Mapping spontaneous facial expression in people with Parkinson's disease: A multiple case study design

The Story behind the Mask: A Narrative Review on Hypomimia in Parkinson's Disease

Facial movements are crucial for social and emotional interaction and well-being. Reduced facial expressions (i.e., hypomimia) is a common feature in patients with Parkinson's disease (PD) and previous studies linked this manifestation to both motor symptoms of the disease and altered emotion recognition and processing. Nevertheless, research on facial motor impairment in PD has been rather scarce and only a limited number of clinical evaluation tools are available, often suffering from poor validation processes and high inter- and intra-rater variability. In recent years, the availability of technology-enhanced quantification methods of facial movements, such as automated video analysis and machine learning application, led to increasing interest in studying hypomimia in PD. In this narrative review, we summarize the current knowledge on pathophysiological hypotheses at the basis of hypomimia in PD, with particular focus on the association between reduced facial expressions and emotional processing and analyze the current evaluation tools and management strategies for this symptom, as well as future research perspectives.

Exploring facial expressions and action unit domains for Parkinson detection

BACKGROUND AND OBJECTIVE

Patients suffering from Parkinson's disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection.

METHODS

Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects.

RESULTS

Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at https://github.com/luisf-gomez/Explorer-FE-AU-in-PD.

CONCLUSIONS

Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.

Facial muscle movements in patients with Parkinson's disease undergoing phonation tests

Purpose

Parkinson's disease (PD) is a serious neurodegenerative disease affecting the elderly. In general, the locomotion deficit, which seriously affects the daily life of patients with PD, usually occurs at a later stage. The mask face symptom meanwhile progressively worsens. However, facial muscle disorders and changes involved in the freezing mask are unclear.

Method

In this study, we recruited 35 patients with PD and 26 age- and sex-balanced controls to undergo phonation tests, while the built-in camera on the laptop recorded their facial expressions during the whole pronunciation process. Furthermore, FaceReader (version 7.0; Noldus Information Technology, Wageningen, Netherlands) was used to analyze changes in PD facial landmark movement and region movement.

Results

The two-tailed Student's t-test showed that the changes in facial landmark movement among 49 landmarks were significantly lower in patients with PD than in the control group (P < 0.05). The data on facial region movement revealed that the eyes and upper lip of patients with PD differed significantly from those in the control group.

Conclusion

Patients with PD had defects in facial landmark movement and regional movement when producing a single syllable, double syllable, and multiple syllables, which may be related to reduced facial expressions in patients with PD.

Action and emotion perception in Parkinson's disease: A neuroimaging meta-analysis

•

The neural substrates for action and emotion perception deficits in PD are still unclear.

•

We addressed this issue via coordinate-based meta-analyses of previous fMRI data.

•

PD patients exhibit decreased response in the basal ganglia.

•

PD patients exhibit a trend toward decreased response in the parietal areas.

•

PD patients exhibit a trend toward increased activation in the posterior cerebellum.

Patients with Parkinson disease (PD) may show impairments in the social perception. Whether these deficits have been consistently reported, it remains to be clarified which brain alterations subtend them. To this aim, we conducted a neuroimaging meta-analysis to compare the brain activity during social perception in patients with PD versus healthy controls. Our results show that PD patients exhibit a significantly decreased response in the basal ganglia (putamen and pallidum) and a trend toward decreased activity in the mirror system, particularly in the left parietal cortex (inferior parietal lobule and intraparietal sulcus). This reduced activation may be tied to a disruption of cognitive resonance mechanisms and may thus constitute the basis of impaired others’ representations underlying action and emotion perception. We also found increased activation in the posterior cerebellum in PD, although only in a within-group analysis and not in comparison with healthy controls. This cerebellar activation may reflect compensatory mechanisms, an aspect that deserves further investigation. We discuss the clinical implications of our findings for the development of novel social skill training programs for PD patients.

