The global aging population presents a significant public health challenge, with rising rates of chronic illnesses, functional decline, and healthcare expenditures. This study proposes an AI-driven framework for scalable preventive health interventions tailored to aging populations, integrating real-time health monitoring, predictive analytics, and personalized care planning. The framework leverages machine learning algorithms, wearable health devices, and electronic health record (EHR) data to identify early signs of functional decline and chronic disease progression among older adults. It emphasizes proactive risk stratification, continuous monitoring, and timely intervention through adaptive, data-informed recommendations. The proposed framework was evaluated using a multi-source dataset comprising physiological metrics, medical history, lifestyle indicators, and sociodemographic variables from over 15,000 individuals aged 60 and above. Feature engineering was applied to capture nuanced predictors such as gait changes, heart rate variability, medication adherence patterns, and social isolation indicators. Predictive models were built using random forest, support vector machines, and deep learning architectures, achieving an area under the ROC curve (AUC) of up to 0.89 in identifying individuals at risk of hospitalization within six months. Furthermore, the framework supports scalable deployment through cloud-based infrastructure and interoperability with telehealth systems, enabling real-time alerts and decision support for care teams. Pilot simulations demonstrated that AI-powered interventions such as automated reminders, nutritional guidance, virtual coaching, and remote triage significantly reduced avoidable hospitalizations and improved preventive screening compliance by 28%. The study highlights the importance of explainable AI to foster trust among clinicians and patients, and proposes an ethical governance model for responsible AI use in elderly care. This AI-driven preventive health framework offers a transformative approach to addressing the complex needs of aging populations by shifting from reactive to preventive care. By integrating AI with human-centered design and public health strategies, the framework enables scalable, equitable, and proactive care delivery. Future work includes expanding the dataset to include cognitive function metrics and longitudinal behavioral data to enhance model robustness and personalization.