Related Experiment Video
Updated: Jun 21, 2026

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Lower-Leg muscle index Identifies High-Risk Peripheral artery disease Patients: Mortality prediction via Machine
Wenxin Zhao1, Yifan Cao1, Yaming Guo1
1Department of Vascular Surgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences& Peking Union Medical College. Beijing 100000, China; Graduate School of Chinese Academy of Medical Sciences & Peking Union Medical College. Beijing 100000, China.
Lower-leg muscle index (LMI) effectively predicts long-term mortality in peripheral artery disease (PAD) patients after revascularization. Machine learning models incorporating LMI demonstrate superior risk stratification compared to abdominal indices.
Area of Science:
- Cardiovascular Disease Research
- Medical Imaging and Diagnostics
- Biomarkers and Prognostics
Background:
- Sarcopenia, or muscle loss, is a known risk factor for adverse outcomes in cardiovascular diseases.
- Previous research on peripheral artery disease (PAD) has primarily focused on lumbar muscle indices, neglecting site-specific lower-limb muscle loss.
- Identifying reliable predictors of mortality in PAD patients undergoing revascularization is crucial for improving patient management.
Purpose of the Study:
- To evaluate the prognostic value of the lower-leg muscle index (LMI) in predicting long-term mortality in PAD patients.
- To compare the predictive performance of LMI against traditional abdominal muscle indices.
- To assess the utility of machine learning (ML) models incorporating LMI for risk stratification in PAD.
Main Methods:
- Retrospective analysis of 208 PAD patients undergoing lower-extremity revascularization.
- Collection of preoperative clinical data and CT angiography-derived muscle indices, including LMI.
- Application of feature selection techniques (LASSO, mRMR, random forest, gradient boosting) and multivariate Cox regression.
- Validation of eight ML models using C-index, AUC, calibration, and decision curve analysis.
Main Results:
- During a mean follow-up of 29.5 months, 44 deaths occurred; non-survivors exhibited greater comorbidity, inflammation, and lower-limb muscle loss.
- LMI demonstrated superior mortality discrimination (AUC 0.71) compared to abdominal indices.
- Higher LMI was significantly associated with reduced mortality risk (HR=0.94, p=0.004).
- Gradient boosting ML models achieved high predictive performance (e.g., 5-year C-index of 0.823).
Conclusions:
- The lower-leg muscle index (LMI) is a superior and accessible predictor of long-term mortality in PAD patients.
- ML models integrating LMI offer enhanced, individualized risk stratification for PAD patients post-revascularization.
- These findings support the use of LMI in clinical practice to guide management strategies for PAD.
Related Concept Videos
Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
Assessing Blood pressure in the Leg
Preparation:
Pulse Assessment Sites
Peripheral Artery Disease I: Introduction
Peripheral Artery Disease IV: Nursing Management
