Integrating AI-Driven Models for Falls Risk Assessment in Older Adults

Falls in older adults represent a major public health concern, leading to significant morbidity and mortality. Traditional falls risk assessments often rely on subjective evaluations, which can vary in accuracy. This research investigates the potential of integrating artificial intelligence (AI) models into falls risk assessment protocols to enhance predictive accuracy and timely intervention. The study reviews various AI-driven models, including machine learning algorithms, that predict falls by analysing data from clinical records, sensor technology, and patient health profiles. Findings suggest that AI models outperform conventional methods in predicting falls risks, allowing healthcare providers to implement more targeted prevention strategies. The poster will visually present the AI architecture, key predictive factors, and a comparative analysis of AI and traditional assessment models. This research highlights the need for the integration of AI technologies into routine geriatric care to improve patient outcomes and reduce healthcare costs associated with falls.