Standard physical examination indicators predict sarcopenia risk with high accuracy in a health checkup population.

PurposeSarcopenia is a progressive disorder of skeletal muscle linked to numerous adverse health outcomes. This study aimed to create and validate a nomogram model to predict sarcopenia risk in a large cohort undergoing routine health exams.MethodsThis retrospective study analyzed data derived from standard physical examination indicators collected in a health checkup population. Participants were randomly divided into a training set comprising 70% and a testing set comprising 30%. In the training cohort, key predictors were determined using LASSO regression and subsequent multivariable logistic regression. A predictive nomogram was subsequently constructed. Model performance was assessed through ROC curves, calibration analysis, and decision curve analysis (DCA).ResultsThe analysis included 3,277 participants. The final nomogram included eight predictors: sex, calf circumference, body mass index (BMI), employment status, total bilirubin, hemoglobin, total cholesterol and creatinine. A web-based dynamic nomogram was created using this model and is available at https://luokang.shinyapps.io/dynnomapp/. The model exhibited strong discriminative performance, achieving an AUC of 0.909 in the training set and 0.891 in the testing set, demonstrating reliable predictive capability across datasets. The calibration curves indicated a strong correlation between the predicted probabilities and the actual outcomes. Furthermore, decision curve analysis supported the potential clinical utility of the nomogram.ConclusionWe created and validated a sarcopenia risk prediction model using routinely collected health examination data and transformed it into an accessible online nomogram. The model demonstrates robust predictive capabilities and significant clinical utility, enabling early detection of high-risk sarcopenia cases in health checkup populations.