ABSTRACT
It is possible to identify unruptured intracranial aneurysms (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk. PubMed, Scopus, Web of Science, and Embase were searched without restrictions until March 20, 2023. Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI. Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. Middle cerebral artery (MCA) and anterior cerebral artery (ACA) were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively. The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (27%) used deep learning techniques such as CNNs and ANNs. Meta-analysis was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01). ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.
Subject(s)
Intracranial Aneurysm , Stroke , Humans , Intracranial Aneurysm/diagnostic imaging , Algorithms , Angiography, Digital Subtraction , Machine LearningABSTRACT
BACKGROUND: Prior guidelines recommended maintaining normothermia following traumatic brain injury (TBI), but recent studies suggest therapeutic hypothermia as a viable option in pediatric cases. However, some others demonstrated a higher mortality rate. Hence, the impact of hypothermia on neurological symptoms and overall survival remains contentious. METHODS: We conducted a systematic review and meta-analysis to evaluate the effects of hypothermia on neurological outcomes in pediatric TBI patients. The PubMed/Medline, Scopus, and Web of Science databases were searched until 1 January 2024 and data were analyzed using appropriate statistical methods. RESULTS: A total of eight studies, comprising nine reports, were included in this analysis. Our meta-analysis did not reveal significant differences in mortality (RR = 1.58; 95% CI = 0.89-2.82, p = 0.055), infection (RR = 0.95: 95% CI = 0.79-1.1, p = 0.6), arrhythmia (RR = 2.85: 95% CI = 0.88-9.2, p = 0.08), hypotension (RR = 1.54: 95% CI = 0.91-2.6, p = 0.10), intracranial pressure (SMD = 5.07: 95% CI = -4.6-14.8, p = 0.30), hospital length of stay (SMD = 0.10; 95% CI = -0.13-0.3, p = 0.39), pediatric intensive care unit length of stay (SMD = 0.04; 95% CI = -0.19-0.28, p = 0.71), hemorrhage (RR = 0.86; 95% CI = 0.34-2.13, p = 0.75), cerebral perfusion pressure (SMD = 0.158: 95% CI = 0.11-0.13, p = 0.172), prothrombin time (SMD = 0.425; 95% CI = -0.037-0.886, p = 0.07), and partial thromboplastin time (SMD = 0.386; 95% CI = -0.074-0.847, p = 0.10) between the hypothermic and non-hypothermic groups. However, the heart rate was significantly lower in the hypothermic group (-1.523 SMD = -1.523: 95% CI = -1.81--1.22 p < 0.001). CONCLUSIONS: Our findings challenge the effectiveness of therapeutic hypothermia in pediatric TBI cases. Despite expectations, it did not significantly improve key clinical outcomes. This prompts a critical re-evaluation of hypothermia's role as a standard intervention in pediatric TBI treatment.
ABSTRACT
BACKGROUND: Diffuse midline gliomas (DMGs) encompass a set of tumors, and those tumors with H3K27M mutation carry a poor prognosis. In recent years, machine learning (ML)-based radiomics have shown promising results in predicting gene mutation status non-invasively. Therefore, this study aims to comprehensively evaluate the diagnostic performance of ML-based magnetic resonance imaging (MRI) radiomics in predicting H3K27M mutation status in DMG patients. METHODS: A systematic search was conducted using relevant keywords in PubMed/Medline, Scopus, Embase, and Web of Science from inception to May 2023. Original studies evaluating the diagnostic performance of ML models in predicting H3K27M mutation status in DMGs were enrolled. Quality assessment of the enrolled studies was conducted using QUADAS-2. Data were analyzed using STATA version 17.0 to calculate pooled sensitivity, specificity, positive (PLR) and negative likelihood ratio (NLR), diagnostic score, and diagnostic odds ratio (DOR). RESULTS: A total of 13 studies, including 12 retrospectives and one both retrospective and prospective study, enrolled 1510 (male=777) DMG patients. Six studies underwent meta-analysis which showed a pooled sensitivity, specificity, PLR, NLR, diagnostic score, and DOR of 0.91 (95% CI 0.77-0.97), 0.81 (95% CI 0.73-0.88), 4.86 (95% CI 3.25-7.24), 0.11 (95% CI 0.04-0.29), 3.75 (95% CI 2.62-4.88), and 42.61 (95% CI 13.77-131.87), respectively. CONCLUSION: Non-invasive prediction of H3K27M mutation status in patients with DMGs using MRI radiomics is a promising tool with good diagnostic performance. However, the pooled metrics had a wide confidence interval, which required further studies to enhance ML algorithms' accuracy and facilitate their integration into daily clinical practice.
ABSTRACT
BACKGROUND: Wide-necked bifurcation aneurysms (WNBAs) are challenging intracranial aneurysms. Several device and treatment approaches have been proposed for the treatment of WNBAs. The endovascular clip system (eCLIPs) is a newly developed endovascular device with flow diverter and flow disruptor features. This study aims to investigate the safety and efficacy of the eCLIPs for treatment of patients with WNBAs. METHODS: This is a systematic review and meta-analysis study conducted in accordance with the PRISMA (preferred reporting items for systematic reviews and meta-analyses) guidelines. The electronic databases of PubMed, Embase, Scopus, and Web of Science were systematically reviewed from inception to June 19, 2023. The rate of complete and near-complete occlusion, successful device implantation, and serious adverse events were pooled using STATA, version 17. RESULTS: A total of 5 studies with 110 patients with WNBAs were systematically investigated. Our findings show that the immediate successful implantation rate of eCLIPs was 0.93 (95% confidence interval [CI], 0.88-0.97). Moreover, the immediate postoperative complete occlusion rate was 0.34 (95% CI, 0.10-0.58), and the immediate postoperative near-complete occlusion rate was 0.35 (95% CI, 0.24-0.45). Also, the near-complete occlusion rate at the latest follow-up was 0.3 (95% CI, 0.16-0.44). The serious adverse event rate was 0.14 (95% CI, 0.05-0.22). Stroke was also reported in 2 studies, with 1 study reporting 1 patient who experienced stroke within the first 24 hours and 1 study reporting no patients with stroke. CONCLUSIONS: Our findings document that the eCLIPs is a safe and effective device for treating patients with WNBAs and associated with favorable outcomes.