Head movements during conversational speech in patients with schizophrenia

Leask, Stuart; Park, Bert; Khana, Priya; DiMambro, Ben

doi:10.1177/2045125312464997

Cited by 8 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The logarithm of short-term energy is representative of signal loudness and is calculated on a per frame basis via Eq. 2 below (Low, 2011).…”

Section: Prosodic Features: Log Energymentioning

confidence: 99%

“…The selection of features significantly influences the accuracy of machine learning classifiers. As described in Moore et al (2003Moore et al ( , 2008 and Low (2011), acoustic features are often split into categories and subcategories to determine optimal feature sets. In this study, similar groupings are used and split into prosodic, spectral, cepstral, and TEO-based.…”

Section: Feature Extractionmentioning

confidence: 99%

“…where S(n) is the magnitude of the power spectrum for bin number n, bin center f(n), and N total bins (Low, 2011).…”

Section: Spectral Features: Spectral Centroidmentioning

confidence: 99%

See 2 more Smart Citations

Objective Methods for Reliable Detection of Concealed Depression

et al. 2015

View full text Add to dashboard Cite

Recent research has shown that it is possible to automatically detect clinical depression from audiovisual recordings. Before considering integration in a clinical pathway, a key question that must be asked is whether such systems can be easily fooled. This work explores the potential of acoustic features to detect clinical depression in adults both when acting normally and when asked to conceal their depression. Nine adults diagnosed with mild to moderate depression as per the Beck Depression Inventory (BDI-II) and Patient Health Questionnaire (PHQ, Chang, 2012) were asked a series of questions and to read a excerpt from a novel aloud under two different experimental conditions. In one, participants were asked to act naturally and in the other, to suppress anything that they felt would be indicative of their depression. Acoustic features were then extracted from this data and analyzed using paired t-tests to determine any statistically significant differences between healthy and depressed participants. Most features that were found to be significantly different during normal behavior remained so during concealed behavior. In leave-one-subject-out automatic classification studies of the 9 depressed subjects and 8 matched healthy controls, an 88% classification accuracy and 89% sensitivity was achieved. Results remained relatively robust during concealed behavior, with classifiers trained on only non-concealed data achieving 81% detection accuracy and 75% sensitivity when tested on concealed data. These results indicate there is good potential to build deception-proof automatic depression monitoring systems.

show abstract

“…The logarithm of short-term energy is representative of signal loudness and is calculated on a per frame basis via Eq. 2 below (Low, 2011).…”

Section: Prosodic Features: Log Energymentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Objective Methods for Reliable Detection of Concealed Depression

et al. 2015

View full text Add to dashboard Cite

show abstract

“…intensity of stimulus correlated motion [269,323]. Finally, there might be combinations of case/control status and experimental conditions that interact to induce even more motion as recently reported [316,320].…”

Section: Introductionmentioning

confidence: 81%

“…Importantly, both these methods assume that HM is independent of the trait of interest (e.g., case-control status, or a cognitive or personality measure); thus the HM contribution to the fMRI signal is considered to be solely noise. However, in groups of patients with diseases such as multiple sclerosis or stroke there is increased HM compared to healthy controls [268,316,317], although the evidence is somewhat contradictory for schizophrenia [274,[318][319][320].…”

