Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Major Depressive Disorder Prediction and Feature Analysis Using Smartwatch Data Based on Ensemble Learning

스마트워치를 활용한 앙상블 학습 기반 우울증 예측 및 특성분석

  • Jaehoon Ko (Department of Biomedical Engineering, Yonsei University) ;
  • Somin Oh (Department of Biomedical Engineering, Yonsei University) ;
  • Erdenebayar Urtnasan (Institute of Yonsei AI Data Convergence Science, Yonsei University Mirae Campus) ;
  • Jaehong Key (Department of Biomedical Engineering, Yonsei University)
  • Received : 2024.10.16
  • Accepted : 2024.12.04
  • Published : 2024.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Major Depressive Disorder is a significant mental health condition triggered by various social and environmental factors. Traditional diagnostic methods for depression primarily rely on subjective assessments, including self-reported surveys and psychiatric consultations, which often lack objectivity and consistency. To address these limitations, this study developed a machine learning-based depression prediction model using ensemble learning techniques and applied SHAP to quantitatively analyze the contribution of individual features to model predictions. The study utilized real-world data collected over three years from 160 participants using smartwatches. To increase the size and diversity of dataset, a segmentation technique was applied resulting in 3,080 independent samples. The dataset included sleep metrics, heart rate, step count, and PHQ-9 survey results. Ensemble learning models were trained and evaluated using metrics such as accuracy, precision, recall, and F1-score. Among these, XGBoost, LightGBM, and CatBoost achieved the highest accuracy of 99.50%. SHAP analysis identified key predictors of depression, with sleep metrics specifically variability in individual sleep duration and average night sleep duration emerging as the most significant contributors across all ensemble learning models. Specifically, night sleep duration, variability in overall sleep states, proportion of Deep sleep during night sleep, variability in REM sleep duration, and proportion of REM sleep during total daily sleep were found to be important features for detection MDD. Future work aims to enhance diagnostic accuracy and robustness by expanding the datasets and feature variables, integrating advanced deep learning, and leveraging explainable AI with wearable device data to enable personalized, early detection and intervention for depression prevention and management.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 및 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2022R1F1A1069516, 2022RIS-005).

References

  1. Koo SK. Depression Status in Korea. Osong Public Health Res Perspect 2018;9(4):141-142. https://doi.org/10.24171/j.phrp.2018.9.4.01
  2. Cheong CY, Park JY, SHIM KH, Kim SY, Kim MS, Fond G, Boyer L, Kang JS, Kim T, Yon DK. National trends in counseling for stress and depression and COVID-19 pandemic related factors among adults, 2009-2022: A nationwide study in South Korea Stress, depression, and pandemic. Psychiatry Research. 2024;337:115919. https://doi.org/10.1016/j.psychres.2024.115919
  3. Huang Y, Zhao N. Generalized anxiety disorder, depressive symptoms and sleep quality during COVID-19 outbreak in China: a web-based cross-sectional survey. Psychiatry Research. 2020;288:112954. https://doi.org/10.1016/j.psychres.2020.112954
  4. Salari N, Hosseinian-Far A, Jalali R, Vaisi-Raygani A, Rasoulpoor S, Mohammadi M, Rasoulpoor S, Khaledi-Paveh B. Prevalence of stress, anxiety, depression among the general population during the COVID-19 pandemic: a systematic review and meta-analysis. Globalization and Health. 2020;16(1). https://doi.org/10.1186/s12992-020-00589-w
  5. Mobram S, Vali M. Depression detection based on linear and nonlinear speech features in I-vector/SVDA framework. Computers in Biology and Medicine. 2022;149:105926. https://doi.org/10.1016/j.compbiomed.2022.105926
  6. Tavares VDO, Schuch FB, de Sousa GM, Hallgren M, Oliveira L, Cabral D, Nóbrega R, Barbosa DC, Almeida VRN, Tinoco H, Lira RA, Hallak JE, Arcoverde E, Cuthbert C, Patten S, Galvão-Coelho NL. Effectiveness of an affect-adjusted, supervised, multimodal, online and home-based exercise group protocol for major depression: a randomized controlled trial. Psychology of Sport and Exercise. 2024;18:102729.
  7. Marx W, Penninx BWJH, Solmi M, Furukawa TA, Firth J, Carvalho AF, Bers M. Major depressive disorder. Nature Reviews Disease Primers. 2023;9(44). https://doi.org/10.1038/s41572-023-00454-1
  8. Sanchez-Villegas A, Schlatter J, Ortuno F, Lahortiga F, Pla J, Benito S, Martinez-Gonzalez MA. Validity of a self-reported diagnosis of depression among participants in a cohort study using the Structured Clinical Interview for DSM-IV (SCID-I). BMC Psychiatry. 2008;8:43. https://doi.org/10.1186/1471-244X-8-43
  9. Craddock N, Mynors-Wallis L. Psychiatric diagnosis: impersonal, imperfect and important. The British Journal of Psychiatry. 2014;204(2):93-95. https://doi.org/10.1192/bjp.bp.113.133090
  10. Smith KM, Renshaw PF, Bilello J. The diagnosis of depression: current and emerging methods. