Ghoche, Maged

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.

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.