Automated analysis of facial emotions in subjects with cognitive impairment

Differences in expressing facial emotions are broadly observed in people with cognitive impairment. However, these differences have been difficult to objectively quantify and systematically evaluate among people with cognitive impairment across disease etiologies and severity. Therefore, a computer vision-based deep learning model for facial emotion recognition trained on 400.000 faces was utilized to analyze facial emotions expressed during a passive viewing memory test. In addition, this study was conducted on a large number of individuals (n = 493), including healthy controls and individuals with cognitive impairment due to diverse underlying etiologies and across different disease stages. Diagnoses included subjective cognitive impairment, Mild Cognitive Impairment (MCI) due to AD, MCI due to other etiologies, dementia due to Alzheimer's diseases (AD), and dementia due to other etiologies (e.g., Vascular Dementia, Frontotemporal Dementia, Lewy Body Dementia, etc.). The Montreal Cognitive Assessment (MoCA) was used to evaluate cognitive performance across all participants. A participant with a score of less than or equal to 24 was considered cognitively impaired (CI). Compared to cognitively unimpaired (CU) participants, CI participants expressed significantly less positive emotions, more negative emotions, and higher facial expressiveness during the test. In addition, classification analysis revealed that facial emotions expressed during the test allowed effective differentiation of CI from CU participants, largely independent of sex, race, age, education level, mood, and eye movements (derived from an eye-tracking-based digital biomarker for cognitive impairment). No screening methods reliably differentiated the underlying etiology of the cognitive impairment. The findings provide quantitative and comprehensive evidence that the expression of facial emotions is significantly different in people with cognitive impairment, and suggests this may be a useful tool for passive screening of cognitive impairment.

Autonomic factors do not underlie the elevated self-disgust levels in Parkinson's disease

INTRODUCTION

Parkinson's disease (PD) is manifested along with non-motor symptoms such as impairments in basic emotion regulation, recognition and expression. Yet, self-conscious emotion (SCEs) such as self-disgust, guilt and shame are under-investigated. Our previous research indicated that Parkinson patients have elevated levels of self-reported and induced self-disgust. However, the cause of that elevation-whether lower level biophysiological factors, or higher level cognitive factors, is unknown.

METHODS

To explore the former, we analysed Skin Conductance Response (SCR, measuring sympathetic activity) amplitude and high frequency Heart Rate Variability (HRV, measuring parasympathetic activity) across two emotion induction paradigms, one involving narrations of personal experiences of self-disgust, shame and guilt, and one targeting self-disgust selectively via images of the self. Both paradigms had a neutral condition.

RESULTS

Photo paradigm elicited significant changes in physiological responses in patients relative to controls-higher percentages of HRV in the high frequency range but lower SCR amplitudes, with patients to present lower responses compared to controls. In the narration paradigm, only guilt condition elicited significant SCR differences between groups.

CONCLUSIONS

Consequently, lower level biophysiological factors are unlikely to cause elevated self-disgust levels in Parkinson's disease, which by implication suggests that higher level cognitive factors may be responsible.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Automated Computer Vision Assessment of Hypomimia in Parkinson Disease: Proof-of-Principle Pilot Study

BACKGROUND

Facial expressions require the complex coordination of 43 different facial muscles. Parkinson disease (PD) affects facial musculature leading to "hypomimia" or "masked facies."

OBJECTIVE

We aimed to determine whether modern computer vision techniques can be applied to detect masked facies and quantify drug states in PD.

METHODS

We trained a convolutional neural network on images extracted from videos of 107 self-identified people with PD, along with 1595 videos of controls, in order to detect PD hypomimia cues. This trained model was applied to clinical interviews of 35 PD patients in their on and off drug motor states, and seven journalist interviews of the actor Alan Alda obtained before and after he was diagnosed with PD.

RESULTS

The algorithm achieved a test set area under the receiver operating characteristic curve of 0.71 on 54 subjects to detect PD hypomimia, compared to a value of 0.75 for trained neurologists using the United Parkinson Disease Rating Scale-III Facial Expression score. Additionally, the model accuracy to classify the on and off drug states in the clinical samples was 63% (22/35), in contrast to an accuracy of 46% (16/35) when using clinical rater scores. Finally, each of Alan Alda's seven interviews were successfully classified as occurring before (versus after) his diagnosis, with 100% accuracy (7/7).

