首页|Guangzhou University of Chinese Medicine Reports Findings in Osteoporosis (Machi ne-learning models for diagnosis of rotator cuff tears in osteoporosis patients based on anteroposterior X-rays of the shoulder joint)
Guangzhou University of Chinese Medicine Reports Findings in Osteoporosis (Machi ne-learning models for diagnosis of rotator cuff tears in osteoporosis patients based on anteroposterior X-rays of the shoulder joint)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Musculoskeletal Diseas es and Conditions - Osteoporosis is the subject of a report. According to news r eporting from Shenzhen, People's Republic of China, by NewsRx journalists, resea rch stated, "This study aims to diagnose Rotator Cuff Tears (RCT) and classify t he severity of RCT in patients with Osteoporosis (OP) through the analysis of sh oulder joint anteroposterior (AP) X-ray-based localized proximal humeral bone mi neral density (BMD) measurements and clinical information based on machine learn ing (ML) models. A retrospective cohort of 89 patients was analyzed, including 6 3 with both OP and RCT (OPRCT) and 26 with OP only." The news correspondents obtained a quote from the research from the Guangzhou Un iversity of Chinese Medicine, "The study analyzed a series of shoulder radiograp hs from April 2021 to April 2023. Grayscale values were measured after plotting ROIs based on AP X-rays of shoulder joint. Five kinds of ML models were develope d and compared based on their performance in predicting the occurrence and sever ity of RCT from ROIs' greyscale values and clinical information (age, gender, ad vantage side, lumbar BMD, and acromion morphology (AM)). Further analysis using SHAP values illustrated the significant impact of selected features on model pre dictions. R1-6 had a positive correlation with BMD respectively. The nine variab les, including greyscale R1-6, age, BMD, and AM, were used in the prediction mod els. The RF model was determined to be superior in effectively diagnosing RCT in OP patients, with high AUC scores of 0.998, 0.889, and 0.95 in the training, va lidation, and testing sets, respectively. SHAP values revealed that the most inf luential factors on the diagnostic outcomes were the grayscale values of all can cellous bones in ROIs. A column-line graph prediction model based on nine variab les was constructed, and DCA curves indicated that RCT prediction in OP patients was favored based on this model. Furthermore, the RF model was also the most su perior in predicting the types of RCT within the OPRCT group, with an accuracy o f 86.364% and 73.684% in the training and test sets, respectively. SHAP values indicated that the most significant factor affecting the predictive outcomes was the AM, followed by the grayscale values of the grea ter tubercle, among others. ML models, particularly the RF algorithm, show signi ficant promise in diagnosing RCT occurrence and severity in OP patients using co nventional shoulder X-rays based on the nine variables."
ShenzhenPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesHealth and MedicineMachine LearningMetab olic Bone Diseases and ConditionsMusculoskeletal Diseases and ConditionsOste oporosis
NETL
NSTL
