Machine learning algorithms for predicting scapular kinematics. (March 2019)

• Record Type: Journal Article
• Authors: Nicholson, Kristen F.; Richardson, R. Tyler; van Roden, Elizabeth A. Rapp; Quinton, R. Garry; Anzilotti, Kert F.; Richards, James G.
• Is Part Of: Medical engineering & physics. Volume 65(2019)
• Page Start: 39
• Page End: 45
• Publication Date: 2019-03
• Subjects: Shoulder mechanics -- Machine learning -- Neural networks -- Biomechanics; ST scapulothoracic -- TS trigonum spinae -- IA inferior angle -- AP acromion process; Biomedical engineering -- Periodicals; Biomedical Engineering -- Periodicals; Physics -- Periodicals; Génie biomédical -- Périodiques; Biomedical engineering; Electronic journals; Periodicals; 610.28
• DOI: 10.1016/j.medengphy.2019.01.005
• Languages: English
• ISSNs: 1350-4533

Abstract

Highlights: Machine learning algorithms were used to determine scapula orientation. Individualized neural networks were able to predict 3D scapula orientation. Estimated orientations compared favorably to fluoroscopy-determined orientations. On average, the estimated orientation was within 10° of the gold standard. Abstract: The goal of this study was to develop and validate a non-invasive approach to estimate scapular kinematics in individual patients. We hypothesized that machine learning algorithms could be developed using motion capture data to accurately estimate dynamic scapula orientation based on measured humeral orientations and acromion process positions. The accuracy of the algorithms was evaluated against a gold standard of biplane fluoroscopy using a 2D to 3D fluoroscopy/model matching process. Individualized neural networks were developed for nine healthy adult shoulders. These models were used to predict scapulothoracic kinematics, and the predicted kinematics were compared to kinematics obtained using biplane fluoroscopy to determine the accuracy of the machine learning algorithms. Results showed correlations between predicted kinematics and validation kinematics. Estimated kinematics were within 10 of validation kinematics. We concluded that individualized machine learning algorithms show promise for providing accurate, non-invasive measurements of scapulothoracic kinematics.