Investigating Rhythmicity in App Usage to Predict Depressive Symptoms: Protocol for Personalized Framework Development and Validation Through a Countrywide Study

Overview

Journal JMIR Res Protoc

Publisher JMIR Publications

Specialty General Medicine

Date 2024 Apr 24

PMID 38657238

Authors

Md Sabbir Ahmed

Tanvir Hasan

Salekul Islam

Nova Ahmed

Affiliations

Soon will be listed here.

Abstract

Background: Understanding a student's depressive symptoms could facilitate significantly more precise diagnosis and treatment. However, few studies have focused on depressive symptom prediction through unobtrusive systems, and these studies are limited by small sample sizes, low performance, and the requirement for higher resources. In addition, research has not explored whether statistically significant rhythms based on different app usage behavioral markers (eg, app usage sessions) exist that could be useful in finding subtle differences to predict with higher accuracy like the models based on rhythms of physiological data.

Objective: The main objective of this study is to explore whether there exist statistically significant rhythms in resource-insensitive app usage behavioral markers and predict depressive symptoms through these marker-based rhythmic features. Another objective of this study is to understand whether there is a potential link between rhythmic features and depressive symptoms.

Methods: Through a countrywide study, we collected 2952 students' raw app usage behavioral data and responses to the 9 depressive symptoms in the 9-item Patient Health Questionnaire (PHQ-9). The behavioral data were retrieved through our developed app, which was previously used in our pilot studies in Bangladesh on different research problems. To explore whether there is a rhythm based on app usage data, we will conduct a zero-amplitude test. In addition, we will develop a cosinor model for each participant to extract rhythmic parameters (eg, acrophase). In addition, to obtain a comprehensive picture of the rhythms, we will explore nonparametric rhythmic features (eg, interdaily stability). Furthermore, we will conduct regression analysis to understand the association of rhythmic features with depressive symptoms. Finally, we will develop a personalized multitask learning (MTL) framework to predict symptoms through rhythmic features.

Results: After applying inclusion criteria (eg, having app usage data of at least 2 days to explore rhythmicity), we kept the data of 2902 (98.31%) students for analysis, with 24.48 million app usage events, and 7 days' app usage of 2849 (98.17%) students. The students are from all 8 divisions of Bangladesh, both public and private universities (19 different universities and 52 different departments). We are analyzing the data and will publish the findings in a peer-reviewed publication.

Conclusions: Having an in-depth understanding of app usage rhythms and their connection with depressive symptoms through a countrywide study can significantly help health care professionals and researchers better understand depressed students and may create possibilities for using app usage-based rhythms for intervention. In addition, the MTL framework based on app usage rhythmic features may more accurately predict depressive symptoms due to the rhythms' capability to find subtle differences.

International Registered Report Identifier (irrid): DERR1-10.2196/51540.

References

Xu Y, Su S, Li X, Mansuri A, McCall W, Wang X . Blunted rest-activity circadian rhythm increases the risk of all-cause, cardiovascular disease and cancer mortality in US adults. Sci Rep. 2022; 12(1):20665. PMC: 9712599. DOI: 10.1038/s41598-022-24894-z. View

de Angel V, Lewis S, White K, Oetzmann C, Leightley D, Oprea E . Digital health tools for the passive monitoring of depression: a systematic review of methods. NPJ Digit Med. 2022; 5(1):3. PMC: 8752685. DOI: 10.1038/s41746-021-00548-8. View

Thomas K, Burr R . Circadian research in mothers and infants: how many days of actigraphy data are needed to fit cosinor parameters?. J Nurs Meas. 2009; 16(3):201-6. PMC: 2774919. DOI: 10.1891/1061-3749.16.3.201. View

Hossain M, Ahmmed F, Khandokar L, Rahman S, Hridoy A, Alam Ripa F . Status of psychological health of students following the extended university closure in Bangladesh: Results from a web-based cross-sectional study. PLOS Glob Public Health. 2023; 2(3):e0000315. PMC: 10021959. DOI: 10.1371/journal.pgph.0000315. View

Mitchell J, Quante M, Godbole S, James P, Hipp J, Marinac C . Variation in actigraphy-estimated rest-activity patterns by demographic factors. Chronobiol Int. 2017; 34(8):1042-1056. PMC: 6101244. DOI: 10.1080/07420528.2017.1337032. View

Bingham C, Arbogast B, Guillaume G, Lee J, Halberg F . Inferential statistical methods for estimating and comparing cosinor parameters. Chronobiologia. 1982; 9(4):397-439. View

Rykov Y, Thach T, Bojic I, Christopoulos G, Car J . Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling. JMIR Mhealth Uhealth. 2021; 9(10):e24872. PMC: 8576601. DOI: 10.2196/24872. View

Kroenke K, Spitzer R, Williams J . The PHQ-9: validity of a brief depression severity measure. J Gen Intern Med. 2001; 16(9):606-13. PMC: 1495268. DOI: 10.1046/j.1525-1497.2001.016009606.x. View

Tseng V, Sano A, Ben-Zeev D, Brian R, Campbell A, Hauser M . Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia. Sci Rep. 2020; 10(1):15100. PMC: 7492221. DOI: 10.1038/s41598-020-71689-1. View

10.

Moskon M . CosinorPy: a python package for cosinor-based rhythmometry. BMC Bioinformatics. 2020; 21(1):485. PMC: 7597035. DOI: 10.1186/s12859-020-03830-w. View

11.

Quante M, Mariani S, Weng J, Marinac C, Kaplan E, Rueschman M . Zeitgebers and their association with rest-activity patterns. Chronobiol Int. 2018; 36(2):203-213. PMC: 6492024. DOI: 10.1080/07420528.2018.1527347. View

12.

Coyne J, Schwenk T . Nondetection of depression by primary care physicians reconsidered. Gen Hosp Psychiatry. 1995; 17(1):3-12. DOI: 10.1016/0163-8343(94)00056-j. View

13.

Andaur Navarro C, Damen J, Takada T, Nijman S, Dhiman P, Ma J . Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review. BMJ. 2021; 375:n2281. PMC: 8527348. DOI: 10.1136/bmj.n2281. View

14.

Murnane E, Abdullah S, Matthews M, Kay M, Kientz J, Choudhury T . Mobile Manifestations of Alertness: Connecting Biological Rhythms with Patterns of Smartphone App Use. MobileHCI. 2019; 2016:465-477. PMC: 6436843. DOI: 10.1145/2935334.2935383. View

15.

Anderson S, FitzGerald G . Sexual dimorphism in body clocks. Science. 2020; 369(6508):1164-1165. DOI: 10.1126/science.abd4964. View

16.

Esaki Y, Obayashi K, Saeki K, Fujita K, Iwata N, Kitajima T . Association between circadian activity rhythms and mood episode relapse in bipolar disorder: a 12-month prospective cohort study. Transl Psychiatry. 2021; 11(1):525. PMC: 8514471. DOI: 10.1038/s41398-021-01652-9. View

17.

Masubuchi S, Hashimoto S, Endo T, Honma S, Honma K . Amplitude reduction of plasma melatonin rhythm in association with an internal desynchronization in a subject with non-24-hour sleep-wake syndrome. Psychiatry Clin Neurosci. 1999; 53(2):249-51. DOI: 10.1046/j.1440-1819.1999.00535.x. View

18.

Ng K, Sun J, Hu J, Wang F . Personalized Predictive Modeling and Risk Factor Identification using Patient Similarity. AMIA Jt Summits Transl Sci Proc. 2015; 2015:132-6. PMC: 4525240. View

19.

Wang R, Wang W, Dasilva A, Huckins J, Kelley W, Heatherton T . Tracking Depression Dynamics in College Students Using Mobile Phone and Wearable Sensing. Proc ACM Interact Mob Wearable Ubiquitous Technol. 2024; 2(1). PMC: 11501090. DOI: 10.1145/3191775. View

20.

Chowdhury A, Ghosh S, Sanyal D . Bengali adaptation of brief patient health questionnaire for screening depression at primary care. J Indian Med Assoc. 2005; 102(10):544-7. View