Research

Paper

TESTING March 24, 2026

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

Authors

Paolo Gabriel, Peter Rehani, Zack Drumm, Tyler Troy, Tiffany Wyatt, Narinder Singh

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.

Metadata

arXiv ID: 2603.22785
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22785v1</id>\n    <title>Exposure-Normalized Bed and Chair Fall Rates via Continuous AI Monitoring</title>\n    <updated>2026-03-24T04:20:48Z</updated>\n    <link href='https://arxiv.org/abs/2603.22785v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22785v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-24T04:20:48Z</published>\n    <arxiv:comment>23 pages, 6 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Paolo Gabriel</name>\n    </author>\n    <author>\n      <name>Peter Rehani</name>\n    </author>\n    <author>\n      <name>Zack Drumm</name>\n    </author>\n    <author>\n      <name>Tyler Troy</name>\n    </author>\n    <author>\n      <name>Tiffany Wyatt</name>\n    </author>\n    <author>\n      <name>Narinder Singh</name>\n    </author>\n  </entry>"
}