The role of intraluminal thrombus formation for expansion of abdominal aortic aneurysms

Individual risk assessment for rupture of abdominal aortic aneurysm using artificial intelligence

OBJECTIVE

This study aimed to develop a prediction tool to identify abdominal aortic aneurysms (AAAs) at increased risk of rupture incorporating demographic, clinical, imaging, and medication data using artificial intelligence (AI).

DESIGN

A development and validation study for individual prognosis using AI in a case-control design.

METHODS

From two Danish hospitals, all available ruptured AAA cases between January 2009 and December 2016 were included in a ratio of 1:2 with elective surgery controls. Cases with previous AAA surgery or missing preoperative scans were excluded. Features from computed tomography angiography scans and hospital records were manually retrieved. The sample was divided randomly and evenly into developmental and internal validation groups. A SHapley Additive exPlanations Feature Importance Rank Ensembling (SHAPFire) AI tool was developed using a gradient boosting decision tree framework. The final SHAPFire AI model was compared with models using (1) solely infrarenal anterior-posterior diameter and (2) all available features.

RESULTS

The study included 637 individuals (84.8% men, mean age 73 ± 7 years, 213 ruptured AAAs). The SHAPFire AI incorporated 20 of 68 available features, and aneurysm size, blood pressure, and relationships between height and weight were given highest rankings. The receiver operating characteristic curve for the SHAPFire AI model displayed a significant increase in accuracy identifying ruptured AAA cases compared with the conventional model based solely on diameter with areas under the curves of 0.86 ± 0.04 and 0.74 ± 0.03 (P = .008), respectively. SHAPFire AI was comparable in performance with the model using all features.

CONCLUSIONS

This study successfully developed a SHAPFire AI tool to identify AAAs at increased risk of rupture with significantly higher accuracy than diameter alone. External validation of the model is warranted before clinical implementation.

Endovascular Aneurysm Repair for Abdominal Aortic Aneurysm: A Comprehensive Review

Abdominal aortic aneurysm (AAA) can be defined as an abnormal, progressive dilatation of the abdominal aorta, carrying a substantial risk for fatal aneurysmal rupture. Endovascular aneurysmal repair (EVAR) for AAA is a minimally invasive endovascular procedure that involves the placement of a bifurcated or tubular stent-graft over the AAA to exclude the aneurysm from arterial circulation. In contrast to open surgical repair, EVAR only requires a stab incision, shorter procedure time, and early recovery. Although EVAR seems to be an attractive solution with many advantages for AAA repair, there are detailed requirements and many important aspects should be understood before the procedure. In this comprehensive review, fundamental information regarding AAA and EVAR is presented.

Magnetic resonance imaging of the intraluminal thrombus in abdominal aortic aneurysms: a quantitative and qualitative evaluation and correlation with growth rate

BACKGROUND

The role of the intraluminal thrombus (ILT) in abdominal aortic aneurysm (AAA) growth remains incompletely understood. MRI is superior to other methods in depicting the morphology of the ILT. This study brings preliminary, but novel information on the presence and morphological characteristics of the ILT and AAA growth rates in a screening cohort.

METHODS

Cohort study with 46 patients from the Viborg Vascular Trial. All underwent one non-contrast-enhanced magnetic resonance imaging (MRI) at the end of follow-up. ILT presence was noted and, if present, it was allocated to one of four morphological categories based on visual appearance and signal intensity on T2 weighted images.

RESULTS

The mean growth rate was 1.95 mm/year ±0.87 (SD). The observation time was 5.59±0.63 (SD) years. ILT was present in AAA size groups as follows: 30-34.9 mm 20.00%, 35-39.9 mm 88.89%, 40-44.9 mm 81.25%, 45-49.9 mm 100% and 50-54.9 mm 100%. Out of 46, 8 had no ILT at the time of MRI. The presence of any sort of ILT yielded a significantly increased unadjusted and an adjusted growth rate of 1.09 mm/year (95% CI: 0.48; 1.70) and 1.24 mm/year (95% CI: 0.64; 1.83), respectively. All four thrombus types were retrospectively associated with an increased recorded growth rate compared with "no thrombus". Presence of a thin circumferential thrombus was retrospectively associated with the highest increase in growth rate, viz. 2.09 mm/year (95% CI: 1.23; 2.95).

CONCLUSIONS

We observed faster growth rate in those AAA that had developed an ILT. Even faster growth was observed amongst those AAA containing a thin ILT located along the inner circumference.

A Propensity Score–Matched Analysis of Inflammatory Response With Endovascular Aneurysm Sealing vs Endovascular Aneurysm Repair

Purpose: To evaluate the risk of postimplantation syndrome associated with endovascular aneurysm sealing (EVAS) and endovascular aneurysm repair (EVAR) in patients treated for abdominal aortic aneurysm (AAA). Methods: From December 2013 to May 2015, 41 AAA patients treated with EVAS (mean age 72±9 years; 38 men) and 63 with EVAR (mean age 74±10 years; 55 men) at a single center were retrospectively reviewed. To control for treatment selection bias, propensity score matching was used to compare outcomes by treatment mode. Main outcomes were postimplantation syndrome (defined as temperature >38°C and leukocyte count >12,000/µL), inflammatory response markers [platelets and high-sensitivity C-reactive protein (hs-CRP)], and clinical complications through 30 days. Results: In 39 matched patients per group, the incidences of postimplantation syndrome (p=0.07), mean body temperature (p=0.05), mean leukocyte count (p=0.003), and mean hs-CRP (p<0.001) were proportionally lower with EVAS vs EVAR. Serious adverse events (0% vs 12.8%, p=0.05) and endoleaks (0% vs 10.3%, p=0.13) through 30 days were less frequent with EVAS, but the group differences were not significantly different. The choice of endovascular graft material influenced postoperative and 30-day clinical outcomes, with greater overall risk observed with polyester stent-grafts. Conclusion: Endovascular aneurysm sealing is associated with a blunted systematic inflammatory response compared with EVAR. Polyester stent-grafts induce the greatest periprocedural inflammatory response.

[Sleep apnea syndrome and abdominal aortic aneurysm: Study of the prevalence of sleep apnea syndrome in patients with aneurysm and research of association. Clinical study on 52 patients]

OBJECTIVES

Prevalence of abdominal aortic aneurysms (AAA) in Europe is between 4.1 % and 8.9 %. The risk of rupture of AAA is related to the evolution of its diameter. The role of sleep apnea (SA) remains still discussed. The objective of this study was to study the prevalence of SA in patients presenting with AAA in comparison with the general population as well as the relation between the AAA diameter and the severity of SA.

MATERIALS AND METHODS

Between June 2012 and December 2014, we included all patients referred for surgical treatment of an AAA. All the patients had a preoperative polysomnography and angio-scanner. An apnea/hypopnea index (AHI)>10/h was chosen for the diagnosis of SA. SA prevalence was compared with the prevalence in general population. The patients were also divided into two groups according to the severity of SA: group 1 (no SA and light SAS); group 2 (moderate and severe SA).

RESULTS

Fifty-two patients were included. Fifty-six percent of the patients presented SA - prevalence was significantly higher than in the general population (56 vs. 8 %, P<0.001). The distribution of the two groups was: group 1, n=27 patients, group 2, n=25 patients. AAA diameter and BMI were higher in group 2 than in group 1, respectively 61mm vs. 55mm, P=0.03 and 28 vs. 23, P=0.02.

CONCLUSION

Prevalence of SA in patients with an AAA seems to be significantly higher than in general population. The growth of the aneurysm seems to be linked to the severity of SA.