PREDICTION OF NEW OSTEOPOROSIS CASES USING TIME SERIES AND ARTIFICIAL NEURAL NETWORKS: A COMPARATIVE STUDY

Afrah  Al-Bossly; Abdelgalal  O. I. Abaker; Nuzaiha  Mohamed; Zahra  Idreis Mahamoud; M.  Aripov; Azhari  A. Elhag

Afrah Al-Bossly Department of Mathematics, College of Science and Humanities in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al Kharj, 11942,Saudi Arabia
Abdelgalal O. I. Abaker Applied College, Khamis Mushait, King Khalid University, Abha, Saudi Arabia
Nuzaiha Mohamed Department of Public Health, College of Public Health and Health Informatics, University of Hail, Ha’il, 81451,Saudi Arabia
Zahra Idreis Mahamoud Department of Mathematics, College of Science, Qassim University, Buraydah, 51452, Saudi Arabia
M. Aripov Department of Applied Mathematics and Computer Analysis, Faculty of Mathematics, NUU, Uzbekistan
Azhari A. Elhag Department of Mathematics and Statistics, College of Science, Taif University, Taif 21944, Saudi Arabia

Abstract

Osteoporosis stands as a significant public health concern characterized by diminished bone density and heightened susceptibility to fractures, affecting over 200 million individuals globally. Recent statistics from the International Osteoporosis Foundation indicate that approximately 33% of women aged 50 and above and 20% of males are at risk of experiencing osteoporotic fractures during their lifetime. This study aims to juxtapose the predictive efficacy of time series models and artificial neural networks to enhance the early detection of osteoporosis cases. Methodologically, the research involves preprocessing and standardization of datasets to optimize their suitability for machine learning applications. An Artificial Neural Network (ANN) tailored for osteoporosis prediction demonstrates superior predictive performance when compared to conventional approaches such as the autoregressive integrated moving average (ARIMA) model. The enhanced predictive capabilities are substantiated through rigorous statistical analyses evaluating the model's accuracy. Osteoporosis data spanning from 1965 to 2023 are sourced from the official website of the Australian Government Institute of Health and Welfare.