Hyperdense basilar artery sign diagnoses acute posterior circulation stroke and predicts short-term outcome

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.

Diagnostic and prognostic computed tomography imaging markers in basilar artery occlusion (Review)

Acute ischemic stroke treatment has been revolutionized by the addition of mechanical and aspiration thrombectomy. Randomized controlled trials have proven beyond doubt, the substantial clinical impact of endovascular interventions in anterior circulation territory strokes. Unfortunately, patients with vertebrobasilar ischemic stroke could not be included in these early trials due to inherent clinical, radiological, and prognostic particularities of posterior circulation ischemia; thus, indications for the treatment of posterior fossa strokes and basilar artery occlusion (BAO) are mainly based on retrospective studies and registries. BAO carries high morbidity and mortality, despite the new improvements in endovascular therapy. Identifying patients who will likely benefit from invasive treatment and have a good clinical outcome resides in discovering clinical, biological, or imaging markers, that have prognostic implications. Such imaging markers have been described, especially in the last decade. Hyperdense Basilar Artery Sign (HDBA), Posterior Circulations-Alberta Stroke Program Early CT Score (pc-ASPECTS), Pons-Midbrain Index (PMI), Posterior Circulation Collateral Score (pc-CS), Posterior Circulation CT Angiography Score (pc-CTA), and Basilar Artery on CT Prognostic Score (BATMAN), are computed tomography (CT) markers with properties that can aid the diagnosis of BAO and can independently predict clinical outcome. This paper aims to present a comprehensive review of these imaging signs to have a thorough understanding of their diagnostic and prognostic attributes.

Systematic combined noncontrast CT-CT angiography in the management of unexplained nontraumatic coma

BACKGROUND

Nontraumatic impaired consciousness is a common issue in emergency departments with a serious but widely variable prognosis.

STUDY OBJECTIVES

The aim of this prospective study was to evaluate the ability of systematic combined noncontrast computed tomography (NCCT)/computed tomography angiography (CTA) imaging, firstly to provide a neurologic prognosis and secondly to ensure early detection of basilar artery occlusion (BAO), in unexplained nontraumatic impaired consciousness management.

METHODS

Combined NCCT/CTA imaging was performed on 65 patients with impaired consciousness and no history of trauma prospectively over 14 months in a single center. Images were assessed based on visual and quantitative criteria. Clinical outcome was assessed using the modified Rankin Scale at 3 months. Statistical analysis aimed to identify the prognostic value of combined NCCT/CTA imaging and its ability for early BAO detection.

RESULTS

This study shows that combined NCCT/CTA imaging was a significant predictor of poor neurological outcome, with a positive predictive value of 94.6%. The combination was also crucial for early detection of BAO, given that 42.8% of cases were misdiagnosed with NCCT alone. Basilar artery occlusion represented 10.8% of all unexplained nontraumatic impaired consciousness.

CONCLUSIONS

Systematic combined NCCT/CTA imaging is an efficient tool for predicting poor neurologic prognosis in cases of unexplained nontraumatic impaired consciousness and is also essential for detecting BAO.