» Articles » PMID: 36772625

A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity

Overview
Journal Sensors (Basel)
Publisher MDPI
Specialty Biotechnology
Date 2023 Feb 11
PMID 36772625
Authors
Affiliations
Soon will be listed here.
Abstract

The treatment of mood disorders, which can become a lifelong process, varies widely in efficacy between individuals. Most options to monitor mood rely on subjective self-reports and clinical visits, which can be burdensome and may not portray an accurate representation of what the individual is experiencing. A passive method to monitor mood could be a useful tool for those with these disorders. Some previously proposed models utilized sensors from smartphones and wearables, such as the accelerometer. This study examined a novel approach of processing accelerometer data collected from smartphones only while participants of the open-science branch of the BiAffect study were typing. The data were modeled by von Mises-Fisher distributions and weighted networks to identify clusters relating to different typing positions unique for each participant. Longitudinal features were derived from the clustered data and used in machine learning models to predict clinically relevant changes in depression from clinical and typing measures. Model accuracy was approximately 95%, with 97% area under the ROC curve (AUC). The accelerometer features outperformed the vast majority of clinical and typing features, which suggested that this new approach to analyzing accelerometer data could contribute towards unobtrusive detection of changes in depression severity without the need for clinical input.

Citing Articles

Towards Personalised Mood Prediction and Explanation for Depression from Biophysical Data.

Chatterjee S, Mishra J, Sundram F, Roop P Sensors (Basel). 2024; 24(1).

PMID: 38203024 PMC: 10781272. DOI: 10.3390/s24010164.


Improving Depression Severity Prediction from Passive Sensing: Symptom-Profiling Approach.

Akbarova S, Im M, Kim S, Toshnazarov K, Chung K, Chun J Sensors (Basel). 2023; 23(21).

PMID: 37960563 PMC: 10649076. DOI: 10.3390/s23218866.


Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients.

Lee T, Lee H, Lee J, Kim J Sensors (Basel). 2023; 23(20).

PMID: 37896636 PMC: 10611007. DOI: 10.3390/s23208544.

References
1.
Stange J, Zulueta J, Langenecker S, Ryan K, Piscitello A, Duffecy J . Let your fingers do the talking: Passive typing instability predicts future mood outcomes. Bipolar Disord. 2018; 20(3):285-288. PMC: 5940490. DOI: 10.1111/bdi.12637. View

2.
Bechtel W . Circadian Rhythms and Mood Disorders: Are the Phenomena and Mechanisms Causally Related?. Front Psychiatry. 2015; 6:118. PMC: 4547005. DOI: 10.3389/fpsyt.2015.00118. View

3.
Hidalgo-Mazzei D, Young A, Vieta E, Colom F . Behavioural biomarkers and mobile mental health: a new paradigm. Int J Bipolar Disord. 2018; 6(1):9. PMC: 6161977. DOI: 10.1186/s40345-018-0119-7. View

4.
Zulueta J, Piscitello A, Rasic M, Easter R, Babu P, Langenecker S . Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study. J Med Internet Res. 2018; 20(7):e241. PMC: 6076371. DOI: 10.2196/jmir.9775. View

5.
Victory A, Letkiewicz A, Cochran A . Digital solutions for shaping mood and behavior among individuals with mood disorders. Curr Opin Syst Biol. 2020; 21:25-31. PMC: 7473040. DOI: 10.1016/j.coisb.2020.07.008. View