A robust multi-utility neural network technique integrated with discriminators for bone health decisioning to facilitate clinical-driven processes

作     者：Ramaraj, Kottaimalai Amiya, Gautam Rajasekaran, Murugan Pallikonda Govindaraj, Vishnuvarthanan Vasudevan, Muneeswaran Thirumurugan, M. Zhang, Yu-Dong Abdullah, S. Sheik Thiyagarajan, Arunprasath 

作者机构：Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Biomedical Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Consultant Orthopaedic Surgeon MGR Medical University Tamilnadu Chennai India School of Informatics University of Leicester LeicesterLE1 7RH United Kingdom 

出 版 物：《Research on Biomedical Engineering》 (Res. Biomed. Eng.)

年 卷 期：2023年第39卷第1期

页      面：139-157页

核心收录：

基　　金：The authors thank Dr. R.Sayee Venkatesh  M.D.(General Medicine)  D.M.(Cardio)  Chennai  Tamilnadu  India  for supporting the research. Also  the authors thank the International Research Centre of Kalasalingam Academy of Research and Education  Tamil Nadu  India  for permitting to use the computational facilities available in the Biomedical Research and Diagnostic Techniques Development Centre. This research was supported by the Department of Science and Technology  New Delhi under the Biomedical Device and Technology Development Scheme (BDTD) of Technology Development Programme (TDP). (Ref. No. DST/TDP/BDTD/28/2021(G)).The authors thank Dr. R.Sayee Venkatesh  M.D.(General Medicine)  D.M.(Cardio)  Chennai  Tamilnadu  India  for supporting the research. Also  the authors thank the International Research Centre of Kalasalingam Academy of Research and Education  Tamil Nadu  India  for permitting to use the computational facilities available in the Biomedical Research and Diagnostic Techniques Development Centre. This research was supported by the Department of Science and Technology  New Delhi under the Biomedical Device and Technology Development Scheme (BDTD) of Technology Development Programme (TDP). (Ref. No. DST/TDP/BDTD/28/2021(G)) 

主　　题：Deterioration 

摘      要：Purpose: Osteoporosis (OP) is a malformation of the bones caused by the loss of bone mass and its mineral density, and also deterioration in bone quality or structures, causing an increased risk of fractures. Apart from bone cracks, damage to hip, spine vertebrae and wrist are the most prevalent. Method: This work proposes a hybrid strategy to categorise the normal and abnormal bone mineral density (BMD) values obtained from 140 patients. Owing to the smaller sample and the large number of variables in a high-dimensional data classification issue, classical linear discriminant analysis (LDA) performs poorly, resulting in the instability and singularity of the sample covariance matrix. To suppress this, a normalised radial basis function neural network (NRBFNN) coupled with a modified version of LDA (MLDA) is being proposed through this paper for BMD evaluations. In this study, we propose a novel modified version of LDA (MLDA) based on a robust estimator for high-dimensional covariance matrices, and has been proved to be asymptotically highly reliable than the sample covariance matrix. Results: Instead of employing un-normalised RBF, NRBFNN is used for BMD classification. The suggested hybrid algorithm MLDA-NRBFNN achieved a classification accuracy of 97.5% on comparing with ANN, PAC-ANN and RBFN. Conclusion: With the intervention of the proposed method, the doctors could tend to have a precursor to assay the patients with varied bone ailments and to understand the recovery impact of knee replacement as well. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering.