Purpose
Metabolic syndrome is a multifactorial condition associated with increased risks of cardiovascular disease and type 2 diabetes. This study aims to evaluate whether combining AI-based abdominal CT metrics with traditional InBody analysis enhances the prediction of metabolic syndrome.
Materials and Methods
This retrospective study included 977 adults who underwent both abdominal CT and InBody assessments. AI-derived measurements were obtained using a deep-learning V-Net model trained to segment seven body tissue types. InBody measurements included BMI, body fat percentage, fat mass, and waist-hip ratio. Metabolic syndrome was defined by NCEP-ATP III criteria. Logistic regression and ROC analyses were used to evaluate the predictive performance of AI-derived metrics, InBody metrics, and their combination.
Results
Body fat percentage and waist-hip ratio from InBody analysis were strong predictors of metabolic syndrome (AUC 0.82). AI-derived visceral fat was also significantly associated with metabolic syndrome (AUC 0.61). Combining both AI and InBody metrics slightly improved predictive performance (AUC 0.83), indicating a complementary diagnostic value.
Conclusions
While InBody metrics remain superior in predicting metabolic syndrome due to their close association with metabolic processes, AI-derived body composition metrics, particularly visceral fat, offer structural insights. The modest improvement in prediction when combined suggests the potential of an integrated diagnostic model in clinical practice.

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

• 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