Signal Processing and Machine Learning for Mental Health Research and Clinical Applications [Perspectives]

Bone, Daniel; Lee, Chi-Chun; Chaspari, Theodora; Gibson, James; Narayanan, Shrikanth

doi:10.1109/msp.2017.2718581

Cited by 90 publications

(41 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, more recent studies have tried to capitalize on the technological advancements in speech signal processing, and the application of multivariate ML techniques to better capture the complex, multivariate and often non-linear nature of acoustic patterns (Bone et al, 2017;Huys et al, 2016; for an introduction to ML techniques in the context of voice analysis see also the appendix to .…”

Section: Introductionmentioning

confidence: 99%

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Parola

Simonsen

Bliksted

et al. 2019

Preprint

View full text Add to dashboard Cite

Voice atypicalities have been a characteristic feature of schizophrenia since its first definitions. They are often associated with core negative symptoms such as flat affect and alogia, and with the social impairments seen in the disorder. This suggests that voice atypicalities may represent a marker of clinical features and social functioning in schizophrenia. We systematically reviewed and meta-analyzed the evidence for distinctive acoustic patterns in schizophrenia, as well as their relation to clinical features. We identified 46 articles, including 55 studies with a total of 1254 patients with schizophrenia and 699 healthy controls. Summary effect sizes (Hedges'g and Pearson's r) estimates were calculated using multilevel Bayesian modeling. We identified weak atypicalities in pitch variability (g = -0.55) related to flat affect, and stronger atypicalities in proportion of spoken time, speech rate, and pauses (g's between -0.75 and -1.89) related to alogia and flat affect. However, the effects were mostly modest (with the important exception of pause duration) compared to perceptual and clinical judgments, and characterized by large heterogeneity between studies.Moderator analyses revealed that tasks with a more demanding cognitive and social component showed larger effects both in contrasting patients and controls and in assessing symptomatology. In conclusion, studies of acoustic patterns are a promising but, yet unsystematic avenue for establishing markers of schizophrenia. We outline recommendations towards more cumulative, open, and theory-driven research.

show abstract

Section: Introductionmentioning

confidence: 99%

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Parola

Simonsen

Bliksted

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…We will further validate and advance upon the VaDE-based behavior representation framework on an expanded list of dyadic interaction databases. By continuing to develop algorithm in achieving a robust emotion recognition system would contribute to the enabling of the next generation applications in not only humancentered research and development but also create a tangible impact on mental health-related applications [32].…”

Section: Resultsmentioning

confidence: 99%

Encoding Individual Acoustic Features Using Dyad-Augmented Deep Variational Representations for Dialog-level Emotion Recognition

Lee

2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

Face-to-face dyadic spoken dialog is a fundamental unit of human interaction. Despite numerous empirical evidences in demonstrating interlocutor's behavior dependency in dyadic interactions, few technical works exist in leveraging the unique pattern of dynamics in task of advancing emotion recognition during face-to-face settings. In this work, we propose a framework of encoding an individual's acoustic features with dyadaugmented deep networks. The dyad-augmented deep networks includes a general variational deep Gaussian Mixture embedding network and a dyad-specific fine-tuned network. Our framework utilizes the augmented dyad-specific feature space to incorporate the unique behavior pattern emerged when two people interact. We perform dialog-level emotion regression tasks in both the CreativeIT and the NNIME databases. We obtain affect regression accuracy of 0.544 and 0.387 for activation and valence in the CreativeIT database (a relative improvement of 4.41% and 4.03% compared to using features without augmenting the dyad-specific representation), and we obtain 0.700 and 0.604 (4.48% and 4.14% relative improvement) for regressing activation and valence in the NNIME database.

show abstract

“…However examples and opportunities for ML in the mental health context were only briefly discussed (specifically detecting depression using social media and predictive models for classifying psychological conditions), due to the broader aim of this study beyond mental health. A more recent review by Bone et al [4] investigated signal processing and ML for mental health research and clinical applications, concluding that the collaboration of clinicians with data scientists is leading to important scientific breakthroughs not previously possible. However, as this review was not systematic in nature it did not cover the broad scope of applications that exist.…”

Section: Background and Significancementioning

confidence: 99%

Machine learning in mental health: A systematic scoping review of methods and applications

Shatte¹,

Hutchinson²,

Teague³

2018

Preprint

View full text Add to dashboard Cite

ObjectiveThis paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice. Materials and MethodsEight health and information technology research databases were searched using the terms "big data" or "machine learning" and "mental health". Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type and size, and study results. Articles were then synthesised via narrative review. ResultsThree hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health; and, (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's Disease. ML techniques used included support vector machines, decision trees, neural networks, latent dirichlet allocation, and clustering. Discussion and ConclusionOverall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration.With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to improve other areas of psychological functioning. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field. BACKGROUND AND SIGNIFICANCE

show abstract

Signal Processing and Machine Learning for Mental Health Research and Clinical Applications [Perspectives]

Cited by 90 publications

References 17 publications

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Encoding Individual Acoustic Features Using Dyad-Augmented Deep Variational Representations for Dialog-level Emotion Recognition

Machine learning in mental health: A systematic scoping review of methods and applications

Contact Info

Product

Resources

About