Using Machine Learning to Predict Five-Year Reintervention Risk in Type B Aortic Dissection Patients After Thoracic Endovascular Aortic Repair

2021 ◽  
Vol 11 (6) ◽  
pp. 1560-1567
Author(s):  
Weiyuan Lin ◽  
Lifeng Que ◽  
Guisen Lin ◽  
Rui Chen ◽  
Qiyang Lu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
High Risk ◽  
Aortic Dissection ◽  
Thoracic Endovascular Aortic Repair ◽  
Type B ◽  
Imaging Data ◽  
Type B Aortic Dissection ◽  
Medical Guidelines

Purpose: Type B aortic dissection (TBAD) is a high-risk disease, commonly treated with thoracic endovascular aortic repair (TEVAR). However, for the long-term follow-up, it is associated with a high 5-year reintervention rate for patients after TEVAR. There is no accurate definition of prognostic risk factors for TBAD in medical guidelines, and there is no scientific judgment standard for patients’ quality of life or survival outcome in the next five years in clinical practice. A large amount of medical data features makes prognostic analysis difficult. However, machine learning (ML) permits lots of objective data features to be considered for clinical risk stratification and patient management. We aimed to predict the 5-year prognosis in TBAD after TEVAR by Ml, based on baseline, stent characteristics and computed tomography angiography (CTA) imaging data, and provided a certain degree of scientific basis for prognostic risk score and stratification in medical guidelines. Materials and Methods: Dataset we recorded was obtained from 172 TBAD patients undergoing TEVAR. Totally 40 features were recorded, including 14 baseline, 5 stent characteristics and 21 CTA imaging data. Information gain (IG) was used to select features highly associated with adverse outcome. Then, the Gradient Boost classifier was trained using grid search and stratified 5-fold cross-validation, and Its predictive performance was evaluated by the area under the curve (AUC) in the receiver operating characteristic (ROC). Results: Totally 60 patients underwent reintervention during follow-up. Combing 24 features selected by IG, ML model predicted prognosis well in TBAD after TEVAR, with an AUC of 0.816 and a 95% confidence interval of 0.797 to 0.837. Reintervention rate of prediction was slightly higher than the actual (48.2% vs. 34.8%). Conclusion: Machine learning, which combined with baseline, stent characteristics and CTA imaging data for personalized risk computations, effectively predicted reintervention risk in TBAD patients after TEVAR in 5-year follow-up. The model could be used to efficiently assist the clinical management of TBAD patients and prompt high-risk factors.

Long-term Results of Thoracic Endovascular Aortic Repair for Type B Aortic Dissection and Risk Factors for Survival

2020 ◽  
Vol 27 (3) ◽  
pp. 358-367 ◽  
Author(s):  
Dong-lin Li ◽  
Yun-jun He ◽  
Xiao-hui Wang ◽  
Yang-yan He ◽  
Zi-heng Wu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Aortic Dissection ◽  
Thoracic Endovascular Aortic Repair ◽  
Long Term Results ◽  
Type B ◽  
Type B Aortic Dissection ◽  
Chronic Patients ◽  
Aneurysmal Dilatation ◽  
Factors Influencing

Purpose: To compare characteristics of acute, subacute, and chronic type B aortic dissection and their influence on long-term results of thoracic endovascular aortic repair (TEVAR). Materials and Methods: In a single-center, retrospective cohort study, 314 patients (median age 52 years; 244 men) with acute (n=165), subacute (n=115), or chronic (n=34) type B aortic dissection underwent TEVAR between January 2009 and December 2013. Patient demographics, risk factors, and imaging characteristics were compared among the groups. Univariable and multivariable Cox regression analyses were performed to identify any factors influencing survival. Results: The acute and subacute patients exhibited more complications at presentation than chronic patients. However, the chronic patients exhibited more aneurysmal dilatation (p<0.001) and true lumen collapse (p<0.001). Over a mean follow-up of 68.1±22.9 months (range 2–108), subacute patients showed a lower reintervention rate (3.6% vs 12.1% vs 12.1%, p=0.045), a lower major complication rate (14.4% vs 33.1% vs 27.3%, p=0.002), and better cumulative overall survival (p=0.03) than the acute and chronic groups, respectively. Furthermore, acute patients developed more stent-graft–induced distal erosion (p=0.017) and retrograde type A dissection (RTAD) (p=0.036), whereas chronic patients had less aortic remodeling in the stented segment (p<0.001), distal thoracic aorta (p<0.001), and abdominal aorta (p=0.047). Finally, multivariable analysis demonstrated age >52 years, visceral malperfusion, and RTAD as independent factors influencing overall survival; aneurysmal dilatation, rupture/impending rupture, and RTAD were independent factors influencing aorta-specific survival. Conclusion: Acute and subacute patients had increased risks of rupture and complications at presentation, whereas chronic patients had increased risks for aneurysmal dilatation. From a long-term perspective, the subacute phase might be an optimal time for TEVAR in cases of type B aortic dissection that do not need emergent interventions. The risk factors influencing survival should be identified, carefully managed, and possibly prevented.