CONCLUSIONS

This proof-of-principle pilot study demonstrated that computer vision holds promise as a valuable tool for PD hypomimia and for monitoring a patient's motor state in an objective and noninvasive way, particularly given the increasing importance of telemedicine.

Social Symptoms of Parkinson's Disease

Parkinson's disease (PD) is typically well recognized by its characteristic motor symptoms (e.g., bradykinesia, rigidity, and tremor). The cognitive symptoms of PD are increasingly being acknowledged by clinicians and researchers alike. However, PD also involves a host of emotional and communicative changes which can cause major disruptions to social functioning. These incude problems producing emotional facial expressions (i.e., facial masking) and emotional speech (i.e., dysarthria), as well as difficulties recognizing the verbal and nonverbal emotional cues of others. These social symptoms of PD can result in severe negative social consequences, including stigma, dehumanization, and loneliness, which might affect quality of life to an even greater extent than more well-recognized motor or cognitive symptoms. It is, therefore, imperative that researchers and clinicans become aware of these potential social symptoms and their negative effects, in order to properly investigate and manage the socioemotional aspects of PD. This narrative review provides an examination of the current research surrounding some of the most common social symptoms of PD and their related social consequences and argues that proactively and adequately addressing these issues might improve disease outcomes.

Profile of social self-management practices in daily life with Parkinson's disease is associated with symptom severity and health quality of life

Purpose: Social participation is a key determinant of healthy aging, yet little is known about how people with Parkinson's disease manage social living. This study describes individual differences in social self-management practices and their association with symptom severity and health quality of life.Methods: People with Parkinson's disease (N = 90) completed measures of healthy routines, activities and relationships, symptom severity, and health related quality of life. Cluster analysis identified profiles of social self-management practices. Analysis of variance tested differences between profiles in symptom severity and health quality of life.Results: Participants clustered into one of seven groups according to different combinations of three practices: health resources utilization, activities in home and community, and social support relationships. The healthiest cluster engaged equally in all three practices at above sample average degree of engagement. Four clusters that engaged at or above sample average in activities in home and community experienced less health problems than three clusters that engaged below average. Variation in aspects of social lifestyle unrelated to health appeared also to contribute to profile diversity.Conclusion: Findings provide insight into similarity and variation in how people with Parkinson's disease engage with social self-management resources and point to person-centered interventions.Implications for RehabilitationSocial self-management is a biopsychosocial construct to identify and describe self-care practices that engage one's social resources for managing healthful daily living.People with Parkinson's disease vary in their profiles of engaging in social self-management practices in daily living, and this variability relates to severity of symptoms and health quality of life.Learning how to identify health-centered social self-management practices may help people with Parkinson's disease to focus on the healthfulness of their own practices.Learning how to strategically engage one's social resources as part of self-care may help people with Parkinson's disease to master managing their health and well-being in daily life.

Emotional cues from expressive behavior of women and men with Parkinson's disease

OBJECTIVE

Emotional experience of people with Parkinson's disease is prone to being misunderstood by observers and even healthcare practitioners, which affects treatment effectiveness and makes clients suffer distress in their social lives. This study was designed to identify reliable emotional cues from expressive behavior in women and men with Parkinson's disease.

METHOD

Videotaped expressive behavior of 96 participants during an interview of discussing enjoyable events was rated using the Interpersonal Communication Rating Protocol. Indices from emotional measures were represented in three components. Correlational analyses between expressive behavior domains and emotional components were conducted for the total sample and by gender separately.

RESULTS

More gross motor expressivity and smiling/laughing indicated more positive affect in the total sample. Less conversational engagement indicated more negative affect in women. However, women with more negative affect and depression appeared to smile and laugh more.

CONCLUSION

This study identified reliable cues from expressive behavior that could be used for assessment of emotional experience in people with Parkinson's disease. For women, because smiling/laughing may convey two possible meanings, that is, more positive and more negative affect, this cue needs to be interpreted cautiously and be used for detecting the intensity, not the type, of emotional experience. Healthcare practitioners should be sensitive to valid cues to make an accurate evaluation of emotion in people with Parkinson's disease.