Evaluation of deep learning algorithms in detecting moyamoya disease: a systematic review and single-arm meta-analysis.

The diagnosis of Moyamoya disease (MMD) relies heavily on imaging, which could benefit from standardized machine learning tools. This study aims to evaluate the diagnostic efficacy of deep learning (DL) algorithms for MMD by analyzing sensitivity, specificity, and the area under the curve (AUC) compared to expert consensus. We conducted a systematic search of PubMed, Embase, and Web of Science for articles published from inception to February 2024. Eligible studies were required to report diagnostic accuracy metrics such as sensitivity, specificity, and AUC, excluding those not in English or using traditional machine learning methods. Seven studies were included, comprising a sample of 4,416 patients, of whom 1,358 had MMD. The pooled sensitivity for common and random effects models was 0.89 (95% CI: 0.85 to 0.92) and 0.92 (95% CI: 0.85 to 0.96), respectively. The pooled specificity was 0.89 (95% CI: 0.86 to 0.91) in the common effects model and 0.91 (95% CI: 0.75 to 0.97) in the random effects model. Two studies reported the AUC alongside their confidence intervals. A meta-analysis synthesizing these findings aggregated a mean AUC of 0.94 (95% CI: 0.92 to 0.96) for common effects and 0.89 (95% CI: 0.76 to 1.02) for random effects models. Deep learning models significantly enhance the diagnosis of MMD by efficiently extracting and identifying complex image patterns with high sensitivity and specificity. Trial registration: CRD42024524998 https://www.crd.york.ac.uk/prospero/displayrecord.php?RecordID=524998.

Brain tissue oxygen combined with intracranial pressure monitoring versus isolated intracranial pressure monitoring in patients with traumatic brain injury: an updated systematic review and meta-analysis.

Monitoring intracranial pressure (ICP) is pivotal in the management of severe traumatic brain injury (TBI), but secondary brain injuries can arise despite normal ICP levels. Cerebral tissue oxygenation monitoring (PbtO2) may detect neuronal tissue infarction thresholds, enhancing neuroprotection. We performed a systematic review and meta-analysis to evaluate the effects of combined cerebral tissue oxygenation (PbtO2) and ICP compared to isolated ICP monitoring in patients with TBI. PubMed, Embase, Cochrane, and Web of Sciences databases were searched for trials published up to June 2023. A total of 16 studies comprising 37,820 patients were included. ICP monitoring was universal, with additional placement of PbtO2 in 2222 individuals (5.8%). The meta-analysis revealed a reduction in mortality (OR 0.57, 95% CI 0.37-0.89, p = 0.01), a greater likelihood of favorable outcomes (OR 2.28, 95% CI 1.66-3.14, p < 0.01), and a lower chance of poor outcomes (OR 0.51, 95% CI 0.34-0.79, p < 0.01) at 6 months for the PbtO2 plus ICP group. However, these patients experienced a longer length of hospital stay (MD 2.35, 95% CI 0.50-4.20, p = 0.01). No significant difference was found in hospital mortality rates (OR 0.81, 95% CI 0.61-1.08, p = 0.16) or intensive care unit length of stay (MD 2.46, 95% CI - 0.11-5.04, p = 0.06). The integration of PbtO2 to ICP monitoring improved mortality outcomes and functional recovery at 6 months in patients with TBI. PROSPERO (International Prospective Register of Systematic Reviews) CRD42022383937; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=383937.

Transradial versus transfemoral approach in cerebral angiography: A meta-analysis.

BACKGROUND: Cerebral angiography has two common access sites: Transradial approach and transfemoral approach. However, there's no definitive answer to which one is superior. OBJECTIVE: Compare transradial approach and transfemoral approach for a cerebral angiography procedure. METHODS: A systematic review of the literature of studies reporting both transradial approach and transfemoral approach results was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. PubMed, Cochrane Library, and Embase were queried. RESULTS: The meta-analysis examined 18 studies comprising 9388 patients undergoing cerebral angiography. Among the patients, 4598 underwent transradial approach (48.9%) and 4790 underwent transfemoral approach (51.1%). Our results revealed no statistical differences between the approaches regarding procedure success, crossover to transfemoral approach, procedure and fluoroscopy time between both approaches in cerebral angiography. Total, major, and minor complications comparisons were more favorable to transradial approach for this procedure. CONCLUSION: These findings suggest, despite the ultimate decision regarding the choice of access method might be influenced by the physician's experience and personal preference, the data distinctly lean toward transradial approach as the preferable option for cerebral angiography. The advantages of transradial approach, highlighted by its lower complication rates, especially major complications, suggest that its adoption could contribute to enhanced patient safety and procedural outcomes.

Early ambulation versus prolonged bed rest for incidental durotomies in spine procedures: a systematic review and meta-analysis.

Incidental durotomies are frequent complications of spine surgery associated with cerebrospinal fluid (CSF) leak-related symptoms. Management typically involves prolonged bed rest to reduce CSF pressure at the durotomy site. However, early ambulation may be a safer, effective alternative. PubMed, Web of Science, Embase, Cochrane, and Scopus were systematically searched for studies comparing early ambulation (bed rest ≤ 24 h) with prolonged bed rest (> 24 h) for patients with incidental durotomies in spine surgeries. The outcomes of interest were CSF leak, hypotensive headache, additional surgical repair, pseudomeningocele, and pulmonary complications. Systematic reviews and meta-analysis were performed following the Cochrane Handbook for Systematic Reviews of Interventions. We included a total of 704 patients from 6 studies. There was a significant reduction in the incidence of pulmonary complications (RR 0.23; 95% CI 0.08-0.67; p = 0.007) in the early mobilization group. The incidence of CSF leak (RR 1.34; 95% CI 0.83-2.14; p = 0.23), hypotensive headache (RR 0.72; 95% CI 0.27-1.90; p = 0.50), additional repair surgery (RR 1.29; 95% CI 0.76-2.2; p = 0.35), and pseudomeningocele (RR 1.29; 95% CI 0.20-8.48; p = 0.79) did not differ significantly. In patients with incidental durotomy following spinal surgery, early mobilization was associated with a lower incidence of pulmonary complications as compared with prolonged bed rest. There was no significant difference between groups in terms of CSF leak, need for additional repair, pseudomeningocele, and hypotensive headache.

Machine Learning Algorithms to Predict Delayed Cerebral Ischemia After Subarachnoid Hemorrhage: A Systematic Review and Meta-analysis.

Delayed cerebral ischemia (DCI) is a common and severe complication after subarachnoid hemorrhage (SAH). Logistic regression (LR) is the primary method to predict DCI, but it has low accuracy. This study assessed whether other machine learning (ML) models can predict DCI after SAH more accurately than conventional LR. PubMed, Embase, and Web of Science were systematically searched for studies directly comparing LR and other ML algorithms to forecast DCI in patients with SAH. Our main outcome was the accuracy measurement, represented by sensitivity, specificity, and area under the receiver operating characteristic. In the six studies included, comprising 1828 patients, about 28% (519) developed DCI. For LR models, the pooled sensitivity was 0.71 (95% confidence interval [CI] 0.57-0.84; p < 0.01) and the pooled specificity was 0.63 (95% CI 0.42-0.85; p < 0.01). For ML models, the pooled sensitivity was 0.74 (95% CI 0.61-0.86; p < 0.01) and the pooled specificity was 0.78 (95% CI 0.71-0.86; p = 0.02). Our results suggest that ML algorithms performed better than conventional LR at predicting DCI.Trial Registration: PROSPERO (International Prospective Register of Systematic Reviews) CRD42023441586; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=441586.