SCIENTIFIC PUBLICATIONS AND ABSTRACTS

Rudokaite, J, Ong, L-L, Janssen, MP, Postma, E, Huis in ’t Veld, E. Predicting vasovagal reactions to a virtual blood donation using facial image analysis. Transfusion. 2022; 62: 838– 847. https://doi.org/10.1111/trf.16832

Abstract: People with needle fear experience not only anxiety and stress but also vasovagal reactions (VVR), including nausea, dizziness, sweating, pallor changes, or even fainting. However, the mechanism behind needle fear and the VVR response are not yet well understood. The aim of our study was to explore whether fluctuations in facial temperature in several facial regions are related to the level of experienced vasovagal reactions, in a simulated blood donation.

We recruited 45 students at Tilburg University and filmed them throughout a virtual blood donation procedure using an Infrared Thermal Imaging (ITI) camera. Participants reported their fear of needles and level of experienced vasovagal reactions. ITI data pre-processing was completed on each video frame by detecting facial landmarks and image alignment before extracting the mean temperature from the six regions of interest.

Temperatures of the chin and left and right cheek areas increased during the virtual blood donation.

Mixed-effects linear regression showed a significant association between self-reported vasovagal reactions and temperature fluctuations in the area below the nose.

Our results suggest that the area below the nose may be an interesting target for measuring vasovagal reactions using video imaging techniques. This is the first in a line of studies, which assess whether it is possible to automatically detect levels of fear and vasovagal reactions using facial imaging, from which the development of e-health solutions and interventions can benefit.

Rudokaite, J, Ong, L-L., Onal Ertugrul, I., Janssen, MP, Huis in ’t Veld, E. Predicting vasovagal reactions to needles with anticipatory facial temperature profiles (submitted).

In this study, we use a novel, non-invasive neurophysiological imaging technique (infrared thermal imaging) combined with artificial intelligence to assess and predict emotional and vasovagal (physical) reactions to needle fear in a real health care setting. This topic is quite understudied, as it is normally assessed using laboratory induced reactions using tilt-table tests, or by showing pictures or videos of needles. For this study, we’ve collected real-life data of actual people undergoing a needle-related procedure (a blood donation), resulting in a unique dataset.

This study aims to investigate whether facial temperature profiles measured in the waiting room, prior to a blood donation, can be used to predict who will experience VVR during the donation. Average temperature profiles from six facial regions were extracted from pre-donation recordings of 194 blood donors, and machine learning was used to classify whether a donor would experience low or high levels of VVR during the donation. An XGBoost classifier was able to predict who will experience an adverse reaction during a blood donation based on this early facial temperature data, with a high F1-score (the weighted average or precision and recall) of 0.86. Temperature fluctuations in the area under the nose, chin and forehead have the highest predictive value.

This is the first study to demonstrate that it is indeed possible to accurately predict whether a person will suffer from an adverse emotional or physical (vasovagal) reactions during the needle-related procedure, based on their facial reactions in the waiting room. This technique opens up an easy to administer and non-invasive way to prevent needle-induced fear and vasovagal reactions.

Rudokaite, J, Ong, L-L., Onal Ertugrul, I., Janssen, MP, Huis in ’t Veld, E. Predicting vasovagal reactions to needles from video data using 2D-CNN with GRU and LSTM. (in preparation, almost ready for submission)

Most people are not aware or are not able to self-report the adverse emotional and physical reactions so-called vasovagal reactions (VVR) until they escalate, and it is too late to prevent them. Thus, rather than relying on the self-report measurements, in our study we investigate whether we can predict VVR levels from the facial features measured during the blood donation. We filmed 235 blood donors throughout the blood donation procedure where 1776 obtained videos were used for data analysis. We compared 5 different sequences of videos – 45 seconds, 30 seconds, 20 seconds, 10 seconds and 5 seconds to test the shortest video duration required to predict VVR levels. We used 2D-CNN with LSTM and GRU on continuous VVR scores and on discrete (low and high) VVR values obtained during the blood donation. The results showed that during the classification task the highest achieved F1 score was 0.81 using GRU on 25 frames and during the regression task the lowest achieved root mean square error was 2.56 using GRU on 50 frames. This study is to demonstrate that it is possible to predict vasovagal responses during a blood donation using facial features, which supports the development of interventions to prevent VVR.

Rudokaite, J, Onal Ertugrul, I., Ong, L-L., Janssen, MP, Huis in ’t Veld, E. Predicting vasovagal reactions to needles from facial action units. (in preparation, almost ready for submission).

Merely a sight of needles for some people can cause extreme emotional and physical reactions such as fear, panic, nausea, dizziness or even fainting, so-called vasovagal reactions (VVR). However, needle fear is not easily solvable because vasovagal reactions are automatic and difficult to self-report before it is too late to intervene. This study aims to investigate whether facial action units measured in the waiting room, prior to a blood donation, can be used to predict who will experience VVR during the donation. Presence and intensity of 17 facial action units were extracted from video recordings of 227 donors, and used to classify low and high level of VVR by a machine learning algorithms. We included three groups of blood donors: (1) those who have never experienced vasovagal reactions in the past (N=81), (2) those who experienced vasovagal reaction at their last donation (N=51), and (3) new donors with an increased risk of experiencing VVR (N=95). The most predictive features were intensity of facial action units in the eye regions, with an F1, the weighted average or precision and recall, score of 0.82. This study is the first to demonstrate that it is possible to predict vasovagal responses during a blood donation using facial action units recorded in the waiting room area prior to donation.

EMAIL ONS

STUUR ONS EEN MAIL NAAR INFO@AINAR.NL

BEL ONS

BEL ONS OP +31 (0)6 107 058 68

VIND ONS

PLESMANLAAN 125
1066 CX AMSTERDAM

INFO

KVK 83754687
BTW NL862978749B01

© COPYRIGHT AINAR 2020 – 2024