Citations

BACKGROUND AND OBJECTIVES: Aneurysm risk prediction remains an imprecise science that places patients at risk for either over or undertreatment. Machine learning (ML) models may improve clinical practice by adding precision to risk assessment. This study aims to comprehensively assess the current landscape of ML applications in predicting the risk of aneurysm rupture and compare the performance with the widely used PHASES score. METHODS: A systematic review of PubMed, Scopus, and Web of Science was conducted. All studies using ML tools to predict the rupture risk of intracranial aneurysms were included. Meta-analysis was conducted with consideration to the ML algorithms and compared with the PHASES score. RESULTS: Thirty-six studies involving 22 462 patients were included in the final analysis. ML techniques, including 124 models using 25 algorithms, were employed. Among various ML models, while they had comparable diagnostic performance, deep learning exhibited a slightly better performance profile (sensitivity = 0.792, specificity = 0.788, and accuracy = 0.778 in external validation). Based on our analysis, ML, regardless of the algorithm, provides comparable sensitivity (0.743 vs 0.771, P = .60) and higher specificity (0.763 vs 0.507, P < .01) compared with the PHASES score. Consistently, pooling the area under the receiver operating characteristic curve (AUC) for 60 ML models and 5 PHASES score data, ML models exhibited higher AUC (0.84 vs 0.64, P < .01). Using hemodynamic parameters as input for models improved specificity ( P < .01) in the test sets without any significant changes in the sensitivity. The later improvement was not observed in the external validation sets. CONCLUSION: ML techniques have the potential to enhance the prediction of intracranial aneurysm rupture compared with traditional approaches, like the PHASES score. Incorporating hemodynamic parameters may further enhance the accuracy of ML models. Feature prospective studies are required to validate the utility of ML models for clinical integration.

Abstract Purpose: Monitoring disease progression in patients with high-grade gliomas (HGG) is challenging due to treatment-related changes in imaging and the requirement for neurosurgical intervention to obtain diagnostic tissue. DNA junctions in HGG often amplify oncogenes, making these DNA fragments potentially more abundant in blood than monoallelic mutations. In this study, we piloted a cell-free DNA approach for disease detection in the plasma of patients with HGG by leveraging patient-specific DNA junctions associated with oncogene amplifications. Experimental Design: Whole-genome sequencing of grade 3 or 4 isocitrate dehydrogenase–mutant or wild-type astrocytomas was utilized to identify amplified junctions. Individualized qPCR assays were developed using patient-specific primers designed for the amplified junction. ctDNA levels containing these junctions were measured in patient plasma samples. Results: Unique amplified junctions were evaluated by individualized semi-qPCR assays in presurgical plasma of 18 patients, 15 with tumor-associated focal amplifications and three without tumor-associated focal amplifications. high copy-number junctions were robustly detected in the plasma of 14 of 15 (93.3%) patients with amplified junctions and none of the controls. Changes in junction abundance correlated with disease trajectory in serial plasma samples from five patients, including increased abundance of amplified junctions preceding radiographic disease progression. Conclusions: In patients with grade 3 or 4 astrocytomas who had tumor-associated amplifications, patient-specific amplified junctions were successfully detected in assayed plasma from most patients. Longitudinal analysis of plasma samples correlated with disease trajectory, including cytoreduction and progression.

Telesurgery has the potential to overcome geographical barriers in surgical care, encouraging its deployment in areas with sparse surgical expertise. Despite successful in-human experiments and substantial technological progress, the adoption of telesurgery remains slow. In this Review, we analyze the reasons for this slow adoption. First, we identify various contexts for telesurgery and highlight the vastly different requirements for their realization. We then discuss why procedures with high urgency and skill sparsity are particularly suitable for telesurgery. Last, we summarize key research areas essential for further progress. The goal of this Review is to provide the reader with a comprehensive analysis of the current state of telesurgery research and to provide guidance for faster adoption of this exciting technology.

OBJECTIVE Patients with autosomal dominant polycystic kidney disease (ADPKD) have been identified to have a significantly increased risk of developing intracranial aneurysms (IAs). These patients are diagnosed at younger ages and are also at increased risk for IA rupture. The objective of this systematic review and meta-analysis was to identify risk factors associated with IA detection during screening of asymptomatic ADPKD patients. METHODS The authors searched for studies reporting the prevalence of IA among patients with ADPKD screened using MRA, CTA, or DSA on PubMed, Embase, Google Scholar, Scopus, Web of Science, Cochrane Database of Systematic Reviews, and ClinicalTrials.gov prior to August 2023 by using individualized standardized search strategies. Eligibility of all retrieved studies was assessed according to the PRISMA guidelines. Risk of bias of the included observational studies was assessed using the Newcastle-Ottawa Scale. Meta-analysis was performed using a random-effects model. RESULTS Twenty-four observational studies involving 5907 patients with ADPKD were identified for quantitative analysis. The authors observed an overall prevalence of IA of 12.6%. They identified several risk factors for IA with statistically significantly increased odds for unruptured IA (UIA) detection, including female sex (18 studies, OR 1.63, 95% CI 1.37–1.94, I 2 = 0%), family history of either IA or subarachnoid hemorrhage (SAH) (12 studies, OR 2.17, 95% CI 1.68–2.81, I 2 = 0%), family history of SAH (3 studies, OR 2.67, 95% CI 1.25–5.71, I 2 = 66.0%), stage 3 or greater chronic kidney disease (CKD) (4 studies, OR 2.55, 95% CI 1.84–3.54, I 2 = 0%), and hypertension (13 studies, OR 1.41, 95% CI 1.04–1.91, I 2 = 34%). Age > 45 years, family history of ADPKD, smoking status, and presence of liver cysts did not reach statistical significance as risk factors during this meta-analysis. CONCLUSIONS The results of the authors’ meta-analysis suggest increased risk of UIA detection in screening of ADPKD patients who are female, have a family history of IA or SAH, have hypertension, or have moderate or more severe CKD. Given the increased prevalence of IA in ADPKD patients with these risk factors, these patients may stand to benefit from screening for IA early in treatment or at time of diagnosis, even if neurologically asymptomatic.