A linear support vector machine using acoustic non-invasive data achieved an overall accuracy of 79% for 4-class classification and an AUC of 0.93 for the most dislocated hip joint.
Does SVM classification using acoustic data accurately detect Developmental Dysplasia of Hip in simulated models?
SVM classification of acoustic data shows promise for early, non-invasive detection of developmental dysplasia of the hip in simulated models.
Effect estimate: AUC 0.93
Treatment of Developmental Dysplasia of Hip (DDH) becomes less convoluted if it is detected early. In this paper, an acoustic non-invasive data is used for detection of DDH. We investigate early detection of DDH using machine learning technique through support vector machine (SVM) technique. We use data from a proposed method that tested different simplified models of the hip joint. Models were stimulated with band-limited white acoustic noise (10-2500 Hz) and the response of the model was measured. We obtain phase, transfer function and coherence as features for different simulated hip dysplasia levels and for simulated normal cases. Results shows that linear SVM gives an overall accuracy of 79% for 4 class with an area under the curve (AUC) of.93 for the most dislocated hip joint in receiver operating characteristic (ROC) curve.
Alam et al. (Mon,) conducted a other in Developmental Dysplasia of Hip (DDH). Support vector machine (SVM) classification was evaluated on Overall accuracy for 4 class and AUC for the most dislocated hip joint (AUC 0.93). A linear support vector machine using acoustic non-invasive data achieved an overall accuracy of 79% for 4-class classification and an AUC of 0.93 for the most dislocated hip joint.