Section: Introductionmentioning

confidence: 99%

Breaking down the genetics of depression using brain endophenotypes

Couvy‐Duchesne¹

View full text Add to dashboard Cite

The Queensland Brain Institute 2 Thesis AbstractThe objective of the work presented in this thesis was to extend our understanding of depression aetiology and to identify brain MRI endophenotypes of depression. Our work builds on previous research that highlighted the genetic relationships between stress, sex and depression. In addition, MRI measurements are heritable and do not relying on selfreport. As such, they represent promising endophenotypes that could help break down further the genetics of depression.Preliminary work involved reporting depression prevalence in a young adult Australian twin sample (N=2,773) as well as comorbidity with affective and substance use disorders (Chapter 1). In addition, we demonstrated the good psychometric properties of the SPHERE questionnaire, which provides self-reported measures of anxiety-depression and chronic fatigue. Properties of the scores include: i) stochastic ordering on the sum score, ii) limited sex and age bias through adolescence, iii) high internal consistency, iv) good 3 months test-retest, v) moderate heritability, vi) significant association with lifetime MDD, social anxiety and alcohol dependence diagnoses (Chapter 2).In an older sample of Australian twins (N=5,221, Chapter 3), we performed a direct test of the diathesis-stress hypothesis in depression, which states that stressors can mediate the effect of genetic predisposition (diathesis) on the disease risk. We used Polygenic Risk Scores as a measure of diathesis and report a significant interaction with personal stressful life events, supporting the idea that stress and predisposition have a multiplicative effect on the depression liability scale. This interaction may be different between sexes as suggested by the stratified analysis.We then performed 3 analyses of resting-state fMRI from which we showed that: 1) Head motion (HM) is reliable and heritable in addition to being a major confound in fMRI analyses. However, this is unlikely to greatly confound twin studies of resting-state functional connectivity (FC). As a by-product of the analysis we showed that FC in the Broca's areas networks exhibited low to moderate test-retest and heritability (Chapter 4).2) HM is phenotypically and genetically associated with ADHD scores of Inattention and Hyperactivity/Impulsivity. This leads to most head motion image processing options to reduce power and/or to induce a sampling bias in RS-fMRI studies of ADHD. We discussed ways of circumventing this problem, via volume pruning or multivariate analysis (Chapter 5). 33) Nuisance regression (global signal regression, CompCor and HM regression) options in RS-fMRI processing have a moderate impact on the test-retest of regional homogeneity. Independently of the processing options, the low to moderate intra-class coefficients estimated in our sample may be due to insufficient scanning time (5mins 20s) and would impair our statistical power to detect RS-fMRI endophenotypes of depression (Chapter 6).Rather, we focused on structural brain images and contributed sample...

show abstract

Motion energy analysis during speech tasks in medication-naïve individuals with at-risk mental states for psychosis

et al. 2022

View full text Add to dashboard Cite

Movement abnormalities are commonly observed in schizophrenia and at-risk mental states (ARMS) for psychosis. They are usually detected with clinical interviews, such that automated analysis would enhance assessment. Our aim was to use motion energy analysis (MEA) to assess movement during free-speech videos in ARMS and control individuals, and to investigate associations between movement metrics and negative and positive symptoms. Thirty-two medication-naïve ARMS and forty-six healthy control individuals were filmed during speech tasks. Footages were analyzed using MEA software, which assesses movement by differences in pixels frame-by-frame. Two regions of interest were defined—head and torso—and mean amplitude, frequency, and coefficient of variability of movements for them were obtained. These metrics were correlated with the Structured Interview for Prodromal Syndromes (SIPS) symptoms, and with the risk of conversion to psychosis—inferred with the SIPS risk calculator. ARMS individuals had significantly lower mean amplitude of head movement and higher coefficients of movement variability for both head and torso, compared to controls. Higher coefficient of variability was related to higher risk of conversion. Negative correlations were seen between frequency of movement and most SIPS negative symptoms. All positive symptoms were correlated with at least one movement variable. Movement abnormalities could be automatically detected in medication-naïve ARMS subjects by means of a motion energy analysis software. Significant associations of movement metrics with symptoms were found, supporting the importance of movement analysis in ARMS. This could be a potentially important tool for early diagnosis, intervention, and outcome prediction.

show abstract

Head movements during conversational speech in patients with schizophrenia

Abstract: Movement sensors proved well suited to capturing head movements, demonstrating a large effect size in subjects with schizophrenia.

Cited by 8 publications

References 7 publications

Objective Methods for Reliable Detection of Concealed Depression

Objective Methods for Reliable Detection of Concealed Depression

Breaking down the genetics of depression using brain endophenotypes

Motion energy analysis during speech tasks in medication-naïve individuals with at-risk mental states for psychosis

Contact Info

Product

Resources

About