Predicting anxiety state using smartphone-based passive sensing

Yusuke Fukazawa, Taku Ito, Tsukasa Okimura, Yuichi Yamashita, Takaki Maeda, Jun Ota

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This study predicts the change of stress levels using real-world and online behavioral features extracted from smartphone log information. Previous studies of stress detection using smartphone data focused on a single feature and did not consider all features simultaneously. We propose a method to extract a co-occurring combination of a user's real-world and online behavioral features by converting raw sensor data into categorical features. We conducted an experiment in which the State Trait Anxiety Inventory (STAI) was used to assess the anxiety-related stress levels of 20 healthy participants. The participants installed a log-collecting application on their smartphones and answered the STAI questions once a day for one month. The proposed method showed an F-score of 74.2%, which is 4.0% higher than the F-score of previous studies (70.2%) that used single non-combined features. The results demonstrate that anxiety-related stress levels can be predicted using combined features extracted from smartphone log data.

Original languageEnglish
Article number103151
JournalJournal of Biomedical Informatics
Volume93
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Smartphones
Anxiety
Equipment and Supplies
Healthy Volunteers
Smartphone
Sensors
Experiments

Keywords

  • Anxiety
  • Machine learning
  • Smartphone

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Predicting anxiety state using smartphone-based passive sensing. / Fukazawa, Yusuke; Ito, Taku; Okimura, Tsukasa; Yamashita, Yuichi; Maeda, Takaki; Ota, Jun.

In: Journal of Biomedical Informatics, Vol. 93, 103151, 01.05.2019.

Research output: Contribution to journalArticle

Fukazawa, Yusuke ; Ito, Taku ; Okimura, Tsukasa ; Yamashita, Yuichi ; Maeda, Takaki ; Ota, Jun. / Predicting anxiety state using smartphone-based passive sensing. In: Journal of Biomedical Informatics. 2019 ; Vol. 93.
@article{0c92699fd3bb46dcbe9db6843d102ba6,
title = "Predicting anxiety state using smartphone-based passive sensing",
abstract = "This study predicts the change of stress levels using real-world and online behavioral features extracted from smartphone log information. Previous studies of stress detection using smartphone data focused on a single feature and did not consider all features simultaneously. We propose a method to extract a co-occurring combination of a user's real-world and online behavioral features by converting raw sensor data into categorical features. We conducted an experiment in which the State Trait Anxiety Inventory (STAI) was used to assess the anxiety-related stress levels of 20 healthy participants. The participants installed a log-collecting application on their smartphones and answered the STAI questions once a day for one month. The proposed method showed an F-score of 74.2{\%}, which is 4.0{\%} higher than the F-score of previous studies (70.2{\%}) that used single non-combined features. The results demonstrate that anxiety-related stress levels can be predicted using combined features extracted from smartphone log data.",
keywords = "Anxiety, Machine learning, Smartphone",
author = "Yusuke Fukazawa and Taku Ito and Tsukasa Okimura and Yuichi Yamashita and Takaki Maeda and Jun Ota",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.jbi.2019.103151",
language = "English",
volume = "93",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Predicting anxiety state using smartphone-based passive sensing

AU - Fukazawa, Yusuke

AU - Ito, Taku

AU - Okimura, Tsukasa

AU - Yamashita, Yuichi

AU - Maeda, Takaki

AU - Ota, Jun

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This study predicts the change of stress levels using real-world and online behavioral features extracted from smartphone log information. Previous studies of stress detection using smartphone data focused on a single feature and did not consider all features simultaneously. We propose a method to extract a co-occurring combination of a user's real-world and online behavioral features by converting raw sensor data into categorical features. We conducted an experiment in which the State Trait Anxiety Inventory (STAI) was used to assess the anxiety-related stress levels of 20 healthy participants. The participants installed a log-collecting application on their smartphones and answered the STAI questions once a day for one month. The proposed method showed an F-score of 74.2%, which is 4.0% higher than the F-score of previous studies (70.2%) that used single non-combined features. The results demonstrate that anxiety-related stress levels can be predicted using combined features extracted from smartphone log data.

AB - This study predicts the change of stress levels using real-world and online behavioral features extracted from smartphone log information. Previous studies of stress detection using smartphone data focused on a single feature and did not consider all features simultaneously. We propose a method to extract a co-occurring combination of a user's real-world and online behavioral features by converting raw sensor data into categorical features. We conducted an experiment in which the State Trait Anxiety Inventory (STAI) was used to assess the anxiety-related stress levels of 20 healthy participants. The participants installed a log-collecting application on their smartphones and answered the STAI questions once a day for one month. The proposed method showed an F-score of 74.2%, which is 4.0% higher than the F-score of previous studies (70.2%) that used single non-combined features. The results demonstrate that anxiety-related stress levels can be predicted using combined features extracted from smartphone log data.

KW - Anxiety

KW - Machine learning

KW - Smartphone

UR - http://www.scopus.com/inward/record.url?scp=85063516889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063516889&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2019.103151

DO - 10.1016/j.jbi.2019.103151

M3 - Article

C2 - 30880254

AN - SCOPUS:85063516889

VL - 93

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

M1 - 103151

ER -