Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference

ObjectivesWe aimed to clarify the influence of facial expressions on providing early recognition and diagnosis of Parkinson’s disease (PD).MethodsWe included 18 people with PD and 18 controls. The participants were asked to perform 12 monosyllabic tests, 8 disyllabic tests, and 6 multisyllabic tests...

Full description

Saved in:
Bibliographic Details
Main Authors: Meimei Mouse, Hongjie Gong, Yifeng Liu, Fan Xu, Xianwei Zou, Min Huang, Xi Yang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2025.1533942/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063149105938432
author Meimei Mouse
Hongjie Gong
Yifeng Liu
Fan Xu
Xianwei Zou
Min Huang
Xi Yang
author_facet Meimei Mouse
Hongjie Gong
Yifeng Liu
Fan Xu
Xianwei Zou
Min Huang
Xi Yang
author_sort Meimei Mouse
collection DOAJ
description ObjectivesWe aimed to clarify the influence of facial expressions on providing early recognition and diagnosis of Parkinson’s disease (PD).MethodsWe included 18 people with PD and 18 controls. The participants were asked to perform 12 monosyllabic tests, 8 disyllabic tests, and 6 multisyllabic tests and the whole process were recorded. Then 26 video clips recorded were used to decipher the facial muscle movements and face expression via Noldus FaceReader 7.0 software. 16 suitable variables were selected to construct a Bayesian network model.ResultsThe area under the curve of the unsegmented-syllabic, monosyllabic, dissyllabic, and multisyllabic training models was 0.960, 0.958, and 0.962, respectively, with no significant difference between the models. Based on the Bayesian network models, we found that except for valence in the disyllabic model, all positive facial expressions in the four models are negatively associated with the probability of PD. Moreover, negative facial expressions, including sadness, anger, scared, and disgust in the unsegmented-syllabic, monosyllabic, and multisyllabic models, as well as anger in the disyllabic model, are positively correlated to the probability of PD. Sadness, scare and disgust in disyllabic model are negatively associated with the probability of PD.ConclusionExcept for sad, scared, and disgusted generated by reading disyllables, negative expressions generated by reading other syllables were positively associated with the probability of PD. In addition, scared expressions produced during monosyllabic reading had the greatest effect on the probability of PD, and disgusted expressions produced during multisyllabic reading had the least effect.
format Article
id doaj-art-6c658fb1fc54492f9baa4f32665ff94a
institution DOAJ
issn 1664-2295
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj-art-6c658fb1fc54492f9baa4f32665ff94a2025-08-20T02:49:44ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-03-011610.3389/fneur.2025.15339421533942Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inferenceMeimei Mouse0Hongjie Gong1Yifeng Liu2Fan Xu3Xianwei Zou4Min Huang5Xi Yang6Department of Clinic Medicine, School of Clinical Medicine, Chengdu Medical College, Chengdu, ChinaDepartment of Clinic Medicine, School of Clinical Medicine, Chengdu Medical College, Chengdu, ChinaDepartment of Clinic Medicine, School of Clinical Medicine, Chengdu Medical College, Chengdu, ChinaDepartment of Evidence-Based Medicine and Social Medicine, School of Public Health, Chengdu Medical College, Chengdu, ChinaDepartment of Neurology, First Affiliated Hospital of Chengdu Medical College, Chengdu, ChinaDepartment of Physiology, School of Basic Medical Sciences, Chengdu Medical College, Chengdu, ChinaDepartment of Applied Psychology, School of Psychology, Chengdu Medical College, Chengdu, ChinaObjectivesWe aimed to clarify the influence of facial expressions on providing early recognition and diagnosis of Parkinson’s disease (PD).MethodsWe included 18 people with PD and 18 controls. The participants were asked to perform 12 monosyllabic tests, 8 disyllabic tests, and 6 multisyllabic tests and the whole process were recorded. Then 26 video clips recorded were used to decipher the facial muscle movements and face expression via Noldus FaceReader 7.0 software. 16 suitable variables were selected to construct a Bayesian network model.ResultsThe area under the curve of the unsegmented-syllabic, monosyllabic, dissyllabic, and multisyllabic training models was 0.960, 0.958, and 0.962, respectively, with no significant difference between the models. Based on the Bayesian network models, we found that except for valence in the disyllabic model, all positive facial expressions in the four models are negatively associated with the probability of PD. Moreover, negative facial expressions, including sadness, anger, scared, and disgust in the unsegmented-syllabic, monosyllabic, and multisyllabic models, as well as anger in the disyllabic model, are positively correlated to the probability of PD. Sadness, scare and disgust in disyllabic model are negatively associated with the probability of PD.ConclusionExcept for sad, scared, and disgusted generated by reading disyllables, negative expressions generated by reading other syllables were positively associated with the probability of PD. In addition, scared expressions produced during monosyllabic reading had the greatest effect on the probability of PD, and disgusted expressions produced during multisyllabic reading had the least effect.https://www.frontiersin.org/articles/10.3389/fneur.2025.1533942/fullParkinson’s diseasefacial expressionsBayesian networktree-augmented networkprediction modelNoldus FaceReader
spellingShingle Meimei Mouse
Hongjie Gong
Yifeng Liu
Fan Xu
Xianwei Zou
Min Huang
Xi Yang
Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
Frontiers in Neurology
Parkinson’s disease
facial expressions
Bayesian network
tree-augmented network
prediction model
Noldus FaceReader
title Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
title_full Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
title_fullStr Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
title_full_unstemmed Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
title_short Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
title_sort changes in facial expressions can distinguish parkinson s disease via bayesian inference
topic Parkinson’s disease
facial expressions
Bayesian network
tree-augmented network
prediction model
Noldus FaceReader
url https://www.frontiersin.org/articles/10.3389/fneur.2025.1533942/full
work_keys_str_mv AT meimeimouse changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT hongjiegong changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT yifengliu changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT fanxu changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT xianweizou changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT minhuang changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference
AT xiyang changesinfacialexpressionscandistinguishparkinsonsdiseaseviabayesianinference