Study Design
A retrospective diagnostic accuracy study was conducted using internal training and temporal validation cohorts.
Purpose
This study aimed to develop and validate sex-specific diagnostic nomograms for sarcopenia in patients with degenerative lumbar disease (DLD), based on body mass index (BMI), hand-grip strength (HGS), and computed tomography (CT)–derived lumbar muscle indices. Overview of Literature: The Asian Working Group for Sarcopenia (AWGS) 2019 algorithm requires appendicular skeletal muscle mass (ASM) measurement by dual-energy X-ray absorptiometry or bioimpedance analysis together with HGS and a physical performance test. These measurements are not always feasible in spine clinics, although a preoperative lumbar CT is routinely available.
Methods
A training set of 196 patients scheduled for lumbar surgery and a temporal validation set of 150 patients with DLD were analyzed. Sarcopenia was diagnosed according to the AWGS 2019 criteria. Sex-specific multivariable logistic regression was performed using BMI, HGS, psoas muscle index, paraspinal muscle index (PaMI), and gluteal muscle index (GMI), and the resulting models were translated into nomograms. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC), calibration by calibration plots and mean absolute error (MAE), and the optimal cut-off was identified using the Youden index.
Results
The prevalence of sarcopenia was 62.2% (122/196) in the training set and 58.0% (87/150) in the validation set. In the training set, sarcopenic patients had significantly lower BMI (23.7±3.7 vs. 27.0±3.3 kg/m2), HGS (20.3±8.0 vs. 29.2±30.5 kg), PaMI (8.7±5.4 vs. 13.9±8.0), and GMI (26.1±5.7 vs. 30.9±6.2) than non-sarcopenic patients (all p<0.05). On validation, the male nomogram achieved an AUC of 0.958 with an MAE of 0.040, and the female nomogram achieved an AUC of 0.830 with an MAE of 0.021. The Youden index was 0.78 for males and 0.59 for females.
Conclusion
Sex-specific nomograms based on BMI, HGS, and CT-derived lumbar muscle indices provided accurate diagnosis of sarcopenia in patients with DLD without requiring whole-body ASM measurement or a physical performance test, offering a practical screening tool in the spine clinic.

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.