Prediction of Osteoporosis Risk Level Using Machine Learning Techniques

Authors

  •   Rohan Vanmali Student, Department of Information Technology, St. Francis Institute of Technology, Sardar Vallabhbhai Patel Road, Near Bhagwati Hospital, Mount Poinsur, Borivali West - 400 103, Mumbai, Maharashtra
  •   Tejas Kashid Student, Department of Information Technology, Assistant Professor, St. Francis Institute of Technology, Sardar Vallabhbhai Patel Road, Near Bhagwati Hospital, Mount Poinsur, Borivali West - 400 103, Mumbai, Maharashtra
  •   William Rodrigues Student, Department of Information Technology, St. Francis Institute of Technology, Sardar Vallabhbhai Patel Road, Near Bhagwati Hospital, Mount Poinsur, Borivali West - 400 103, Mumbai, Maharashtra
  •   Asher Rodrigues Student, St. Francis Institute of Technology, Sardar Vallabhbhai Patel Road, Near Bhagwati Hospital, Mount Poinsur, Borivali West - 400 103, Mumbai, Maharashtra
  •   Sonali Suryawanshi Assistant Professor, St. Francis Institute of Technology, Sardar Vallabhbhai Patel Road, Near Bhagwati Hospital, Mount Poinsur, Borivali West - 400 103, Mumbai, Maharashtra

DOI:

https://doi.org/10.17010/ijcs/2023/v8/i3/172863

Keywords:

Bone Mass Density

, Fracture, Osteoporosis.

Paper Submission Date

, April 27, 2023, Paper sent back for Revision, May 7, Paper Acceptance Date, May 10, Paper Published Online, June 5, 2023

Abstract

Low bone density and bone tissue degeneration are prominent symptoms of osteoporosis, which increases the risk of fractures. To avoid long term consequences and enhance patient outcomes, osteoporosis fractures must be identified early and prevented. In this research, we offer a Machine Learning based method for calculating the risk of osteoporosis fractures based on a variety of inputs, including age, gender, weight, height, smoking, alcohol use, diabetes, arthritis, parental fractures, and T-score. We use the Logistic Regression, K-Nearest Neighbour, and Support Vector Machine Machine Learning models to predict the risk level of osteoporosis fractures, which may be high risk, medium risk, or low risk. We evaluate the performance of these models based on a number of factors, such as accuracy, precision, recall, and F1-score. The estimated risk level of osteoporosis fractures is stored in a database together with other input data for future use.

Downloads

Download data is not yet available.

Downloads

Published

2023-07-06

How to Cite

Vanmali, R., Kashid, T., Rodrigues, W., Rodrigues, A., & Suryawanshi, S. (2023). Prediction of Osteoporosis Risk Level Using Machine Learning Techniques. Indian Journal of Computer Science, 8(3), 17–24. https://doi.org/10.17010/ijcs/2023/v8/i3/172863

Issue

Volume 8, Issue 3, May-June 2023

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

References

W. Moudani, A. Shahin, F. Chakik, and D. Rajab, “Intelligent Predictive Osteoporosis System,†Int. J. Comput. Appl., vol. 32, no. 5, pp. 28–37, Oct. 2011, doi: 10.5120/3901-5468.

J.A. Kanis, C. Cooper, R. Rizzoli, J. –Y. Reginster, “European guidance for the diagnosis and management of Osteoporosis in postmenopausal women,†Osteoporosis Int., vol. 30, pp. 399–428, Oct. 2015, doi: 10.1007/s00198-018-4704-5.

Q. Wu, F. Nasoz, J. Jung, B. Bhattarai, M. V. Han, “Machine Learning approaches for fracture risk assessment: A comparative analysis of Genomic and Phenotypic data in 5130 older men,†Calcif Tissue Int., vol. 107, pp. 353–361, Oct. 2020, doi: 10.1155/2013/850735.

H.-W. Chang, Y.-H. Chiu, H.-Y. Kao, C.-H., Yang, and W.- H. Ho, “Comparison of classification algorithms with wrapper-based feature selection for predicting Osteoporosis outcome based on genetic factors in a Taiwanese women population,†Int. J. Endocrinology, vol. 1–8, Jan. 2013, doi: 10.1155/2013/850735.

N. Guannoni., R. Sassi., W. Bedhiafi, and M. Elloumi., “A Comparison Between Classification Algorithms for Postmenopausal Osteoporosis Prediction in Tunisian Population,†In: Renda, M., Bursa, M., Holzinger, A., Khuri, S. (eds) Inf. Tech. Bio- Medical Inform. ITBAM 2016. Lecture Notes in Comput. Sci. (), vol 9832, pp. 234–248, Aug. 2016, Springer, Cham, doi: 10.1007/978-3-319-43949-5_19.

M. Saranya and K. Sarojimi, “An improved and optimal prediction of bone disease based in risk factors,†Int. J. Comput. Sci. Inf. Technol., vol. 7, no. 2 , pp. 820–823, 2016. [Online]. Available: https://ijcsit.com/docs/Volume%207/vol7issue2/ijcsit2016070283.pdf

Z. Wang., J. Fu,. R. Yan., J. S. Park, and H. G. Kim, “A comparative analysis of Machine Learning techniques for early detection of Osteoporosis,†Int. J. Pure Appl. Math., vol. 119, no. 18, pp. 97–114, 2018.[Online]. Available: https://acadpubl.eu/hub/2018-119-18/1/9.pdf

T. Agarwal, H. Sharma, C. Latha, and S. Gupta, “A review of role of machine learning models in coronary heart disease detection accuracy,†Indian J. of Comput. Sci., vol. 7, no. 1, pp. 36–44, 2022. doi:10.17010/ijcs/2022/v7/i1/168955.