Pigtail; image quality was significantly higher at 50% [3(3)vs.2(3),p=<.001] and 100% [4(3) vs.2(3),p=.001] of MB deployment. CHA was detected in 93% cases (3rd Step). Mean image quality was significantly higher when final angiogram (4th Step) was performed from introducer (Pigtail2.6±1.1vs.3.1±0.9Introducer,p=<.001). Rates of intra-/postoperative adverse events (pain,vomit,diarrhea) were 7.7% and 12.5%. Conclusions Preimplant CO2-angiography should be performed from Introducer-sheath. MB steric bulk during its deployment should be used to improve image quality and LoRA visualization with CO2. CHA can be satisfactorily visualized with CO2. Completion CO2-angiogram should be performed from femoral Introducer-sheath. This operative protocol allows to perform CO2-EVAR with minimal ICM and low rate of mild complications.

Late onset spinal cord ischemia after thoracoabdominal aortic aneurysm open repair

The aim of this study is to evaluate if spinal cord ischemia (SCI), especially its late presentation, and can be correlated to the results of intraoperative evoked potential monitoring (IOM). Methods. This study is a physician-initiated, retrospective, single-center, non-randomized study. Data from all patients undergoing a thoracoabdominal aortic aneurysm surgical repair (TAAA SR) between January 2016 and March 2020 IOM was collected and analyzed. Results. During the study period, 261 patients underwent TAAA SR with MEP/SSEPs monitoring [190 males, 73%; median age 65 (57-71)]. Thirty-seven patients suffered from SCI, for an overall rate of 14% (permanent 9%). When stratifying patients according to the SCI onset, 18 patients presented with an early (11 permanent) and 19 with a late SCI (<24h) (11 permanent). Of 261 patients undergoing TAAA SR with IOM, 15 were excluded due to changes in the upper extremity motor evoked potentials. For the remaining 246, the association between SCI and IOM was investigated: only irreversible IOM loss without peripheral changes have been found to be a risk factor for late onset SCI (p=.006). Furthermore, given that no statistical differences were found between the two groups when no IOM changes were recorded (p=.679), this situation cannot reliably rule out any SCI in our cohort. Independent risk factors for late spinal cord ischemia onset found at multivariate analysis were smoking history (p=.008), BMI>28 (p=.048) and TAAA extent II (p=.009). The irreversible MEP change without peripheral showed a trend of significance (p=.052). Conclusions. Evoked potential intraoperative monitoring is an important adjunct during thoracoabdominal aortic open repair to predict and possibly prevent spinal cord ischemia. Irreversible IOM loss without peripheral changes was predictive of late SCI, therefore more attention should be paid to the postoperative management of this subgroup of patients.

Development of a hydrogel construct to prevent endoleaks occurrence following endovascular abdominal aortic aneurysm repair

Abdominal aortic aneurysm is the pathological dilation of the abdominal tract of the aorta and, if left untreated, could undergo rupture with a mortality rate of up to 90%. EVAR is the most common method for AAA treatment consisting in the internal coverage of the aorta with a metallic stent to isolate the aneurysmatic segment from the systemic circulation. Although EVAR technical success rate is high, reinterventions are common. Among the causes of reinterventions typeII endoleaks are the most frequent and consist in retrograde blood flow into the aneurysmal sac from collateral aortic branches. Continued perfusion of the aneurysm sac may lead to aneurysm rupture, therefore AAA sac embolization is performed using metallic coils. However, the presence of artifacts caused by the presence of metallic coils is a limitation because they are radiopaque and can hamper the endoleak during imaging follow-up. This study is aimed at developing a biocompatible hydrogel that could be injected into the aneurysmal sac and may allow a selective intraprocedural sac embolization to reduce post procedural typeII endoleak and eventual AAA rupture. P(BT75BSI25) was synthesized by polycondensation and its biocompatibility tested to assess whether the polymers had no toxic effects. HUVEC cell line was used to mimic the environment in which the polymer would be in contact with, PBS was used as a positive control and MTT assay was performed to evaluate cellular viability after being in contact with the hydrogel. MTT assay showed no significant difference between PBS and P(BT75BSI25), thus the polymer is biocompatible, as confirmed by the analysis of apoptosis by flow cytometry. An aromatic copolymer was obtained via polycondensation and was found to be biocompatible in contact with endothelial cells. This suggests that the hydrogel could be potentially used in the clinical setting for the treatment of type II endoleak after EVAR.

Type A quadricuspid aortic valve and ascending aorta aneurysm: a rare combination.

Quadricuspid aortic valve (QAV) is a rare congenital anomaly associated with aortic valve insufficiency and significant morbidity, and requires the replacement or, rarely, the repair of the malfunctioning heart valve. A QAV associated with an ascending aorta aneurysm is an extremely rare anatomic combination with a hypothetical, but not clear, shared embryological etiology. To date, only two cases of type B QAV with ascending aorta aneurysm have been reported. Herein is described the first ever case of a 38-year-old male suffering from severe symptomatic aortic valve regurgitation due to a type A QAV, associated with an ascending aorta aneurism, who underwent a successful combined replacement of the aortic valve and ascending aorta.

Drawback of aortoplasty for aneurysm of the ascending aorta associated with aortic valve disease.

BACKGROUND: Aortoplasty has been advocated for moderate dilatation of the ascending aorta associated with aortic valve disease. We report our results with this conservative approach. METHODS: Seventeen consecutive patients with unsupported aortoplasty were reviewed. Twelve patients had aortic valve regurgitation and 5 had stenosis. The aortic wall was analyzed histologically in 14 patients. Follow-up was complete, with a mean time of 6 years (range, 2.3 to 10.5 years). RESULTS: Two patients among the 15 hospital survivors died during follow-up of causes unrelated to aortic pathology. Survival at 7 years was 86.7% (+/- 8.8%). Recurring aortic aneurysms developed in 4 patients after a mean time of 63 months, with an event-free survival at 7 years of 41% (+/- 21%). All of these 4 patients had aortic valve regurgitation and cystic medial necrosis. CONCLUSIONS: The recurrence rate of aneurysms after unsupported aortoplasty and aortic valve replacement is high in patients with aortic regurgitation. This strongly suggests that in these patients, the aortic dilatation is related to an underlying wall deficiency, associated with the aortic valve pathology, rather than to the hemodynamic stress imposed by the aortic valve disease.