Classification of osteoporosis by artificial neural network based on monarch butterfly optimisation algorithm

• Published in: Healthcare technology letters Vol. 5; no. 2; pp. 70 - 75
• Main Authors: Devikanniga, D, Joshua Samuel Raj, R
• Format: Journal Article
• Language: English
• Published: England The Institution of Engineering and Technology 01.04.2018; John Wiley & Sons, Inc; Wiley
• Subjects: 10-fold cross-validation method; Algorithms; Bias; BMD values; bone; bone mineral density; Butterflies & moths; clinical methods; diseases; femoral neck dataset; Heuristic; hybrid classifier model; life threatening disease; lumbar spine dataset; medical diagnostic computing; menopause; mild bone fractures; monarch butterfly optimisation algorithm; monarch butterfly optimisation-based artificial neural network classifier; neural nets; Neural networks; optimisation; orthopaedics; Osteoporosis; osteoporosis classification; osteoporosis diagnosis; osteoporotic patient; patient diagnosis; pattern classification; receiver operating characteristics analysis; sensitivity analysis; skeletal regions; Standard scores; Support vector machines; Wilcoxon signed-rank test; 10-fold cross-validation method; hybrid classifier model; orthopaedics; sensitivity analysis; femoral neck dataset; BMD values; bone mineral density; optimisation; osteoporosis diagnosis; menopause; monarch butterfly optimisation-based artificial neural network classifier; medical diagnostic computing; pattern classification; diseases; bone; life threatening disease; osteoporotic patient; lumbar spine dataset; Wilcoxon signed-rank test; mild bone fractures; monarch butterfly optimisation algorithm; receiver operating characteristics analysis; skeletal regions; clinical methods; neural nets; patient diagnosis; osteoporosis classification
• ISSN: 2053-3713; 2053-3713
• DOI: 10.1049/htl.2017.0059

Osteoporosis is a life threatening disease which commonly affects women mostly after their menopause. It primarily causes mild bone fractures, which on advanced stage leads to the death of an individual. The diagnosis of osteoporosis is done based on bone mineral density (BMD) values obtained through various clinical methods experimented from various skeletal regions. The main objective of the authors’ work is to develop a hybrid classifier model that discriminates the osteoporotic patient from healthy person, based on BMD values. In this Letter, the authors propose the monarch butterfly optimisation-based artificial neural network classifier which helps in earlier diagnosis and prevention of osteoporosis. The experiments were conducted using 10-fold cross-validation method for two datasets lumbar spine and femoral neck. The results were compared with other similar hybrid approaches. The proposed method resulted with the accuracy, specificity and sensitivity of 97.9% ± 0.14, 98.33% ± 0.03 and 95.24% ± 0.08, respectively, for lumbar spine dataset and 99.3% ± 0.16%, 99.2% ± 0.13 and 100, respectively, for femoral neck dataset. Further, its performance is compared using receiver operating characteristics analysis and Wilcoxon signed-rank test. The results proved that the proposed classifier is efficient and it outperformed the other approaches in all the cases.