International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Design Phase of the Osteoporosis Prediction System |
|---|---|
| ABSTRACT | Osteoporosis is a long-term ailment of the bones that develops due to the reduction in bone mineral density (BMD) and deterioration of bone tissues that substantially predetermine the development of fractures. They need to be diagnosed earlier to prevent severe health problems, which can be disabling and deteriorate the quality of life. However, traditional methods of diagnosis, such as Dual-Energy X-ray Absorptiometry (DEXA), are quite costly and require the presence of a clinic, and can only be used after symptoms have appeared. Machine Learning (ML) offers an affordable platform that is viable and can be utilised to anticipate early osteoporosis using clinical and lifestyle measures that are readily available. Some of the factors whose importance is quite strong in defining the bone strength include age, gender, hormonal status, family history, nutritional intake, physical activity, and comorbid health conditions. With the help of such variables, it is possible to automatically detect the risk of osteoporosis via the application of ML models without using the special diagnostic tools necessary. The prediction model that is proposed in this paper is based on machine learning, and the data pre-processing is complemented by Natural Language Processing (NLP), which would enable classifying people as having or not having osteoporosis. The system is expected to increase the rate of prediction through the good selection of features and the assessment of the model. The proposed solution stands a high chance of screening the population in bulk and will also assist in screening of the population earlier on importantly, in the resource-constrained facility. |
| AUTHOR | SHITAL BHADE, SUPRIYA KORE, MANASI SHINDE, RENUKA SONAWANE, PROF. PAYAL NIKAM |
| VOLUME | 176 |
| DOI | 10.15680/IJIRCCE.2025.1311031 |
| pdf/31_Design Phase of the Osteoporosis Prediction System.pdf | |
| KEYWORDS |