Unplanned stents in thoracic endovascular aortic repair for type B aortic dissection: A 16-year single-center report

Vascular ◽  
2017 ◽  
Vol 26 (4) ◽  
pp. 400-409
Author(s):  
Junjun Liu ◽  
Rongjie Zhang ◽  
Rui Feng ◽  
Jiaxuan Feng ◽  
Zhiqing Zhao ◽  
...  
Keyword(s):  
Risk Factors ◽  
Aortic Dissection ◽  
Operation Time ◽  
Thoracic Endovascular Aortic Repair ◽  
Endovascular Aortic Repair ◽  
Rank Test ◽  
Type B ◽  
Type B Aortic Dissection ◽  
Aortic Repair ◽  
Type Ia

Background Unplanned stents in thoracic endovascular aortic repair mean additional stents implantation beyond the preoperative planning to achieve operation success. This study aimed to reveal the prevalence and consequences of unplanned stents in thoracic endovascular aortic repair for type B aortic dissection and explore the reasons, risk factors and solutions for unplanned stents. Methods Retrospectively analysis consecutive patients diagnosed as type B aortic dissection with initial tear originating distal from the left subclavian artery and underwent thoracic endovascular aortic repair from September 1998 to June 2014 in our center. Results Under the criteria, this study enrolled 322 patients, with 83 (25.8%) patients in unplanned group. The incidence rate of unplanned stents in thoracic endovascular aortic repair for type B aortic dissection in each year demonstrates as a bimodal curve. The curve showed that, 2003 and, 2004 was the first and highest peak and 2007 was the second peak. There was no difference in five-year survival rate between planned and unplanned patients (log-rank test, p = 0.994). The unplanned group had higher hospitalization expenses (142,699.08 ± 78,446.75 yuan vs. 175,238.58 ± 34,838.01 yuan; p = 0.019), longer operation time (104.50 ± 93.24 min vs. 179.08 ± 142.47 min; p < 0.001) and hospitalization time (17.07 ± 16.62 d vs. 24.00 ± 15.34 d; p = 0.001). The reasons for unplanned stents were type Ia endoleak (46 patients, 55.4%), bird beak (25 patients, 30.1%), and inappropriate shaping of stent (9 patients, 10.8%). Asymptomatic aortic dissection patients had higher incidence of unplanned stents. Short proximal neck length (2.66 ± 0.59 mm vs. 2.50 ± 0.51 mm; p = 0.016), short stent coverage length (154.62 ± 41.12 mm vs. 133.60 ± 44.33 mm; p = 0.002), and large distal stent oversize (75.44±10.77% vs. 82.68±15.80%; p <0.001) were risk factors for unplanned stents in thoracic endovascular aortic repair. Conclusion There are some special risk factors and reasons for unplanned stents in thoracic endovascular aortic repair for type B aortic dissection. Knowing these can we reduce the utilization of unplanned stents with appropriate methods.

scholarly journals Frequency of abdominal aortic expansion after thoracic endovascular repair of type B aortic dissection

Vascular ◽  
2016 ◽  
Vol 24 (6) ◽  
pp. 567-579 ◽  
Author(s):  
Tim F Weber ◽  
Dittmar Böckler ◽  
Matthias Müller-Eschner ◽  
Moritz Bischoff ◽  
Moritz Kronlage ◽  
...  
Keyword(s):  
Retrospective Study ◽  
Aortic Dissection ◽  
False Lumen ◽  
Celiac Trunk ◽  
Thoracic Endovascular Aortic Repair ◽  
Infrarenal Aorta ◽  
Type B ◽  
Type B Aortic Dissection ◽  
Abdominal Aortic

Purpose To determine abdominal aortic expansion after thoracic endovascular aortic repair (TEVAR) in patients with aortic dissection type B and 36 months minimum follow-up. Methods Retrospective study of 18 TEVAR patients with follow-up >36 months. Abdominal aortic diameters at celiac trunk (location B) and infrarenal aorta (location C) were recorded on the first and last imaging after TEVAR. False lumen thrombosis was determined at level of endograft (A) and at B and C. Aortic expansion was defined as diameter increase of 5 mm or 15%. Correlation analyses were performed to investigate potential determinants of expansion. Results Median follow-up was 75.2 months. Sixteen of 18 patients (88.9%) demonstrated abdominal expansion. Mean expansion was 9.9 ± 6.1 mm at B and 11.7 ± 6.5 mm at C, without a difference between acute and chronic dissections. Critical diameters of 55 mm were reached in two patients treated for chronic dissection (11.1%). Annual diameter increase was significantly greater at locations with baseline diameters >30 mm (2.1 ± 1.1 mm vs. 1.0 ± 0.6 mm, p = 0.009). Baseline diameters were greater in patients with chronic dissections. Conclusion Abdominal aortic expansion can be frequently recognized after TEVAR for aortic dissection type B and occurs independently from thoracic false lumen thrombosis. Clinical significant abdominal aortic expansion may occur more frequently in patients treated with TEVAR for chronic dissection.

