Purpose: To evaluate whether an artificial intelligence (AI)–assisted surveillance device, AUGi, improves documentation of falls and injury rates in assisted living facilities (ALFs). Method: The current study represents a secondary analysis of existing facility fall documentation data. An interrupted time series design analyzed monthly fall data from 9 months before and 4 months after AUGi installation. Segmented regression assessed changes in fall documentation trends. Results: No statistically significant immediate or trend changes were observed for total, injured, or non-injured falls. Injury rate slightly declined (Cohen's d = −0.54) without significance. Although statistical power was low (13%), the effect size suggests potential clinical relevance. Conclusion: Findings suggest pre-installation under-documentation and improved post-installation accuracy. AI–assisted surveillance may enhance fall reporting, patient safety, and quality improvement in long-term care. Findings may serve as a springboard for more rigorous studies examining injury prevention, quality of life, and mortality outcomes in ALFs.
Sun et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: