Vendor-reported figures — source: helpany.com
Traditional care models rely on periodic check-ins and staff intuition, frequently missing early signs of resident deterioration. Nearly half of all long-term care residents experience falls annually—averaging 1.7 falls per person—costing communities up to $380,000 in direct expenses each year. Care teams lacked real-time visibility into subtle behavioral changes that precede emergencies.
Communities deployed PAUL, Helpany's radar-based fall prevention device, which monitors residents 24/7 using contactless radar (no cameras, microphones, or wearables). Its AI continuously tracks motion patterns—gait speed, bathroom usage, sleep restlessness—and alerts caregivers when deviations suggest early risk. The platform also analyzes routines and service plan discrepancies for quality assurance.
Across 10 Arizona communities, falls dropped an average of 66%, with some communities achieving up to 72% fewer incidents and zero nighttime falls month over month. The platform enabled over 1,000 proactive interventions, delivered 21% more personalized caregiver time without adding staff, and reduced fall-related 911 calls by up to 80%. Communities estimated $108,000–$200,000 in added annual value per site.
Have a similar implementation?
Share your customer's AI results and link it to your vendor profile.
Submit a case study →