Detecting Depression Through Gait Data: Examining the Contribution of Gait Features in Recognizing Depression

Repeated social defeat stress differently affects arthritis-associated hypersensitivity in male and female mice

Chronic stress enhances the risk of neuropsychiatric disorders and contributes to the aggravation and chronicity of pain. The development of stress-associated diseases, including pain, is affected by individual vulnerability or resilience to stress, although the mechanisms remain elusive. We used the repeated social defeat stress model promoting susceptible and resilient phenotypes in male and female mice and induced knee mono-arthritis to investigate the impact of stress vulnerability on pain and immune system regulation. We analyzed different pain-related behaviors, measured blood cytokine and immune cell levels, and performed histological analyses at the knee joints and pain/stress-related brain areas. Stress susceptible male and female mice showed prolonged arthritis-associated hypersensitivity. Interestingly, hypersensitivity was exacerbated in male but not female mice. In males, stress promoted transiently increased neutrophils and Ly6Chigh monocytes, lasting longer in susceptible than resilient mice. While resilient male mice displayed persistently increased levels of the anti-inflammatory interleukin (IL)-10, susceptible mice showed increased levels of the pro-inflammatory IL-6 at the early- and IL-12 at the late arthritis stage. Although joint inflammation levels were comparable among groups, macrophage and neutrophil infiltration was higher in the synovium of susceptible mice. Notably, only susceptible male mice, but not females, presented microgliosis and monocyte infiltration in the prefrontal cortex at the late arthritis stage. Blood Ly6Chigh monocyte depletion during the early inflammatory phase abrogated late-stage hypersensitivity and the associated histological alterations in susceptible male mice. Thus, recruitment of blood Ly6Chigh monocytes during the early arthritis phase might be a key factor mediating the persistence of arthritis pain in susceptible male mice. Alternative neuro-immune pathways that remain to be explored might be involved in females.

Associations of depressive symptoms with lower extremity function and balance in Korean older adults

OBJECTIVES

The relationship of depressive symptoms to lower extremity function and balance, especially in older adults without a depression diagnosis, remains unclear. Therefore, our study analyzed this relationship using a large sample of Korean older adults.

METHODS

We used data from the Korean National Health Insurance Service's Health Screening Program database. Individuals aged 66 years who had undergone the National Screening Program for Transitional Ages in Korea and were without a diagnosis of depressive disorder were included. The lower extremity function and balance were evaluated using 2 physical tests, while depressive symptoms were assessed using a 3-question survey. Multivariable-adjusted logistic regression analysis was used to examine the association between depressive symptoms and lower extremity function and balance.

RESULTS

Among 66,041 individuals, those with depressive symptoms showed significantly higher rates of abnormal lower extremity function and abnormal balance. The adjusted odds ratios (aORs) and 95% confidence intervals (CIs) for the association of depressive symptoms to abnormal lower extremity function and abnormal balance were (aOR, 1.34; 95% CI, 1.25 to 1.44) and (aOR, 1.38; 95% CI, 1.29 to 1.48), respectively. Assessment of the relationship based on depressive symptom scores revealed that higher scores were associated with higher aORs (p for trend <0.001). Subgroup analyses further confirmed this relationship, especially among patients with cerebrovascular disease or dementia.

CONCLUSIONS

This study revealed an association between depressive symptoms and the abnormal lower extremity function and balance of 66-year-old individuals without a diagnosis of depressive disorder.

Systematic evaluation of a predator stress model of depression in mice using a hierarchical 3D-motion learning framework

Investigation of the neurobiology of depression in humans depends on animal models that attempt to mimic specific features of the human disorder. However, frequently-used paradigms based on social stress cannot be easily applied to female mice which has led to a large sex bias in preclinical studies of depression. Furthermore, most studies focus on one or only a few behavioral assessments, with time and practical considerations prohibiting a comprehensive evaluation. In this study, we demonstrate that predator stress effectively induced depression-like behaviors in both male and female mice. By comparing predator stress and social defeat models, we observed that the former elicited a higher level of behavioral despair and the latter elicited more robust social avoidance. Furthermore, the use of machine learning (ML)-based spontaneous behavioral classification can distinguish mice subjected to one type of stress from another, and from non-stressed mice. We show that related patterns of spontaneous behaviors correspond to depression status as measured by canonical depression-like behaviors, which illustrates that depression-like symptoms can be predicted by ML-classified behavior patterns. Overall, our study confirms that the predator stress induced phenotype in mice is a good reflection of several important aspects of depression in humans and illustrates that ML-supported analysis can simultaneously evaluate multiple behavioral alterations in different animal models of depression, providing a more unbiased and holistic approach for the study of neuropsychiatric disorders.

