Cervical artery dissection is an uncommon but important cause of ischemic stroke in young adults. Severe cough or infection may precipitate arterial injury through mechanical stress or inflammation. We report the case of a 35-year-old man who presented with sudden severe posterior neck pain and headache after severe coughing during COVID-19. Brain magnetic resonance imaging (MRI) and angiography revealed infarction of the left middle cerebral artery and stenosis of the left carotid and vertebral arteries with aneurysmal dilatation. Vessel wall MRI revealed intramural hematomas in the left internal carotid artery and both vertebral arteries, confirming the diagnosis of multiple arterial dissections. The patient was treated with dual antiplatelet therapy, and his clinical condition subsequently improved. This case highlights that a cough associated with COVID-19 may trigger cervical artery dissection and that vessel wall MRI helps detect intramural hematomas in the subacute phase.

SARS-CoV-2 is a global pandemic with high mortality and prevalence. Although the disease severity has weakened, it remains a significant global health burden as an endemic disease. Several reports have explored the relationship between intracranial artery dissection and SARS-CoV-2 infection; however, an association with SARS-CoV-2 vaccination has not been established. Here, we describe three cases of vertebral arterial dissection with acute ischemic stroke after SARS-CoV-2 vaccination. This report aimed to raise the clinical awareness of this potential adverse effect, which may facilitate earlier diagnosis and intervention.

Background: Poor outcomes after acute ischemic stroke (AIS) revascularization are anticipated in patients with dementia due to advanced age, comorbidities, and reduced disease awareness. This study investigated clinical characteristics and short-term outcomes of AIS revascularization in patients undergoing dementia treatment. Methods: We retrospectively reviewed patients who underwent AIS revascularization therapy at eight centers of the Catholic University of Korea. Patients receiving anti-dementia medication for cognitive impairment before stroke onset were analyzed. Clinical characteristics and outcomes, including the modified Rankin Scale (mRS) score, hemorrhagic transformation, and mortality, were collected. Results: Among 1,379 patients who received AIS revascularization over 5 years, 13 (0.94%; mean age 83 years; 8 females) had a preexisting diagnosis of dementia (Alzheimer’s disease in 11, mild cognitive impairment in 2) and were on anti-dementia medication. Two patients underwent intravenous thrombolysis combined with endovascular therapy, whereas 11 underwent endovascular therapy alone. Most patients (11/13, 84.6%) presented with an unclear onset time. Stroke lesions were located in the right middle cerebral artery (MCA) in seven cases, left MCA in three, bilateral MCAs in one, and posterior circulation in two. Hemorrhagic transformation occurred in six patients (46%), of whom three (23%) were symptomatic. The mRS scores at discharge were 6 in two patients, 5 in one patient, 4 in nine patients, and 3 in one patient. Four patients died within 3 months of stroke onset. Conclusion The proportion of patients with cognitive impairment receiving anti-dementia medication among those undergoing stroke revascularization therapy was very small. The rates of hemorrhagic transformation and mortality were high. None of the patients achieved favorable outcomes at discharge.

Artificial intelligence (AI), particularly deep learning, continues to advance in medical image analysis and clinical prediction. In stroke care—where timely, accurate decisions are critical—AI is seen as a promising tool, with potential to detect complex imaging patterns and enhance clinical workflows. However, practical application in real-world settings remains limited, often due to structural issues in model design, evaluation, and insufficient integration of clinical context. This narrative review examines common pitfalls in developing and applying AI models in stroke care. High performance alone does not ensure clinical value; what matters is whether the predicted target (label) is clinically meaningful and well-defined. If the label is ambiguous or fails to reflect the underlying clinical condition, even highly accurate models may produce misleading or unhelpful outputs. We also discuss limitations of current explainability tools and emphasize that lack of interpretability hinders trust and adoption in high-stakes decisions. Rather than functioning as autonomous decision-makers, AI models are better positioned as coordinators or accelerators—supporting, not replacing, clinical judgment. For responsible integration into practice, developers must disclose key aspects of the model, including training data, label definitions, and performance conditions. Clinicians, in turn, should be prepared to interpret evaluation metrics in the context of real-world care. Ultimately, clinical AI should focus not merely on maximizing performance but on solving problems relevant to clinical practice, with transparency and explainability as essential prerequisites for adoption.

Background: This study aimed to identify the associated factors for brain metastasis (BM) in patients with anaplastic thyroid cancer (ATC) and estimate the diagnostic yield of staging brain magnetic resonance imaging (MRI) during the initial evaluation of ATC. Methods: This retrospective, single-center study included patients newly diagnosed with ATC who underwent brain MRI, from May 2008 to July 2024. The patients were stratified into two groups (BM vs. non-BM). The clinical characteristics of ATC were compared between the two groups using the chi-squared test and multivariable logistic regression analysis. The diagnostic yield of initial staging brain MRI from 2010 to 2024 was calculated. Results: A total of 77 patients (61.52±13.19 years old, 37 men) were included. BM was observed in 19 patients (24.7%). The occurrence of BM was significantly associated with extracranial metastasis (p=0.004), especially lung metastasis (p=0.017), and neurologic symptoms (p=0.001). On multivariable logistic regression analysis, after adjusting for age, sex, and primary thyroid tumor size, the presence of extracranial metastases (odds ratio [OR]: 16.09 [2.39–360.70], p=0.019) and neurologic symptoms (OR: 5.95 [1.73–24.08], p=0.007) were independently associated with BM. The diagnostic yield of staging brain MRI during the initial evaluation of ATC was 6.1% (3/49). The diagnostic rate of BM was 26.5% (18/68) in patients with extracranial metastases and 38.9% (14/36) in those with neurological symptoms. Conclusion Routine staging or surveillance brain MRI in patients with extracranial metastasis is likely to offer significant benefits.

Background: We aimed to determine whether carotid and vertebral duplex sonography can predict adverse outcomes in stroke patients with atrial fibrillation (AF). Methods: A total of 207 stroke patients with AF were analyzed. The key metrics included the carotid plaque score (CPS, 0–24), mean carotid intima-media thickness (cIMT), and high-risk features of sonography (HRFS). HRFS were defined as the presence of ulcerative, irregular, heterogeneous, or hypoechoic plaques; >50% carotid steno-occlusion; or abnormal Doppler spectra in the V2 vertebral artery segment. Predictors of future vascular events and major adverse cardiovascular events (MACEs) were identified using Cox regression, with adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) calculated. The integrated time-dependent area under the curve for HRFS, CHA2DS2-VASc score, mean cIMT, and CPS was also assessed. Results: HRFS (aHR 4.86, 95% CI 1.41–16.77) were independently associated with future vascular events. Age (aHR 1.06, 95% CI 1.02–1.11), chronic kidney disease (aHR 2.03, 95% CI 1.00–4.12), admission National Institutes of Health stroke scale (aHR 1.04, 95% CI 1.00–1.08), and HRFS (aHR 2.45, 95% CI 1.18–5.08) were independently associated with MACE. Adverse outcomes were significantly more frequent in patients with HRFS (p<0.001, log-rank test). HRFS demonstrated a significantly better discriminatory ability than mean cIMT in predicting outcomes. Conclusion Duplex ultrasonography of the carotid and vertebral arteries is crucial for predicting MACE in stroke patients with AF. HRFS, rather than CPS or mean cIMT, may be a better marker for predicting MACE in this population.