Osteoporosis prediction: developing multivariate linear regression and logistic regression models based on standard biochemistry profile

Zihang Weng

doi:10.1117/12.3013209

8 January 2024 Osteoporosis prediction: developing multivariate linear regression and logistic regression models based on standard biochemistry profile

Zihang Weng

Author Affiliations +

Proceedings Volume 12924, Third International Conference on Biological Engineering and Medical Science (ICBioMed2023); 1292440 (2024) https://doi.org/10.1117/12.3013209
Event: 3rd International Conference on Biological Engineering and Medical Science (ICBioMed2023), 2023, ONLINE, United Kingdom

Abstract

Osteoporosis (OP) is a prevalent disease among individuals over the age of 50. The absence of clear symptoms makes it crucial to predict the occurrence of the disease before a fracture takes place for effective treatment. Currently, the primary method for screening and diagnosing OP is through the use of bone mineral density (BMD) testing, which may not be the most effective approach for OP screening. To address this issue, a multivariate logistic regression model was constructed using statistics from the NHANES, the Continuous National Health and Nutrition Examination Survey, from 2017 to 2020 based on physical examination, questionnaire data, and standard biochemical indicators to determine the presence of osteoporosis. Through data cleaning and screening, data gathered from a nationally representative dataset demonstrate that age, BMI, ferritin, phosphorus, folate content, and whether the parents of the interviewee had ever been told by health professional that they have osteoporosis, are strongly linked, especially in females, to the onset of osteoporosis in those over 50. The logistic regression model possesses a 0.839 area under the receiver operating pattern (ROC) curve. This study aims to provide a more effective method for OP screening and to contribute to the understanding and management of the disease.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zihang Weng "Osteoporosis prediction: developing multivariate linear regression and logistic regression models based on standard biochemistry profile", Proc. SPIE 12924, Third International Conference on Biological Engineering and Medical Science (ICBioMed2023), 1292440 (8 January 2024); https://doi.org/10.1117/12.3013209

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available