Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting out of Memphis, Tennessee, by NewsRx editors, research stated, "Machine learning (ML) may be superior to trad itional methods for clinical outcome prediction. We sought to systematically rev iew the literature on ML for clinical outcome prediction in cerebrovascular and endovascular neurosurgery." Our news journalists obtained a quote from the research from Semmes-Murphey Neur ologic and Spine Institute, "A comprehensive literature search was performed, an d original studies of patients undergoing cerebrovascular surgeries or endovascu lar procedures that developed a supervised ML model to predict a postoperative o utcome or complication were included. A total of 60 studies predicting 71 outcom es were included. Most cohorts were derived from single institutions (66.7% ). The studies included stroke (32), subarachnoid hemorrhage ((SAH) 16), unruptu red aneurysm (7), arteriovenous malformation (4), and cavernous malformation (1) . Random forest was the best performing model in 12 studies (20%) f ollowed 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 predi ction 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 operato r 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 f or 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. ML performs favorably for clinical outcome prediction in cerebrovascular and endova scular neurosurgery."
NETL
NSTL