Gait disorders in unipolar and bipolar depression

Objectives

Bipolar and unipolar depressions have a similar clinical picture, but different neurological and psychological mechanisms. These misleading similarities can lead to overdiagnosis and increased suicide risk. Recent studies show that gait is a sensitive objective marker for distinguishing the type of depression. The present study aims to compare psychomotor reactivity disorders and gait activity in unipolar and bipolar depression.

Methods

A total of 636 people aged 40.7 ± 11.2 years are studied with an ultrasound cranio-corpo-graph. They are divided into three groups - patients with unipolar depression, with bipolar depression and healthy controls. Each person performs three psychomotor tasks - a classic Unterberger task, a simplified version with open eyes and a complex version with an additional cognitive task.

Results

We find significant differences in psychomotor activity and reactivity between the three groups. Bipolar patients have more inhibited psychomotor skills than unipolar and they are both more inhibited than the norms. The simplified variant of the equilibriometric task is the most sensitive one and psychomotor reactivity is a more precise marker than psychomotor activity.

Conclusion

Both psychomotor activity and reactivity in gait could be sensitive markers for distinguishing similar psychiatric conditions. The application of the cranio-corpo-graph and the possible development of similar devices could lead to new diagnostic and therapeutic approaches, including early detection and prediction of the type of depression.

Artificial intelligence assisted tools for the detection of anxiety and depression leading to suicidal ideation in adolescents: a review

Epidemiological studies report high levels of anxiety and depression amongst adolescents. These psychiatric conditions and complex interplays of biological, social and environmental factors are important risk factors for suicidal behaviours and suicide, which show a peak in late adolescence and early adulthood. Although deaths by suicide have fallen globally in recent years, suicide deaths are increasing in some countries, such as the US. Suicide prevention is a challenging global public health problem. Currently, there aren't any validated clinical biomarkers for suicidal diagnosis, and traditional methods exhibit limitations. Artificial intelligence (AI) is budding in many fields, including in the diagnosis of medical conditions. This review paper summarizes recent studies (past 8 years) that employed AI tools for the automated detection of depression and/or anxiety disorder and discusses the limitations and effects of some modalities. The studies assert that AI tools produce promising results and could overcome the limitations of traditional diagnostic methods. Although using AI tools for suicidal ideation exhibits limitations, these are outweighed by the advantages. Thus, this review article also proposes extracting a fusion of features such as facial images, speech signals, and visual and clinical history features from deep models for the automated detection of depression and/or anxiety disorder in individuals, for future work. This may pave the way for the identification of individuals with suicidal thoughts.

Associations Between Depression Symptom Severity and Daily-Life Gait Characteristics Derived From Long-Term Acceleration Signals in Real-World Settings: Retrospective Analysis

BACKGROUND

Gait is an essential manifestation of depression. However, the gait characteristics of daily walking and their relationships with depression have yet to be fully explored.

OBJECTIVE

The aim of this study was to explore associations between depression symptom severity and daily-life gait characteristics derived from acceleration signals in real-world settings.

METHODS

We used two ambulatory data sets (N=71 and N=215) with acceleration signals collected by wearable devices and mobile phones, respectively. We extracted 12 daily-life gait features to describe the distribution and variance of gait cadence and force over a long-term period. Spearman coefficients and linear mixed-effects models were used to explore the associations between daily-life gait features and depression symptom severity measured by the 15-item Geriatric Depression Scale (GDS-15) and 8-item Patient Health Questionnaire (PHQ-8) self-reported questionnaires. The likelihood-ratio (LR) test was used to test whether daily-life gait features could provide additional information relative to the laboratory gait features.

RESULTS

Higher depression symptom severity was significantly associated with lower gait cadence of high-performance walking (segments with faster walking speed) over a long-term period in both data sets. The linear regression model with long-term daily-life gait features (R2=0.30) fitted depression scores significantly better (LR test P=.001) than the model with only laboratory gait features (R2=0.06).

CONCLUSIONS

This study indicated that the significant links between daily-life walking characteristics and depression symptom severity could be captured by both wearable devices and mobile phones. The daily-life gait patterns could provide additional information for predicting depression symptom severity relative to laboratory walking. These findings may contribute to developing clinical tools to remotely monitor mental health in real-world settings.

