September 10, 2025Open Access

Digital phenotyping using wearable-determined physical behaviors and machine learning to detect depression and anxiety in a general population

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Digital phenotyping identifies depression and anxiety in a general population using wearable data, highlighting potential physical behavior metrics.

Accuracy of 66%-72% and AUC of 66%-70% were achieved using machine learning models, particularly with random forest.
Physical behavior metrics such as wake up time and activity intensity emerged as key predictors of depression and anxiety.
Participants wore accelerometers for 14 days to collect data, allowing for a comprehensive analysis of physical behaviors.
Findings suggest wearable-derived metrics may effectively differentiate individuals with and without depression and anxiety symptoms.

Sameh et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 10, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Digital phenotyping identifies depression and anxiety in a general population using wearable data, highlighting potential physical behavior metrics.

Accuracy of 66%-72% and AUC of 66%-70% were achieved using machine learning models, particularly with random forest.
Physical behavior metrics such as wake up time and activity intensity emerged as key predictors of depression and anxiety.
Participants wore accelerometers for 14 days to collect data, allowing for a comprehensive analysis of physical behaviors.
Findings suggest wearable-derived metrics may effectively differentiate individuals with and without depression and anxiety symptoms.

Sameh et al. (2025) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark