International Journal of Electrical and Computer Engineering
Vol 5, No 1: February 2015

Feature Selection of the Combination of Porous Trabecular with Anthropometric Features for Osteoporosis Screening

Enny Itje Sela (Universitas Gadjah Mada)
Sri Hartati (Universitas Gadjah Mada)
Agus Harjoko (Universitas Gadjah Mada)
Retantyo Wardoyo (Universitas Gadjah Mada)
Munakhir Mudjosemedi (Universitas Gadjah Mada)



Article Info

Publish Date
01 Feb 2015

Abstract

This study aims to select the important features from the combination of porous trabecular pattern with anthropometric features for osteoporosis screening. The study sample has their bone mineral density (BMD) measured at the proximal femur/lumbar spine using dual-energy X-ray absorptiometry (DXA). Morphological porous features such as porosity, the size of porous, and the orientation of porous are obtained from each dental radiograph using digital image processing. The anthropometric features considered are age, height, weight, and body mass index (BMI). Decision tree (J.48 method) is used to evaluate the accuracy of morphological porous and anthropometric features for selection data. The study shows that the most important feature is age and the considered features for osteoporosis screening are porosity, vertical pore, and oblique pore. The decision tree has considerably high accuracy, sensitivity, and specificity.

Copyrights © 2015






Journal Info

Abbrev

IJECE

Publisher

Subject

Computer Science & IT Electrical & Electronics Engineering

Description

International Journal of Electrical and Computer Engineering (IJECE, ISSN: 2088-8708, a SCOPUS indexed Journal, SNIP: 1.001; SJR: 0.296; CiteScore: 0.99; SJR & CiteScore Q2 on both of the Electrical & Electronics Engineering, and Computer Science) is the official publication of the Institute of ...