• artificial intelligence
• carotid plaque
• deep learning techniques
• ischemic stroke
• vulnerability

• Calcification
• Carotid
• Plaque
• Stenosis
• Stenting
• Stroke
• Transcarotid revascularization
• Transfemoral

• Humans
• Carotid Stenosis/complications
• Carotid Stenosis/diagnostic imaging
• Carotid Stenosis/therapy
• Endovascular Procedures/adverse effects
• Risk Assessment
• Stents/adverse effects
• Time Factors
• Treatment Outcome
• Retrospective Studies
• Stroke/etiology
• Risk Factors
• Myocardial Infarction/etiology
• Femoral Artery
• Carotid Arteries

• acute ischemic stroke
• atherosclerosis of the carotid arteries
• high-density lipoprotein cholesterol
• peripheral lipoprotein (a)
• triglycerides

• Humans
• Plaque, Atherosclerotic/diagnostic imaging
• Ischemic Stroke/diagnostic imaging
• 1-Alkyl-2-acetylglycerophosphocholine Esterase
• Cholesterol, LDL
• Glycated Hemoglobin
• Carotid Arteries
• Triglycerides
• Carotid Stenosis/diagnostic imaging
• Lipoprotein(a)
• Risk Factors

• Carotid stenosis
• Ischemic stroke
• Low-density lipoprotein
• Stents

• Korean Society of Lipid and Atherosclerosis

The current increase in the number of publications on the use of artificial intelligence (AI) technologies in neurosurgery indicates a new trend in clinical neuroscience.

The aim of the study was to conduct a systematic literature review to highlight the main directions and trends in the use of AI in neurosurgery.

• artificial intelligence
• natural language processing
• neurosurgery
• topic modeling in neurosurgery

• TCAR
• anatomic suitability
• carotid artery stenting
• carotid bifurcation
• flow reversal
• transcarotid artery revascularization
• transcarotid artery stenting

• Flapping lung
• Jellyfish sign
• Pericardial effusion
• Pleural effusion
• Ultrasound

• Child
• Humans
• Lung/diagnostic imaging
• Pericardial Effusion/diagnostic imaging
• Pleural Effusion/diagnostic imaging
• Pneumothorax
• Pulmonary Atelectasis/diagnostic imaging
• Ultrasonography

Aim: The prediction of functional outcome is essential in the management of acute ischemic stroke patients. We aimed to explore the various prognostic factors with multivariate linear discriminant analysis or neural network analysis and evaluate the associations between candidate factors, baseline characteristics, and outcome.

Methods: Acute ischemic stroke patients ( n =1,916) with premorbid modified Rankin Scale (mRS) scores of 0–2 were analyzed. The prediction models with multivariate linear discriminant analysis (quantification theory type II) and neural network analysis (log-linearized Gaussian mixture network) were used to predict poor functional outcome (mRS 3–6 at 3 months) with various prognostic factors added to age, sex, and initial neurological severity at admission.

Results: Both models revealed that several nutritional statuses and serum alkaline phosphatase (ALP) levels at admission improved the predictive ability. Of the 1,484 patients without missing data, 560 patients (37.7%) had poor outcomes. The patients with poor outcomes had higher ALP levels than those without (294.3±259.5 vs. 246.3±92.5 U/l, P ＜0.001). Multivariable logistic analyses revealed that higher ALP levels (1-SD increase) were independently associated with poor stroke outcomes after adjusting for several confounding factors, including the neurological severity, malnutrition status, and inflammation (odds ratio 1.21, 95% confidence interval 1.02–1.49). Several nutritional indicators extracted from prediction models were also associated with poor outcome.

Conclusion: Both the multivariate linear discriminant and neural network analyses identified the same indicators, such as nutritional status and serum ALP levels. These indicators were independently associated with functional stroke outcome.

• Acute ischemic stroke
• Neural network analysis
• Outcome

Almost 90% of cerebral thromboembolism cases are caused by atherosclerosis. Craniocervical atherosclerosis is often observed at the carotid bifurcation and is responsible for 20%-30% of all stroke cases. The course of atherosclerotic carotid artery stenosis varies depending on the grade of stenosis and characteristics of the plaque. Carotid artery stenting (CAS) can be used as a less invasive method in patients with symptomatic and asymptomatic high-grade carotid artery stenosis. Diffusion-weighted imaging (DWI) is an effective method for detection of silent or symptomatic acute ischemic lesions that may arise due to CAS or carotid endarterectomy. The number and volume of new ischemic lesions are determined using DWI.

To evaluate the number and volume of ischemic lesions and their cerebral parenchymal and vascular distribution after CAS using DWI.

Forty-seven male (73.4%) and seventeen female (26.6%) patients (total, n = 64) aged 42-84 years (mean 67.96 ± 8.03 years) diagnosed with carotid stenosis between October 2006 and July 2012 were included in this retrospective study. Twelve of the cases (18.8%) were asymptomatic, while fifty-two (81.2%) were symptomatic. The area where the stenosis was highest was measured, and the stenosis rate was determined using the North American Symptomatic Carotid Endarterectomy Trial method. DWI of the cases was evaluated by two radiologists experienced in neuroradiology (B.A. with more than 15 years of experience, E.G. with more than 10 years of experience). Routine DWI examinations were carried out by a 1.5 T MR device 1 h before and after the operation. Since the ischemic lesions that developed in the first hour and in the follow-up period of 5-24 h were assumed to be due to CAS, all lesions within the first 24 h were considered as new ischemias.

In the present study, 39 new ischemic lesions were detected in 20 cases. The average number of new lesions after all CAS operations was 0.62. They were mostly located in the occipital lobes, followed by the frontal and parietal lobes. These new ischemic lesions were most common in the middle cerebral artery territory, followed by the posterior cerebral artery territory and middle cerebral artery-posterior cerebral artery watershed areas. New lesions were found in 31.2% (20/64) of patients, including 17 (26.5%) in ipsilateral and three (4.6%) in contralateral hemispheres. New bilateral lesions were detected in one case (1.5%). The average volume of the new ischemic lesions detected by the two observers was 1.10 cm³. The numbers of newly appearing ischemic lesions in DWI after CAS were significantly higher in cases where stenting was applied on the left side of the carotid artery and in cases where longer plaques (> 1 cm) were responsible for the narrowing in symptomatic patients. The stenosis rate was low in the group with ulcerated plaques.

New ischemic lesions due to CAS appear mostly in the main arterial territory but they may also occur in watershed areas.

• Carotid artery stenosis
• Carotid artery stenting
• Diffusion-weighted imaging
• Ischemia
• Stroke