In Situ Laser Fenestration for Delayed Left Subclavian Artery Revascularization Following Thoracic Endovascular Aortic Repair of Type B Aortic Dissection

2021 ◽  
pp. 153857442110103
Author(s):  
Zhiwei Wang ◽  
Mingxing Li ◽  
Hualong Bai ◽  
Yuanfeng Liu ◽  
Tao Bai ◽  
...  
Keyword(s):  
Aortic Dissection ◽  
Thoracic Endovascular Aortic Repair ◽  
Endovascular Aortic Repair ◽  
Type B ◽  
Type B Aortic Dissection ◽  
Technical Success Rate ◽  
Aortic Repair ◽  
Invasive Method

In situ laser fenestration (ISLF) is currently used to reconstruct the aortic major branches during thoracic endovascular aortic repair (TEVAR). To our knowledge, there have been no reports on the application of ISLF for delayed revascularization of the LSA previously sealed in TEVAR. This report describes 5 patients who underwent ISLF for delayed LSA revascularization, with a technical success rate of 80%. No endoleakage occurred, and stents remained patent during more than 6-month follow-up. ISLF is an effective, safe and minimally invasive method for delayed revascularization of the LSA following TEVAR for type B aortic dissection (TBAD) when patients are selected appropriately.

scholarly journals Assessment of Liver Function for Evaluation of Short- and Long-Term Outcomes in Type B Aortic Dissection Patients Undergoing Thoracic Endovascular Aortic Repair

2021 ◽  
Vol 8 ◽  
Author(s):  
Jitao Liu ◽  
Min Wu ◽  
Enmin Xie ◽  
Lyufan Chen ◽  
Sheng Su ◽  
...  
Keyword(s):  
Liver Fibrosis ◽  
Liver Function ◽  
Aortic Dissection ◽  
Thoracic Endovascular Aortic Repair ◽  
Endovascular Aortic Repair ◽  
Type B ◽  
Type B Aortic Dissection ◽  
Functional Reserve ◽  
Liver Functional Reserve

Background and Aims: Patients with decreased liver function suffer from poor outcomes when undergoing procedures. We aimed to explore the impact of liver fibrosis identified by aspartate transaminase-to-platelet ratio index (APRI) and poor liver functional reserve assessed by a model of end-stage liver disease (MELD) and albumin–bilirubin(ALBI) score on the prognosis of patients with type B aortic dissection (TBAD) undergoing thoracic endovascular aortic repair (TEVAR).Methods: A retrospective analysis of a prospectively maintained database from 2010 to 2017 was performed. APRI &gt; 0.5 was used to identify those with significant liver fibrosis. Logistic and Cox regression analyses were performed to investigate the association between liver fibrosis, MELD, and ALBI with adverse events.Results: TEVAR was performed on 812 TBAD patients including 35 with liver fibrosis and 777 without. Twenty-four (3.0%) patients deceased during hospitalization and 69 (8.8%) patients died after a median 48.2 months follow-up. Multivariable analysis revealed that liver fibrosis, MELD, and ALBI were independently associated with in-hospital [fibrosis: odds ratio (OR) 23.73, 95% confidence interval (CI) 8.89–63.33, P &lt; 0.001; MELD: OR 1.08, 95% CI 1.03–1.14, P = 0.003; ALBI: OR 4.45; 95% CI 1.56–12.67, P = 0.005] and follow-up mortality [fibrosis: hazard ratio (HR) 4.69, 95% CI 1.93–11.42, P = 0.001; MELD: HR 1.07, 95% CI 1.04–1.10, P &lt; 0.001; ALBI: HR 2.88, 95% CI 1.53–5.43, P = 0.001]. The association was further corroborated by a subgroup analysis.Conclusion: Liver fibrosis and poor liver functional reserve could significantly increase the morbidity and mortality after TEVAR. APRI, MELD, and ALBI should be calculated and routinely used for preoperative risk stratification. Strict preoperative preparation and elaborate postoperative care are necessary to improve these patients' prognosis.

Sign in / Sign up

Export Citation Format

Share Document