Related Experiment Video
Updated: Jul 27, 2025
Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers
Published on: March 14, 2018
Multimodality Video Acquisition System for the Assessment of Vital Distress in Children
Vincent Boivin1,2, Mana Shahriari1,3, Gaspar Faure1
1CHU Sainte-Justine Research Centre, Montréal, QC H3T 1C5, Canada.
Insights
This study developed a novel video database to automatically assess vital distress in critically ill children. This system aims to improve early detection and management of respiratory and other critical events in pediatric intensive care units.
Area of Science:
- Biomedical Engineering
- Pediatric Critical Care
- Medical Informatics
Background:
- Vital distress events in children, especially respiratory issues, are often missed.
- Early and accurate detection of vital distress is crucial for improving outcomes in pediatric intensive care.
Purpose of the Study:
- To establish a prospective, high-quality video database for automated vital distress assessment in critically ill children.
- To describe the data acquisition process for a pediatric intensive care unit (PICU) video database.
Main Methods:
- Utilized Azure Kinect DK and Flir Lepton 3.5 LWIR sensors connected to a Jetson Xavier NX board.
- Implemented a secure web application with an API for automated video data acquisition.
- Collected over 290 RGB, thermographic, and point cloud videos, linked to electronic medical records.
Main Results:
- Successfully implemented an ongoing, high-fidelity video database for research and monitoring.
- Acquired extensive video data (RGB, thermographic, point cloud) linked to patient phenotypes.
- Established infrastructure for developing algorithms to quantify and detect vital distress.
Conclusions:
- The developed video database infrastructure supports the creation of algorithms for real-time vital distress detection.
- This technology has the potential to enhance both inpatient and outpatient management of pediatric critical conditions.
- Automated assessment of vital distress in children can lead to improved diagnostic capabilities and patient care.
Abstract:
In children, vital distress events, particularly respiratory, go unrecognized. To develop a standard model for automated assessment of vital distress in children, we aimed to construct a prospective high-quality video database for critically ill children in a pediatric intensive care unit (PICU) setting. The videos were acquired automatically through a secure web application with an application programming interface (API). The purpose of this article is to describe the data acquisition process from each PICU room to the research electronic database. Using an Azure Kinect DK and a Flir Lepton 3.5 LWIR attached to a Jetson Xavier NX board and the network architecture of our PICU, we have implemented an ongoing high-fidelity prospectively collected video database for research, monitoring, and diagnostic purposes. This infrastructure offers the opportunity to develop algorithms (including computational models) to quantify vital distress in order to evaluate vital distress events. More than 290 RGB, thermographic, and point cloud videos of each 30 s have been recorded in the database. Each recording is linked to the patient's numerical phenotype, i.e., the electronic medical health record and high-resolution medical database of our research center. The ultimate goal is to develop and validate algorithms to detect vital distress in real time, both for inpatient care and outpatient management.
