Sarcopenia, a progressive skeletal muscle disorder characterized by the loss of muscle mass and function, represents a significant challenge in geriatric orthopedics, with prevalence reaching as high as 48.7% in surgical populations. It is strongly associated with increased risks of falls, secondary fractures, postoperative complications, and mortality. Despite its clinical importance, traditional diagnostic methods like Dual-energy X-ray Absorptiometry (DXA) and Bioelectrical Impedance Analysis (BIA) are often impractical in acute orthopedic settings due to patient immobilization, positioning constraints, and postoperative fluid imbalances. This narrative review aims to summarize how the emergence of artificial intelligence (AI), particularly deep learning, addresses these gaps by enabling automated, high-throughput opportunistic screening from routine clinical imaging. Convolutional neural networks achieve expert-level segmentation of muscle quantity and quality, with Dice similarity coefficients often exceeding 0.94. AI-derived metrics serve as robust independent predictors for adverse surgical outcomes, including prolonged length of stay and infection, as well as functional recovery and one-year mortality. By integrating these metrics into Clinical Decision Support Systems (CDSS) and Electronic Medical Records (EMR), AI facilitates a paradigm shift from reactive fracture management to proactive prevention through automated "zero-click" alerts and multidisciplinary intervention pathways. While significant challenges regarding technical standardization, biological variability, and model interpretability persist, AI-driven assessment is transforming geriatric orthopedic care from subjective evaluation toward precise, objective quantification.

The author(s) declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.