Clinical Scorecard: Creation and external validation of a machine learning model utilizing composite biomarkers for assessing sarcopenia risk in individuals with cardiovascular disease

At a Glance

Key Highlights

• Sarcopenia affects up to one-third of patients with cardiovascular disease.
• TyG-BMI showed the highest discriminative ability for sarcopenia (AUC = 0.938).
• The CatBoost model demonstrated good discrimination across multiple cohorts.
• The Cardiovascular Disease–Sarcopenia Risk Score (CVD-SRS) provides consistent risk stratification.
• Early recognition of sarcopenia is crucial for prognostic assessment and risk management.

Guideline-Based Recommendations

Diagnosis

• Current diagnosis relies on frameworks by the Asian Working Group for Sarcopenia (AWGS) and the European Working Group on Sarcopenia in Older People (EWGSOP).

Management

• Timely initiation of preventive interventions is essential for patients with CVD and sarcopenia.

Monitoring & Follow-up

• Regular assessment of muscle strength, mass, and physical performance is recommended.

Risks

• Sarcopenia in CVD is associated with increased risks of major adverse cardiovascular events and mortality.

Patient & Prescribing Data

Individuals with cardiovascular disease at risk for sarcopenia.

Composite metabolic biomarkers, particularly TyG-BMI, are useful for early risk assessment.

Clinical Best Practices

• Utilize machine learning models for integrating multidimensional biomarker information.
• Implement practical tools for early risk stratification in clinical settings.

Related Resources & Content

• Cardiovascular Disease and Sarcopenia Study