Page 138 - AIH-1-2

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Enhancing patient safety through integrated

sensor technology and machine learning for
bed-based patient movement detection in

inpatient care

1
2
1
Jonathan Mayer , Rejath Jose , Molly Bekbolatova , Chris Coletti ,
1
2
1
Timothy Devine , and Milan Toma *
1 Department of Osteopathic Manipulative Medicine, New York Institute of Technology College of
Osteopathic Medicine, Old Westbury, New York, United States of America
2 Ferrara Center for Patient Safety and Clinical Simulation, New York Institute of Technology College
of Osteopathic Medicine, Old Westbury, New York, United States of America
Abstract

The occurrence of inpatient falls and new-onset seizures are common complications
during hospital stays, posing risks to patient safety and potentially leading to
prolonged hospital stays and further complications. Given the constraints on
medical staff’s ability to provide constant monitoring due to their workload, the
implementation of a sensor device equipped with machine learning capabilities to
recognize and prevent these events becomes imperative. This study utilized data
*Corresponding author: acquired through the Movella Xsens sensor, which detects real-time motions and 3D
Milan Toma movements, in conjunction with the PyCaret machine-learning algorithm. Adult-sized
(tomamil@tomamil.com)
and infant-sized mannequins were used to assess the algorithm’s ability in predicting
Citation: Mayer J, Jose R, specific movements associated with breathing, seizures, rolling to the right side,
Bekbolatova M, Coletti C, Devine T, rolling to the left side, rolling off the bed from the left, and rolling off the bed from
Toma M. Enhancing patient
safety through integrated sensor the right. The study achieved an overall 89% accuracy rate in detecting each specific
technology and machine learning movement using the combination of PyCaret and Xsens sensors. The application
for bed-based patient movement of PyCaret alongside Xsens sensors demonstrates promising results in accurately
detection in inpatient care.
Artif Intell Health. 2024;1(2): 132-143. detecting movements, thereby mitigating falls and post-seizure complications in an
doi: 10.36922/aih.2790 inpatient setting, consequently improving patient safety. Further exploration of this
Received: January 19, 2024 technology holds the potential to revolutionize healthcare delivery by incorporating
it into a trigger alert system capable of promptly warning medical staff of urgent
Accepted: March 27, 2024
situations through real-time capture and analysis of potentially harmful motions.
Published Online: April 23, 2024
Copyright: © 2024 Author(s). Keywords: Inpatient falls; Sensor device; Machine learning; Patient safety;
This is an Open-Access article
distributed under the terms of the Movement detection
Creative Commons Attribution
License, permitting distribution,
and reproduction in any medium,
provided the original work is
properly cited. 1. Introduction
Publisher’s Note: AccScience During inpatient hospital stays, falls serve as prominent starting points for numerous
Publishing remains neutral with significant afflictions in patients. Annually, the documentation records up to 1 million
regard to jurisdictional claims in
published maps and institutional inpatient hospital falls, with nearly 250,000 causing various injuries and 11,000 even
1
affiliations. leading to fatalities. Inpatient hospital falls not only concern patients on an individual

Volume 1 Issue 2 (2024) 132 doi: 10.36922/aih.2790