Clinical Targets and Attitudes Toward Implementing Digital Health Tools for Remote Measurement in Treatment for Depression: Focus Groups With Patients and Clinicians

BACKGROUND

Remote measurement technologies, such as smartphones and wearable devices, can improve treatment outcomes for depression through enhanced illness characterization and monitoring. However, little is known about digital outcomes that are clinically meaningful to patients and clinicians. Moreover, if these technologies are to be successfully implemented within treatment, stakeholders' views on the barriers to and facilitators of their implementation in treatment must be considered.

OBJECTIVE

This study aims to identify clinically meaningful targets for digital health research in depression and explore attitudes toward their implementation in psychological services.

METHODS

A grounded theory approach was used on qualitative data from 3 focus groups of patients with a current diagnosis of depression and clinicians with >6 months of experience with delivering psychotherapy (N=22).

RESULTS

Emerging themes on clinical targets fell into the following two main categories: promoters and markers of change. The former are behaviors that participants engage in to promote mental health, and the latter signal a change in mood. These themes were further subdivided into external changes (changes in behavior) or internal changes (changes in thoughts or feelings) and mapped with potential digital sensors. The following six implementation acceptability themes emerged: technology-related factors, information and data management, emotional support, cognitive support, increased self-awareness, and clinical utility.

CONCLUSIONS

The promoters versus markers of change differentiation have implications for a causal model of digital phenotyping in depression, which this paper presents. Internal versus external subdivisions are helpful in determining which factors are more susceptible to being measured by using active versus passive methods. The implications for implementation within psychotherapy are discussed with regard to treatment effectiveness, service provision, and patient and clinician experience.

Psychomotor semiology in depression: a standardized clinical psychomotor approach

BACKGROUND

Although psychomotor symptoms are associated with the clinical symptomatology of depression, they are rarely assessed and standardized clinical evaluation tools are lacking. Psychomotor retardation is sometimes assessed through direct patient observations by clinicians or through a clinical observation grid, in the absence of a standardized psychomotor assessment. In this pilot study, we evaluated the feasibility of standardized psychomotor examination of patients with major depressive disorder (MDD) and detailed a psychomotor semiology in these patients.

METHODS

We used a standardized psychomotor assessment to examine 25 patients with MDD and 25 age- and sex-matched healthy controls (HC) and compared their psychomotor profiles. Using standardized tests, we assessed muscle tone and posture, gross motor skills, perceptual-motor skills, and body image/organization. Clinical assessments of depressive symptoms (levels of psychomotor retardation, anxiety, and self-esteem) comprised this detailed psychomotor examination.

RESULTS

All participants were examined using the standardized psychomotor assessment. The main results of the psychomotor examination highlighted low body image of MDD participants (p < 0.001). Significant differences between groups were found in passive muscle tone, posture, emotional control, jumping, manual dexterity, walking, and praxis. Among these psychomotor variables, body image, passivity, jumping and rhythm scores predicted an MDD diagnosis.

CONCLUSIONS

Beyond the psychomotor retardation known to be present in MDD patients, this examination revealed an entire psychomotor symptomatology characterized by elevated muscle tone, poor body image associated with poor self-esteem, slowness in global motor skills and manual praxis, and poor rhythmic adaptation. In light of these results, we encourage clinicians to consider using a standardized tool to conduct detailed psychomotor examination of patients with depressive disorders.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT04031937 , 24/07/2019.

Associations of walking impairment with visual impairment, depression, and cognitive function in U.S. older adults: NHANES 2013-2014

BACKGROUND

Walking impairment, a common health problem among older adults, has been linked to poor vision and mental health. This study aimed to investigate the associations of walking impairment with visual impairment, depression, and cognitive function in older adults.

METHODS

A total of 1,489 adults aged 60 years and older who had participated in the National Health and Examination Survey (NHANES) 2013-2014 in the United States were included. Multivariate logistic regression models were used to examine the associations of walking impairment with visual impairment, depression, and four subdomains of cognitive function. Sample weights were used to ensure the generalizability of the results.

RESULTS

Among all the participants (median age = 68 years; 53.7% women), 17.5% reported walking impairment. Walking impairment was significantly associated with visual impairment (adjusted odds ratio [aOR] = 2.76; 95% CI: 1.47-5.20) and depression (aOR = 4.66; 95% CI: 3.11-6.99). Walking impairment was only associated with the Digit Symbol Substitution (DSST) subdomain of cognitive function in total participants (aOR = 0.97; 95% CI: 0.95-0.99) and in non-Hispanic white adults (aOR = 0.96; 95% CI: 0.94-0.98). Participants with two or three impairment indicators had a higher OR of walking impairment (aOR = 3.64, 95% CI = 2.46-5.38) than those with 0-1 (reference group) impairment indicator.

