AI-Driven Integration of Muscle Mass and Muscle Function: A Novel Approach to Sarcopenia Risk Assessment and Intervention
试验速览
- 阶段
- 不适用
- 状态
- 进行中（未招募）
- 入组人数
- 120
- 试验地点
- 1
- 主要终点
- Accuracy of AI-Based Sarcopenia Risk Prediction Model
研究概览
简要总结
Sarcopenia, the age-related decline in muscle mass and function, is a major contributor to frailty, disability, and mortality in older adults. Current diagnostic tools assess muscle quantity or function separately and lack predictive biomarkers, limiting early detection and personalized management. This study proposes an AI-driven framework that integrates multimodal physiological, metabolic, and functional data with wearable sensor monitoring to improve sarcopenia risk assessment and guide individualized interventions.
In Phase 1, we will analyze a large retrospective dataset of 3,500 adults to identify early predictors of sarcopenia and develop a machine learning-based risk stratification model. Phase 2 will test a 12-week personalized exercise and nutrition intervention in 120 participants, using real-time sensor data and AI-guided adjustments to optimize outcomes. This integrative approach aims to advance early detection, precision intervention, and long-term muscle health in aging populations.
详细描述
Background:
Sarcopenia, defined by the progressive loss of skeletal muscle mass and function, poses significant risks for falls, disability, metabolic dysfunction, and mortality in older adults. Current clinical diagnostics rely on static measures of muscle strength or mass, often missing early-stage or subclinical decline. Moreover, conventional interventions, such as resistance training and increased protein intake, show high inter-individual variability in outcomes due to factors like baseline muscle phenotype, metabolic status, genetics, and gut microbiome composition. Emerging technologies, including wearable sensors, high-throughput metabolic profiling, and AI/ML approaches, provide an opportunity to create predictive, individualized frameworks for sarcopenia risk assessment and management.
Objectives:
- Develop and validate an AI-driven model integrating muscle composition, functional performance, and metabolic biomarkers to predict sarcopenia risk.
- Implement a personalized, adaptive intervention combining exercise and nutrition, guided by AI predictions and real-time monitoring.
- Evaluate the effectiveness of this intervention on muscle mass, functional performance, and metabolic health in older adults.
Methods:
研究设计
- 研究类型
- Interventional
- 分配方式
- Na
- 干预模型
- Single Group
- 主要目的
- Prevention
- 盲法
- None
入排标准
- 年龄范围
- 50 Years 至 70 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Men and women aged 50-70 years
- •At risk for sarcopenia based on muscle mass and/or muscle function screening
- •Able to participate in supervised exercise training
- •Willing to comply with study procedures and provide written informed consent
排除标准
- •Participation in structured exercise or weight loss programs within the past 6 months
- •Unstable body weight (>±5%) in the past 6 months
- •Current smoking or smoking within the past 6 months
- •Pregnancy, breastfeeding, or post-menopause
- •Contraindications to MRI (e.g., implanted devices, tattoos, permanent makeup)
- •Severe cardiopulmonary disease (e.g., recent myocardial infarction, unstable angina)
- •Musculoskeletal or neuromuscular conditions limiting exercise participation
- •Cognitive impairment
- •Chronic diseases including cancer, diabetes, thyroid disease, hypertension, or chronic renal failure
- •Use of medications affecting metabolism
- •Secondary liver disease (viral, autoimmune, alcoholic, or drug-induced)
- •Alcohol intake >20 g/day (women) or >30 g/day (men)
研究组 & 干预措施
AI-Guided Personalized Exercise and Nutrition Intervention
All participants undergo comprehensive baseline profiling and receive a 12-week personalized, AI-guided exercise and nutrition intervention designed to improve muscle mass, muscle function, and metabolic health. Individualized recommendations are generated using a machine learning-based sarcopenia risk prediction model and are dynamically adjusted based on physiological responses and wearable sensor data.
Participants are stratified by sarcopenia risk (low, moderate, high) but all receive the same adaptive intervention framework.
干预措施: Personalized AI-Guided Exercise and Nutrition (Behavioral)
结局指标
主要结局
Accuracy of AI-Based Sarcopenia Risk Prediction Model
时间窗: Baseline to end of follow-up (up to 12 months)
Predictive performance of an artificial intelligence-based model to identify current and future risk of sarcopenia using multimodal baseline data, including body composition, muscle function, metabolic biomarkers, and wearable-derived measures.
Change in MRI-Derived Thigh Muscle Volume
时间窗: Baseline to 12 weeks
Mean change in thigh skeletal muscle volume assessed by 3-Tesla MRI (Siemens Prisma) using standardized segmentation analysis. Unit of Measure: cm³
Change in Handgrip Strength (kg)
时间窗: Baseline to 12 weeks
Mean change in maximal handgrip strength measured using a Jamar dynamometer (best of three trials). Unit of Measure: kg
次要结局
- Change in Appendicular Lean Mass Index (ALM/height²) Measured by DXA(Baseline to 12 weeks)
- Change in Resting Metabolic Rate (kcal/day)(Baseline to 12 weeks)
- Change in Gut Microbiome Diversity(Baseline to 12 weeks)
- Change in Short Physical Performance Battery (SPPB) Total Score(Baseline to 12 weeks)
- Change in Quality of Life Assessed by SF-36(Baseline to 12 weeks)
研究者
Gepner Yftach
Principal Investigator - Professor
Tel Aviv University