Falls in the elderly represent a critical public health issue, with nearly 29% of Italians over 65 experiencing at least one fall per year, often resulting in fractures, hospitalizations, or fatalities in those over 75. Risk factors include advanced age, malnutrition, loneliness, urban living, multiple chronic conditions, and polypharmacy. Fragility fractures account for 72% of related healthcare costs, with individual hip, knee, or wrist fractures averaging over €30,000 in Europe. Falls also cause 10–15% of geriatric hospitalizations. Emerging technologies for fall prevention integrate wearable and environmental sensors with AI to detect vital signs, gait anomalies, and daily activity patterns. When cross-referenced with clinical data on integrated platforms, this enables personalized risk stratification and real-time tele-monitoring, alerting caregivers and healthcare teams in the event of anomalies. This pilot study evaluates a wearable inertial-sensor smartwatch that tracks gait, balance. Predictive algorithms provide feedback to both caregivers and clinicians. The system is part of the CASSIA project led by Feature Jam in collaboration with several research and health institutions in Trieste. Standardized fall-risk assessment tools, such as the Tinetti Scale and Timed Up and Go Test, were correlated with sensor data to validate the system’s predictive capabilities in real-world clinical settings.