Artificial Intelligence Applications in Osteoporosis: A Comprehensive Review of Screening, Diagnosis, and Risk Prediction
| Author | Alireza Keshtkar | en |
| Author | Alireza Karimi | en |
| Author | Farnaz Atighi | en |
| Author | Parsa Yazdanpanahi | en |
| Author | Arzhang Naseri | en |
| Author | Amirhossein Khajepour | en |
| Author | Mohammad Salehi | en |
| Author | Yaser Sarikhani | en |
| Author | Mohammad Hossein Dabbaghmanesh | en |
| Orcid | Alireza Keshtkar [0000-0003-3590-5267] | en |
| Orcid | Alireza Karimi [0009-0008-5154-5074] | en |
| Orcid | Farnaz Atighi [0009-0005-2353-7139] | en |
| Orcid | Parsa Yazdanpanahi [0009-0004-3969-2830] | en |
| Orcid | Arzhang Naseri [0000-0002-4095-2351] | en |
| Orcid | Yaser Sarikhani [0000-0002-0615-9210] | en |
| Orcid | Mohammad Hossein Dabbaghmanesh [0000-0002-4877-0376] | en |
| Issued Date | 2025-12-31 | en |
| Abstract | Context: Osteoporosis is a widespread health concern, with its prevalence increasing as people age. The most serious consequence of osteoporosis is fractures, which often lead to disability and a reduced quality of life. Artificial intelligence (AI) is increasingly used in medicine for screening, diagnosis, classification, and management tasks. In osteoporosis management, from early screening and risk assessment to diagnosis and treatment planning, AI has demonstrated a remarkable ability to improve the accuracy (Acc) and efficiency of patient care. Evidence Acquisition: We conducted a comprehensive search of English-language articles published on AI applications for osteoporosis management, using the PubMed, Scopus, and Google Scholar databases. Results: The latest AI applications in managing osteoporosis can be categorized into three main areas: Screening and diagnosis of osteoporosis, bone mineral density (BMD) prediction, and prediction and diagnosis of osteoporotic fractures. Given the limited accessibility of dual-energy X-ray absorptiometry (DXA) and BMD measurements, recent research has increasingly relied on clinical records and alternative imaging, such as computed tomography (CT) scans and X-rays. Deep learning (DL) models, especially convolutional neural networks (CNNs), excel in analyzing imaging data and have demonstrated superior performance compared to conventional assessments. Conclusions: The AI-driven models show great promise in improving risk stratification, osteoporosis diagnosis, and clinical workflow efficiency. However, methodological variability and limited generalizability underscore the need for standardized validation and reporting to ensure reliable clinical implementation. | en |
| DOI | https://doi.org/10.5812/semj-162399 | en |
| Keyword | Artificial Intelligence | en |
| Keyword | Machine Learning | en |
| Keyword | Deep Learning | en |
| Keyword | Computational Intelligence | en |
| Keyword | Osteoporosis | en |
| Keyword | Bone Mineral Density | en |
| Keyword | Osteoporotic Fracture | en |
| Keyword | Diagnosis | en |
| Keyword | Risk Assessment | en |
| Publisher | Brieflands | en |
| Title | Artificial Intelligence Applications in Osteoporosis: A Comprehensive Review of Screening, Diagnosis, and Risk Prediction | en |
| Type | Review Article | en |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- semj-In_Press-In_Press-162399-publish-pdf.pdf
- Size:
- 609.77 KB
- Format:
- Adobe Portable Document Format
- Description:
- Article/s PDF