2020
DOI: 10.1007/s40473-020-00215-4
|View full text |Cite
|
Sign up to set email alerts
|

Digital Phenotyping Using Multimodal Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
14
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 23 publications
(14 citation statements)
references
References 69 publications
0
14
0
Order By: Relevance
“…Often referred to as “digital phenotyping” 21 within the emerging framework of precision psychiatry, the multimodal nature of passive data obtained from consumer grade devices offers a means to understand the lived experiences of mental health in context 22 . For example, GPS data have recently offered insights into the relationship between reduced mobility and poorer mental health during the COVID‐19 pandemic 23 .…”
Section: Tools and Technologiesmentioning
confidence: 99%
“…Often referred to as “digital phenotyping” 21 within the emerging framework of precision psychiatry, the multimodal nature of passive data obtained from consumer grade devices offers a means to understand the lived experiences of mental health in context 22 . For example, GPS data have recently offered insights into the relationship between reduced mobility and poorer mental health during the COVID‐19 pandemic 23 .…”
Section: Tools and Technologiesmentioning
confidence: 99%
“…Modalities are characterized by unique statistical properties, noise levels, and correlations to prediction variables, which necessitate consideration when combined in a model. It remains an open question which ML architectures can best represent nuanced multimodal human behavioral data 24 . One approach is to model all modalities together as one input, but this requires at least five training examples per feature dimension 25 .…”
Section: Introductionmentioning
confidence: 99%
“…This awareness is widely used during the assessment of the disorders, and is increasingly investigated through automated voice and content analysis [3][4][5][6][7] . The combination of new powerful forms of machine learning, pervasive smartphone data collection, and other sources of big data will allegedly identify historically elusive markers for affective and psychotic disorders and therefore enable more reliable diagnoses, continuous evaluation of symptoms, and perhaps even personalized treatment [8][9][10][11][12] . However, communication is a complex phenomenon and its relation to specific disorders is not straightforward, with many potential confounders and ethical considerations 6,13,14 .…”
Section: The Confounding Role Of Medications On Communication-related...mentioning
confidence: 99%