Purpose
To evaluate the association between lumbar lordosis and age using an AI-based automated measurement model applied to a large dataset of standing lateral spinal radiographs.
Materials and Methods
This retrospective study analyzed 904 high-quality radiographs selected from 2,397 images acquired between 2019 and 2021. Lumbar lordosis was defined as the angle between the superior endplates of L1 and S1 and automatically measured using a validated deep learning model. Subjects were categorized into nine age groups. One-way ANOVA compared lumbar lordosis across age groups, and Pearson correlation assessed the relationship between age and lumbar lordosis.
Results
Lumbar lordosis ranged from 0° to 84° (mean 45.9°±13.4°). The highest mean value was in the 10–19-year group (52.1°), and the lowest in the ≥80-year group (39.6°). Minimum values decreased to 0° in individuals aged ≥60 years. No significant differences were found across age groups (p=0.561). A weak but significant negative correlation was observed between age and lumbar lordosis (r=–0.247, p<0.0001).
Conclusions
AI-based automated measurement enabled efficient large-scale analysis and revealed a wide distribution of lumbar lordosis with a gradual age-related decline. These findings highlight the value of AI in spinal alignment assessment.

Purpose
To develop and validate a deep learning–based artificial intelligence (AI) model for automated measurement of lumbar lordosis (LL) angles from whole spine lateral radiographs.
Materials and Methods
A total of 888 lateral spine X-rays (2019–2021) were retrospectively collected and annotated with four anatomical keypoints (L1 and S1 vertebral landmarks). An AI model using Detectron2 with a Keypoint R-CNN and ResNeXt-101 backbone was trained with data augmentation. Performance was evaluated on 50 test images, comparing AI results to manual annotations by two orthopedic surgeons using intraclass correlation coefficient (ICC), Pearson’s correlation, and Bland–Altman analysis.
Results
The model achieved an average precision of 71.63 for bounding boxes and 86.61 for keypoints. ICCs between AI and human raters ranged from 0.918 to 0.962. Pearson correlation coefficients were r=0.849 and r=0.903. Bland–Altman analysis showed minor underestimation biases (–3.42° and –4.28°) with acceptable agreement.
Conclusions
The AI model showed excellent agreement with expert measurements and high reliability in LL angle assessment. Despite a slight underestimation, it offers a scalable, consistent tool for clinical use. Further studies should evaluate generalizability and interpretability in broader settings.

Citations

• Deep Learning–based AI Analysis of the Correlation Between Lumbar Lordosis and Age
  Soo-Bin Lee, Ja-Yeong Yoon, Dong-Sik Chae, Sang-Bum Kim, Young-Seo Park, Kyung-Yil Kang, Min-Kyu Lee
  Journal of Advanced Spine Surgery.2025; 15(2): 78.     CrossRef
• Efficacy of Biportal Endoscopic Decompression for Lumbar Spinal Stenosis: A Meta-Analysis With Single-Arm Analysis and Comparative Analysis With Microscopic Decompression and Uniportal Endoscopic Decompression
  Shuangwen Lv, Haiwen Lv, Yupeng He, Xiansheng Xia
  Operative Neurosurgery.2024; 27(2): 158.     CrossRef