2020
DOI: 10.1017/s0033291720002718
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood

Abstract: Background Visual and auditory signs of patient functioning have long been used for clinical diagnosis, treatment selection, and prognosis. Direct measurement and quantification of these signals can aim to improve the consistency, sensitivity, and scalability of clinical assessment. Currently, we investigate if machine learning-based computer vision (CV), semantic, and acoustic analysis can capture clinical features from free speech responses to a brief interview 1 month post-trauma that accurately classi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
40
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 65 publications
(41 citation statements)
references
References 106 publications
0
40
0
1
Order By: Relevance
“…The application of ML in some large-scale omics data is a popular undertaking, such as in cancer genomics (Zhou et al, 2018) and radiomics (Huang et al, 2018;Ding et al, 2019). In the depression-related studies, ML algorithms also have been used to find radiomics (Rubin-Falcone et al, 2018) and video- (Schultebraucks et al, 2020) and audiobased markers (Schultebraucks et al, 2020) for diagnosis or medication prediction. However, unlike cancers, in some studies of peripheral transcriptome biomarkers of MDD, it was difficult to find a relatively credible database such as TCGA (The Cancer Genome Atlas) as an independent validation.…”
Section: Discussionmentioning
confidence: 99%
“…The application of ML in some large-scale omics data is a popular undertaking, such as in cancer genomics (Zhou et al, 2018) and radiomics (Huang et al, 2018;Ding et al, 2019). In the depression-related studies, ML algorithms also have been used to find radiomics (Rubin-Falcone et al, 2018) and video- (Schultebraucks et al, 2020) and audiobased markers (Schultebraucks et al, 2020) for diagnosis or medication prediction. However, unlike cancers, in some studies of peripheral transcriptome biomarkers of MDD, it was difficult to find a relatively credible database such as TCGA (The Cancer Genome Atlas) as an independent validation.…”
Section: Discussionmentioning
confidence: 99%
“…It only takes a little time and almost no cost. So, voice data are an ideal data source for depression screening [ 29 , 30 ].…”
Section: Discussionmentioning
confidence: 99%
“…The potential of human speech patterns in detection and prediction of psychopathology has already been demonstrated in several research works (Cummins et al, 2015;Marmar et al, 2019;Schultebraucks et al, 2020b). Therefore, this section discusses speech features that are the most promising for application in risk assessment of ex-COVID-19 patients.…”
Section: Speech Featuresmentioning
confidence: 99%