ABSTRACT
BACKGROUND: Machine learning (ML) may be superior to traditional methods for clinical outcome prediction. We sought to systematically review the literature on ML for clinical outcome prediction in cerebrovascular and endovascular neurosurgery. METHODS: A comprehensive literature search was performed, and original studies of patients undergoing cerebrovascular surgeries or endovascular procedures that developed a supervised ML model to predict a postoperative outcome or complication were included. RESULTS: A total of 60 studies predicting 71 outcomes were included. Most cohorts were derived from single institutions (66.7%). The studies included stroke (32), subarachnoid hemorrhage ((SAH) 16), unruptured aneurysm (7), arteriovenous malformation (4), and cavernous malformation (1). Random forest was the best performing model in 12 studies (20%) followed by XGBoost (13.3%). Among 42 studies in which the ML model was compared with a standard statistical model, ML was superior in 33 (78.6%). Of 10 studies in which the ML model was compared with a non-ML clinical prediction model, ML was superior in nine (90%). External validation was performed in 10 studies (16.7%). In studies predicting functional outcome after mechanical thrombectomy the pooled area under the receiver operator characteristics curve (AUROC) of the test set performances was 0.84 (95% CI 0.79 to 0.88). For studies predicting outcomes after SAH, the pooled AUROCs for functional outcomes and delayed cerebral ischemia were 0.89 (95% CI 0.76 to 0.95) and 0.90 (95% CI 0.66 to 0.98), respectively. CONCLUSION: ML performs favorably for clinical outcome prediction in cerebrovascular and endovascular neurosurgery. However, multicenter studies with external validation are needed to ensure the generalizability of these findings.
ABSTRACT
RATIONALE: Cardioprotective pathways may involve a mitochondrial ATP-sensitive potassium (mitoK(ATP)) channel but its composition is not fully understood. OBJECTIVE: We hypothesized that the mitoK(ATP) channel contains a sulfonylurea receptor (SUR)2 regulatory subunit and aimed to identify the molecular structure. METHODS AND RESULTS: Western blot analysis in cardiac mitochondria detected a 55-kDa mitochondrial SUR2 (mitoSUR2) short form, 2 additional short forms (28 and 68 kDa), and a 130-kDa long form. RACE (Rapid Amplification of cDNA Ends) identified a 1.5-Kb transcript, which was generated by a nonconventional intraexonic splicing (IES) event within the 4th and 29th exons of the SUR2 mRNA. The translated product matched the predicted size of the 55-kDa short form. In a knockout mouse (SUR2KO), in which the SUR2 gene was disrupted, the 130-kDa mitoSUR2 was absent, but the short forms remained expressed. Diazoxide failed to induce increased fluorescence of flavoprotein oxidation in SUR2KO cells, indicating that the diazoxide-sensitive mitoK(ATP) channel activity was associated with 130-kDa-based channels. However, SUR2KO mice displayed similar infarct sizes to preconditioned wild type, suggesting a protective role for the remaining short form-based channels. Heterologous coexpression of the SUR2 IES variant and Kir6.2 in a K(+) transport mutant Escherichia coli strain permitted improved cell growth under acidic pH conditions. The SUR2 IES variant was localized to mitochondria, and removal of a predicted mitochondrial targeting sequence allowed surface expression and detection of an ATP-sensitive current when coexpressed with Kir6.2. CONCLUSIONS: We identify a novel SUR2 IES variant in cardiac mitochondria and provide evidence that the variant-based channel can form an ATP-sensitive conductance and may contribute to cardioprotection.
