An Edge-AI Pose-Estimation Platform for Real-Time Posture and Posture-Transition Monitoring: A Feasibility Study for Pre-Emptive Fall-Risk Alerting in Elderly and Dementia Care
- 1University of Texas at Arlington
Abstract
Falls and unmonitored patient movements remain leading causes of harm in healthcare settings. Current solutions - such as weight-based alarms, remote video monitoring, and in-person sitters - are reactive, labor-intensive, or prone to false alarms, often compromising both care quality and staff efficiency. We developed a machine learning-enabled, proactive-preventive patient monitoring platform that uses 17-keypoint pose estimation to detect changes in patient posture and generate alerts in real time. The Edge-AI device integrates a Raspberry Pi 5, Hailo-8L neural processing unit (NPU), and Raspberry Pi camera module 3, and runs Hailo-YOLOv8-Pose at 30 frames per second to classify postures (i.e., lying, Fowlers, sitting, standing). Alerts are transmitted via Bluetooth to caregivers through earphones or speakers. System performance was evaluated across multiple scenarios, including bed and chair monitoring, free limb movement, partial body occlusion (e.g., blankets), and varying lighting and care environments. The platform maintained accurate monitoring under varying lighting conditions, including lights-off scenarios, and because all processing occurs locally without network dependence, it is designed to continue operating during network outages - an important resilience feature for care environments where connectivity may be interrupted. By abstracting images into skeletal keypoints without recording video, the system preserves privacy while potentially enabling earlier intervention and reducing false alarms and caregiver workload. This cost-effective, scalable system supports future enhancements such as dual alerting, multi-device full-room coverage, and continuous monitoring for dementia patients.
Related
- Feasibility and acceptability of a remote blood pressure monitoring pharmacist-led telehealth programme in an emergency department transition care clinic: a pilot randomised controlled trial
- Feasibility and acceptability of a randomized controlled trial of a patient-centred transition program for stroke survivors and their caregivers—P-NAVISTROKE study
- The hidden pause: Filtering of true prolonged asystole in implantable loop recorder monitoring platform by artificial intelligence.
- Smart Alerting in Smartphone‐Based First Responder Systems and Arrival Before Emergency Medical Services:The ALARM Randomized Clinical Trial
- A bilateral US-UK airplane wastewater monitoring pilot demonstrates the feasibility of an international wastewater surveillance network
BibTeX
@misc{sutton2026edgeai,
title = {{An Edge-AI Pose-Estimation Platform for Real-Time Posture and Posture-Transition Monitoring: A Feasibility Study for Pre-Emptive Fall-Risk Alerting in Elderly and Dementia Care}},
author = {B. Sutton and I. Perry and L. Kim and A. Jujjuvarapu and Y. Chae and Y.-t. Kim},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.04.26362534},
url = {https://www.medrxiv.org/content/10.64898/2026.11.04.26362534v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - An Edge-AI Pose-Estimation Platform for Real-Time Posture and Posture-Transition Monitoring: A Feasibility Study for Pre-Emptive Fall-Risk Alerting in Elderly and Dementia Care
AU - B. Sutton
AU - I. Perry
AU - L. Kim
AU - A. Jujjuvarapu
AU - Y. Chae
AU - Y.-t. Kim
PY - 2026
DA - 2026/11/04
PB - medRxiv
DO - 10.64898/2026.11.04.26362534
UR - https://www.medrxiv.org/content/10.64898/2026.11.04.26362534v1
AB - Falls and unmonitored patient movements remain leading causes of harm in healthcare settings. Current solutions - such as weight-based alarms, remote video monitoring, and in-person sitters - are reactive, labor-intensive, or prone to false alarms, often compromising both care quality and staff efficiency. We developed a machine learning-enabled, proactive-preventive patient monitoring platform that uses 17-keypoint pose estimation to detect changes in patient posture and generate alerts in real time. The Edge-AI device integrates a Raspberry Pi 5, Hailo-8L neural processing unit (NPU), and Raspberry Pi camera module 3, and runs Hailo-YOLOv8-Pose at 30 frames per second to classify postures (i.e., lying, Fowlers, sitting, standing). Alerts are transmitted via Bluetooth to caregivers through earphones or speakers. System performance was evaluated across multiple scenarios, including bed and chair monitoring, free limb movement, partial body occlusion (e.g., blankets), and varying lighting and care environments. The platform maintained accurate monitoring under varying lighting conditions, including lights-off scenarios, and because all processing occurs locally without network dependence, it is designed to continue operating during network outages - an important resilience feature for care environments where connectivity may be interrupted. By abstracting images into skeletal keypoints without recording video, the system preserves privacy while potentially enabling earlier intervention and reducing false alarms and caregiver workload. This cost-effective, scalable system supports future enhancements such as dual alerting, multi-device full-room coverage, and continuous monitoring for dementia patients.
ER -