Fall detection in extreme class imbalance: a cascade architecture for real-world deployment
Falls among older adults result in over 3 million emergency department visits and 32,000 deaths annually in the United States, with medical costs exceeding $50 billion. Automated fall detection systems face a fundamental challenge: extreme class imbalance in continuous monitoring, where fall events constitute less than 2% of footage, causing high false-positive rates and alarm fatigue. We propose a cascade architecture that decomposes fall detection into two sequential stages with complementary optimization objectives. Stage 1 employs a lightweight 3D convolutional neural network trained via curriculum learning with adaptive focal loss to deliberately maximize recall on the minority class. Stage 2 applies a feature-based arbiter that analyzes CNN internal representations to validate candidates, reducing false positives while preserving sensitivity. We validated our approach on 190 videos with simulated falls (LE2I dataset) and 300 spontaneous falls from elderly residents in long-term care facilities (Robinovitch dataset). Our cascade architecture achieved 82.4% recall with 32.2% precision, representing a 38% relative precision improvement over single-stage CNN baselines (88.5% recall, 23.3% precision). The 40.5% false positive reduction substantially improves clinical viability while maintaining sensitivity above 80%, providing a foundation for real-world deployment in care settings facing severe data constraints.