Background
The risk of spinal cord ischemia (SCI) with aortic aneurysm repair can cause significant
neurological morbidity. Prevention of SCI is critical. We sought to identify risk
factors that predispose to SCI that may guide strategies to mitigate the occurrence
of SCI during and following these procedures.
Methods
This study includes all adults who underwent atraumatic, unruptured, thoracic, and
suprarenal aortic aneurysm repairs (endovascular or open) at our institution over
11 years (2010–2020). Our database included patient demographics, aneurysm anatomic
features, and operative characteristics and an extreme gradient boost (XGB) machine
method was used to develop a predictive model for SCI. The model was trained on an
80% randomly stratified cohort of the data and tested on the remaining 20% testing
cohort. Shapley values were used to determine the most important predictive factors
of SCI and decision trees were used to identify risk factor threshold values and highest
risk factor combinations.
Results
Information was collected for 174 adult patients undergoing thoracic and suprarenal
aortic repair from 2010 to 2020. Fifty eight percent of the patients were male. Ninety
seven (55.7%) patients had open aortic repair and 87 (44.3%) had endovascular repair.
Twenty seven (15%) of all patients had major complications and were considered to
have SCI. The XGB model converged over the training cohort with a testing cohort accuracy
of 0.841 [Sensitivity = 75%, Specificity = 68%] and area under the curve of receiver
operating characteristic of 0.774. The XGB model identified older age (> 65 years),
history of neurologic disease, hyperlipidemia, diabetes, coronary artery disease,
heart failure, poor renal function, < 6 months since last aortic repair, chronic anticoagulant
use, preoperational anemia (Hemoglobin < 9), thrombocytopenia (platelet < 90,000),
coagulopathy (prothrombin time > 15s and activated partial thromboplastin time > 40s),
hypotension (mean arterial pressure < 70 mm Hg), longer operations (> 100 min), aneurysms
longer than 5 cm, and anatomic location of aneurysm caudal to T-11 as risk factors
for SCI in all types of aortic repair. Diabetic and heart failure patients undergoing
longer operations (> 100 min) with thrombocytopenia or aneurysms longer than 5 cm
were at the highest risk.
Conclusions
The XGB model accurately identified risk factors of SCI with aortic aneurysm repair
that may guide patient selection, timing of surgery, and strategies to minimize the
risk of SCI.
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Annals of Vascular SurgeryAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Intraoperative neuroprotective interventions prevent spinal cord ischemia and injury in thoracic endovascular aortic repair.J Vasc Surg. 2016; 63: 1458-1465
- Spinal cord injury after thoracic endovascular aortic aneurysm repair.Can J Anaesth. 2017; 64: 1218-1235
- Lumbar drains for vascular procedures: an institutional protocol review and guidelines.World Neurosurg. 2021; 149: e947-e957
- Risk factors for spinal cord ischaemia after thoracic endovascular aortic repair.Interact Cardiovasc Thorac Surg. 2018; 27: 54-59
- Spinal cord protection in aortic endovascular surgery.Br J Anaesth. 2016; 117: ii26-ii31
- Predicting the risk of paraplegia after thoracic and thoracoabdominal aneurysm repair.Ann Thorac Surg. 2010; 90 (discussion 1245): 1237-1244
- Contemporary spinal cord protection during thoracic and thoracoabdominal aortic surgery and endovascular aortic repair: a position paper of the vascular domain of the European Association for Cardio-Thoracic Surgery.Eur J Cardiothorac Surg. 2015; 47: 943-957
- Complications associated with lumbar drain placement for endovascular aortic repair.J Vasc Surg. 2020; 71: e38
- XGBoost: a scalable tree boosting system.in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY2016
- Key challenges for delivering clinical impact with artificial intelligence.BMC Med. 2019; 17: 195
- Procalcitonin, interleukin-6 and C-reactive protein levels predict renal adverse outcomes and mortality in patients with acute type A aortic dissection.Front Surg. 2022; 9: 902108
- Welcome to the tidyverse.J Open Source Softw. 2019; 4: 1686
- Risk of spinal cord ischemia after fenestrated or branched endovascular repair of complex aortic aneurysms.J Vasc Surg. 2019; 69: 357-366
- Abstract TP157: rates of spinal cord infarction after repair of aortic aneurysm or dissection.Stroke. 2017; 48
- Preventing spinal cord injury following thoracoabdominal aortic aneurysm repair: the battle to eliminate paraplegia.JTCVS Tech. 2021; 8: 11-15
- Descending thoracic aortic aneurysm repair: 12-year experience using distal aortic perfusion and cerebrospinal fluid drainage.J Vasc Surg. 2006; 43: 639
- Risk factors for spinal cord ischemia after endovascular repair of thoracoabdominal aortic aneurysms.J Vasc Surg. 2015; 61: 1408-1416
- Spinal cord ischaemia in endovascular thoracic and thoraco-abdominal aortic repair: review of preventive strategies.J Vasc Surg. 2018; 68: 312
- Hypogastric and subclavian artery patency affects onset and recovery of spinal cord ischemia associated with aortic endografting.J Vasc Surg. 2014; 59: 89-94
- Spinal cord ischemia after endovascular aortic repair of a unilateral iliac artery dissecting aneurysm: a case report.Ann Vasc Surg. 2019; 59: 306.e1-306.e5
- POS0274 prediction of vascular complications in Takayasu arteritis by machine learning: a proof-of-concept study based on a prospective cohort.Ann Rheum Dis. 2022; 81: 380
- Image-Derived geometric characteristics predict abdominal aortic aneurysm growth in a machine learning model.in: Functional Imaging and Modeling of the Heart. Springer, Cham2021: 35-45
- Estimation of surgery durations using machine learning methods-A cross-country multi-site collaborative study.Healthcare (Basel). 2022; 10: 1191
- Neuromonitoring, cerebrospinal fluid drainage, and selective use of iliofemoral conduits to minimize risk of spinal cord injury during complex endovascular aortic repair.J Endovasc Ther. 2016; 23: 139-149
- RR24. Fate of patients with spinal cord ischemia(SCI) complicating thoracic endovascular aortic repair (TEVAR).J Vasc Surg. 2012; 55: 98S-99S
- Risk of spinal cord ischemia after endograft repair of thoracic aortic aneurysms.J Vasc Surg. 2001; 34: 997-1003
- Risk factors for spinal cord ischemia and complications of cerebrospinal fluid drainage in patients undergoing fenestrated and branched endovascular aneurysm repair.J Vasc Surg. 2020; 72: e182
Article info
Publication history
Published online: January 02, 2023
Accepted:
December 16,
2022
Received:
July 12,
2022
Footnotes
Disclosure: None of the authors have any disclosures or conflicts of interest.
Identification
Copyright
© 2022 Elsevier Inc. All rights reserved.
