Exposure-Normalized Bed and Chair Fall Rates via Continuous AI Monitoring

TL;DR

This study used continuous AI to accurately measure fall rates based on exposure time, revealing higher fall risks associated with chairs compared to beds, and highlighting footrest positioning as a key factor.

Contribution

It introduces a novel exposure-normalized method for fall rate estimation using AI monitoring, providing more precise risk assessments than traditional bed-day metrics.

Findings

Fall rates were 17.8 per 1,000 chair exposure-hours and 4.3 per 1,000 bed exposure-hours.

Chair falls were often linked to footrest-positioning failures.

The study suggests safer chair setups could reduce fall risks.

Abstract

This retrospective cohort study used continuous AI monitoring to estimate fall rates by exposure time rather than occupied bed-days. From August 2024 to December 2025, 3,980 eligible monitoring units contributed 292,914 hourly rows, yielding probability-weighted rates of 17.8 falls per 1,000 chair exposure-hours and 4.3 per 1,000 bed exposure-hours. Within the study window, 43 adjudicated falls matched the monitoring pipeline, and 40 linked to eligible exposure hours for the primary Poisson model, producing an adjusted chair-versus-bed rate ratio of 2.35 (95% confidence interval 0.87 to 6.33; p=0.0907). In a separate broader observation cohort (n=32 deduplicated events), 6 of 7 direct chair falls involved footrest-positioning failures. Because this was an observational study in a single health system, these findings remain hypothesis-generating and support testing safer chair setups rather than using chairs less.