Non-contact physiological monitoring of preterm infants in the Neonatal Intensive Care Unit

Mauricio Villarroel,João Jorge,Kenny Mccormick,Sara Davis,Lionel Tarassenko,Andrew Zisserman,Gabrielle Green,Peter Watkinson,Carlos Arteta,Sitthichok Chaichulee

doi:10.1038/s41746-019-0199-5

Mauricio Villarroel, João Jorge + Show 8 more

Open Access

https://doi.org/10.1038/s41746-019-0199-5

Copy DOI

Abstract

The implementation of video-based non-contact technologies to monitor the vital signs of preterm infants in the hospital presents several challenges, such as the detection of the presence or the absence of a patient in the video frame, robustness to changes in lighting conditions, automated identification of suitable time periods and regions of interest from which vital signs can be estimated. We carried out a clinical study to evaluate the accuracy and the proportion of time that heart rate and respiratory rate can be estimated from preterm infants using only a video camera in a clinical environment, without interfering with regular patient care. A total of 426.6 h of video and reference vital signs were recorded for 90 sessions from 30 preterm infants in the Neonatal Intensive Care Unit (NICU) of the John Radcliffe Hospital in Oxford. Each preterm infant was recorded under regular ambient light during daytime for up to four consecutive days. We developed multi-task deep learning algorithms to automatically segment skin areas and to estimate vital signs only when the infant was present in the field of view of the video camera and no clinical interventions were undertaken. We propose signal quality assessment algorithms for both heart rate and respiratory rate to discriminate between clinically acceptable and noisy signals. The mean absolute error between the reference and camera-derived heart rates was 2.3 beats/min for over 76% of the time for which the reference and camera data were valid. The mean absolute error between the reference and camera-derived respiratory rate was 3.5 breaths/min for over 82% of the time. Accurate estimates of heart rate and respiratory rate could be derived for at least 90% of the time, if gaps of up to 30 seconds with no estimates were allowed.

Highlights

The World Health Organization defines term pregnancy as a delivery between 37 and 42 weeks of gestation.[1]
This paper proposes non-contact algorithms for estimating heart rate and respiratory rate from preterm infants in an unconstrained and challenging hospital environment
The proposed multi-task deep learning algorithms performed three tasks that provided essential information for the automatic extraction of vital signs from a video camera in a hospital environment: the detection of the patient in the video frame, the automated segmentation of skin areas and the detection of time periods during which clinical interventions were performed by the attending hospital staff

Summary

Introduction

The World Health Organization defines term pregnancy as a delivery between 37 and 42 weeks of gestation.[1] Gestational age is often computed as the number of completed weeks of pregnancy measured from the first day of the mother’s last menstrual period.[2,3] Preterm birth, the primary focus of this paper, is defined as any birth prior to 37 weeks of gestation. Because the physiology and outcomes of preterm infants vary broadly, preterm birth is often subdivided as: late preterm, infants born between 34 and 37 weeks of gestation; moderate preterm, between 32 and. 34 weeks; very preterm, between 28 and 32 weeks; and extremely preterm, infants born less than 28 weeks of gestation.[4]. Preterm birth is a major global health problem.

Objectives

Results

Conclusion