Abstract
2024 OCT 09 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Musculoskeletal Diseases and Cond itions - Spinal Stenosis is the subject of a report. According to news reporting originating from Shaanxi, People's Republic of China, by NewsRx correspondents, research stated, "The objective of this study was to develop and validate machi ne learning (ML) algorithms to predict the 30-day and 6-month risk of deteriorat ing functional status following surgical treatment for thoracic spinal stenosis (TSS). We aimed to provide surgeons with tools to identify patients with TSS who have a higher risk of postoperative functional decline." Our news editors obtained a quote from the research from Xi'an Jiaotong Universi ty, "The records of 327 patients with TSS who completed both follow-up visits we re analyzed. Our primary endpoint was the dichotomized change in the perioperati ve Japanese Orthopedic Association (JOA) score, categorized based on whether it deteriorated or not. The models were developed using Naive Bays, LightGBM, XGBoo st, logistic regression, and random forest classification models. The model perf ormance was assessed by accuracy and the c-statistic. ML algorithms were trained , optimized, and tested. The best-performing algorithms for predicting functiona l decline at 30 days and 6 months after TSS surgery were XGBoost (accuracy= 88.17 %, c-statistic=0.83) and Naive Bays (accuracy=86.03%, c-statistic=0.80). Both algorithms presented good calibration and discrimination in our testing data. We identified several significant predictors, including po or quality of intraoperative SSEP/MEP baseline, poor quality of preoperative SSE P, duration of symptoms, operated level, and motor dysfunction of the lower extr emity. The best-performing algorithms for predicting functional decline at 30 da ys and 6 months after TSS surgery were XGBoost (accuracy= 88.17%, c- statistic=0.83) and Naive Bays (accuracy=86.03%, c-statistic=0.80). Both algorithms presented good calibration and discrimination in our testing da ta."
NETL
NSTL