An AI Approach to Diagnosis of Fragility Spinal Fractures in the Elderly Using Pose-Detection Models

DOI

10.2991/978-94-6463-878-3_9How to use a DOI?

Keywords

AI Diagnosis for Vertebral Compression Fractures; Human Body Structure Diagnosis; Pose Estimation for Healthcare; Spinal Alignment

Abstract

Osteoporotic vertebral compression fractures (VCF) are very common spinal fragility fractures affecting the elderly, with an incidence reaching 700,000 elderly per year, affecting up to 25% of individuals over 70 and 50% over 80 years old. These symptoms typically appear in postmenopausal women and men after their peak bone mass, often due to osteoporosis, where bone quantity decreases as a result of thinning of bone mineral density in the lumbar spine. VCFs can lead to impaired lung function, causing a decrease in forced expiratory volume by up to 9%, and increasing the risk of death due to pulmonary dysfunction. VCF diagnosis can be performed using lateral radiography/X-rays, MRI, or bone scans to assess the severity of the fracture. However, the lengthy and costly VCF diagnosis demands an AI-based approach for VCF diagnosis. This study utilizes pose-detection models, an AI method in computer vision, to determine landmarks on 3D human body structures. Improving existing pose-detection models by adding detailed key points to the spinal structure to suit VCF’s diagnosis process. Study progress collecting pose photos of the elderly, reconstructing the spine, and calculating the percentage of deviation from the front, side, and back views of VCF patients in 3D perspective. Results show the BlazePose model successfully points to landmark poses coordinates within maximum mAP (100%). Subject of VCF diagnosis with 10 10-degree inclination of spinal alignment. This study presents an advanced method for utilizing AI as a non-invasive radiography tool for diagnosing the human body structure.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Putri Alit Widyastuti Santiary
AU  - I Ketut Swardika
AU  - Dewa Ayu Indah Cahya Dewi
AU  - I Gusti Agung Made Yoga Mahaputra
PY  - 2025
DA  - 2025/10/31
TI  - An AI Approach to Diagnosis of Fragility Spinal Fractures in the Elderly Using Pose-Detection Models
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 66
EP  - 73
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_9
DO  - 10.2991/978-94-6463-878-3_9
ID  - Santiary2025
ER  -