CONCLUSIONS

Walking impairment was associated with visual impairment, depression, and cognitive impairment in American older adults and also positively associated with the number of impairment indicators. The association between walking impairment and cognitive impairment varied according to race. Evaluations of vision, cognition, and depression should be conducted among older adults with walking impairment, and the needs of older adults should be provided in the evaluations alongside information on the biological aspects of their particular race.

Integrated Equipment for Parkinson’s Disease Early Detection Using Graph Convolution Network

There is an increasing need to diagnose Parkinson’s disease (PD) in an early stage. Existing solutions mainly focused on traditional ways such as MRI, thus suffering from the ease-of-use issue. This work presents a new approach using video and skeleton-based techniques to solve this problem. In this paper, an end-to-end Parkinson’s disease early diagnosis method based on graph convolution networks is proposed, which takes patients’ skeletons sequence as input and returns the diagnosis result. The asymmetric dual-branch network architecture is designed to process global and local information separately and capture the subtle manifestation of PD. To train the network, we present the first Parkinson’s disease gait dataset, PD-Walk. This dataset consists of 95 PD patients and 96 healthy people’s walking videos. All the data are annotated by experienced doctors. Furthermore, we implement our method on portable equipment, which has been in operation in the First Affiliated Hospital, Zhejiang University School of Medicine. Experiments show that our method can achieve 84.1% accuracy and achieve real-time performance on the equipment in the real environment. Compared with traditional solutions, the proposed method can detect suspicious PD symptoms quickly and conveniently. Integrated equipment can be easily placed in hospitals or nursing homes to provide services for elderly people.

Mental states and personality based on real-time physical activity and facial expression recognition

INTRODUCTION

To explore a quick and non-invasive way to measure individual psychological states, this study developed interview-based scales, and multi-modal information was collected from 172 participants.

METHODS

We developed the Interview Psychological Symptom Inventory (IPSI) which eventually retained 53 items with nine main factors. All of them performed well in terms of reliability and validity. We used optimized convolutional neural networks and original detection algorithms for the recognition of individual facial expressions and physical activity based on Russell's circumplex model and the five factor model.

RESULTS

We found that there was a significant correlation between the developed scale and the participants' scores on each factor in the Symptom Checklist-90 (SCL-90) and Big Five Inventory (BFI-2) [r = (-0.257, 0.632), p < 0.01]. Among the multi-modal data, the arousal of facial expressions was significantly correlated with the interval of validity (p < 0.01), valence was significantly correlated with IPSI and SCL-90, and physical activity was significantly correlated with gender, age, and factors of the scales.

DISCUSSION

Our research demonstrates that mental health can be monitored and assessed remotely by collecting and analyzing multimodal data from individuals captured by digital tools.

Qigong Training Positively Impacts Both Posture and Mood in Breast Cancer Survivors With Persistent Post-surgical Pain: Support for an Embodied Cognition Paradigm

Theories of embodied cognition hypothesize interdependencies between psychological well-being and physical posture. The purpose of this study was to assess the feasibility of objectively measuring posture, and to explore the relationship between posture and affect and other patient centered outcomes in breast cancer survivors (BCS) with persistent postsurgical pain (PPSP) over a 12-week course of therapeutic Qigong mind-body training. Twenty-one BCS with PPSP attended group Qigong training. Clinical outcomes were pain, fatigue, self-esteem, anxiety, depression, stress and exercise self-efficacy. Posture outcomes were vertical spine and vertical head angles in the sagittal plane, measured with a 3D motion capture system in three conditions: eyes open (EO), eyes open relaxed (EOR) and eyes closed (EC). Assessments were made before and after the Qigong training. The association between categorical variables (angle and mood) was measured by Cramer's V. In the EO condition, most participants who improved in fatigue and anxiety scales also had better vertical head values. For the EOR condition, a moderate correlation was observed between changes in vertical head angle and changes in fatigue scale. In the EC condition, most of the participants who improved in measures of fatigue also improved vertical head angle. Additionally, pain severity decreased while vertical spine angle improved. These preliminary findings support that emotion and other patient centered outcomes should be considered within an embodied framework, and that Qigong may be a promising intervention for addressing biopsychosocially complex interventions such as PPSP in BCSs.