Clin-STAR Corner: Practice Changing Advances at the Interface of Artificial Intelligence/Machine Learning and...

Area of Science:

• Geriatric Medicine
• Artificial Intelligence in Healthcare
• Digital Health

Background:

• Older adults are underrepresented in artificial intelligence (AI) and machine learning (ML) model development, leading to concerns about bias and generalizability.
• The ethical, equitable, and person-centered implementation of AI/ML in aging populations requires critical appraisal of emerging tools.
• Randomized controlled trials (RCTs) are essential for evaluating the long-term impact and methodological rigor of AI/ML interventions in older adults.

Purpose of the Study:

• To identify and evaluate recent randomized controlled trials (RCTs) of AI/ML-based interventions in adults aged 65 years and older.
• To assess the clinical impact, scalability, and methodological rigor of AI/ML interventions in geriatric care.
• To synthesize evidence on the effectiveness of AI/ML in rehabilitation, preventive care, and remote monitoring for older adults.

Main Methods:

• A structured MEDLINE search was conducted for RCTs published between January 2023 and December 2025.
• Studies evaluated AI/ML interventions in adults aged 65 years and older.
• Inclusion criteria focused on scalability, clinical impact, and methodological rigor, with four articles meeting the criteria.

Main Results:

• AI/ML interventions demonstrated significant clinical benefits in postoperative rehabilitation and preventive care.
• Applications included robotic systems for weight-bearing quantification, algorithm-guided rehabilitation, personalized exercise programs via smartphone platforms, and AI-driven vaccine counseling chatbots.
• AI-driven interventions improved physical recovery, psychosocial well-being, and uptake of preventive measures compared to conventional care.

Conclusions:

• AI/ML interventions offer transformative potential for enhancing geriatric care, improving recovery, and supporting well-being.
• Future implementation requires addressing digital health literacy, ensuring long-term follow-up, and mitigating potential bias.
• Prioritizing safety, ethics, and equitable access is essential to ensure AI enhances, rather than replaces, person-centered geriatric care.