Higher Prevalence of Diabetes in Pontine Infarction than in Other Posterior Circulation Strokes

The Body Mass Index as a Determinant of Acute Ischemic Location in Mild Non-cardioembolic Stroke Patients

Objective Although the body mass index (BMI) is considered a meaningful parameter for evaluating obesity, the association between the BMI and acute non-cardioembolic stroke remains unclear. We investigated how the BMI was related to patients' background, type of infarction, and infarction location in patients with non-cardioembolic stroke using an acute dual study (ADS) cohort. Methods The ADS trial was conducted between May 2011 and June 2017 in Japan. The BMI classifications were those proposed by the World Health Organization classification: underweight, <18.5 kg/m2; normal weight, 18.5-24.9 kg/m2; overweight, 25-29.9 kg/m2; and obese, ≥30 kg/m2. Results Data from 1,136 patients were analyzed. The median BMI was 23.6 kg/m2 (interquartile range: 21.6-25.8 kg/m2), with a BMI ≥30 kg/m2 in 63 patients (6%), 25-29.9 kg/m2 in 321 (28%), 18.5-24.9 kg/m2 in 692 (61%), and <18.5 kg/m2 in 60 (5%). The group with a BMI ≥30 kg/m2 was the youngest, and the group with a BMI <18.5 kg/m2 was the oldest (p<0.001). The proportion of patients with a history of hypertension (p<0.001), diabetes (p<0.001), dyslipidemia (p<0.001), and statin therapy (p=0.005) increased with increasing BMI. Pontine infarcts were frequent in the following order: obese, overweight, normal weight, and underweight (24%, 18%, 14%, and 13%, respectively; p=0.034). In contrast, cortical infarct were frequent in the order of underweight, normal weight, overweight, and obese at 20%, 19%, 14%, and 3%, respectively (p=0.007). Conclusion Acute stroke patients with a high BMI have more atherosclerosis-related factors in their backgrounds than those with lower BMIs. In addition, the BMI may be a determinant of infarct location in patients with acute stroke.

Utilizing machine learning to facilitate the early diagnosis of posterior circulation stroke

BACKGROUND

Posterior Circulation Syndrome (PCS) presents a diagnostic challenge characterized by its variable and nonspecific symptoms. Timely and accurate diagnosis is crucial for improving patient outcomes. This study aims to enhance the early diagnosis of PCS by employing clinical and demographic data and machine learning. This approach targets a significant research gap in the field of stroke diagnosis and management.

METHODS

We collected and analyzed data from a large national Stroke Registry spanning from January 2014 to July 2022. The dataset included 15,859 adult patients admitted with a primary diagnosis of stroke. Five machine learning models were trained: XGBoost, Random Forest, Support Vector Machine, Classification and Regression Trees, and Logistic Regression. Multiple performance metrics, such as accuracy, precision, recall, F1-score, AUC, Matthew's correlation coefficient, log loss, and Brier score, were utilized to evaluate model performance.

RESULTS

The XGBoost model emerged as the top performer with an AUC of 0.81, accuracy of 0.79, precision of 0.5, recall of 0.62, and F1-score of 0.55. SHAP (SHapley Additive exPlanations) analysis identified key variables associated with PCS, including Body Mass Index, Random Blood Sugar, ataxia, dysarthria, and diastolic blood pressure and body temperature. These variables played a significant role in facilitating the early diagnosis of PCS, emphasizing their diagnostic value.

CONCLUSION

This study pioneers the use of clinical data and machine learning models to facilitate the early diagnosis of PCS, filling a crucial gap in stroke research. Using simple clinical metrics such as BMI, RBS, ataxia, dysarthria, DBP, and body temperature will help clinicians diagnose PCS early. Despite limitations, such as data biases and regional specificity, our research contributes to advancing PCS understanding, potentially enhancing clinical decision-making and patient outcomes early in the patient's clinical journey. Further investigations are warranted to elucidate the underlying physiological mechanisms and validate these findings in broader populations and healthcare settings.

The prevalence and clinical significance of intracranial vertebral artery terminated in posterior inferior cerebellar artery: A multicenter hospital-based study in China

Objective

Intracranial vertebral artery terminated in the posterior inferior cerebellar artery (PICA-VA) is the most popular variant of the posterior inferior cerebellar artery, while its prevalence and clinical significance remained unclear. In the present study, we aimed to investigate the prevalence and clinical significance of PICA-VA.

Methods

This was a multicenter hospital-based cross-sectional study. Patients were enrolled for cerebral MRI and MRA within 1 week of stroke onset. Clinical characteristics were recorded. PICA-VA is termed as a vertebral artery that does not communicate with the basilar artery but terminates in an ipsilateral PICA. We observed the prevalence of PICA-VA and identified a relationship between PICA-VA and vertebrobasilar stroke.

Results

From 1 August 2015 to 31 May 2017, a total of 2,528 patients were enrolled in the present study. Among them, 95 patients (3.76%, 95/2,528) had the variation of PICA-VA, 51 of which (53.7%) were located on the right side. The prevalence of vertebrobasilar stroke was considerably higher in patients with PICA-VA than those without (40.2%, 37/92 vs. 17.1%, 417/2,436, p < 0.01). PICA-VA was an independent risk for vertebrobasilar stroke after being adjusted for a history of intracranial hemorrhage, diabetes, body mass index, and triglyceride.

Conclusion

The present study showed that 3.76% of patients with acute stroke had PICA-VA, which independently increased the risk of acute vertebrobasilar stroke.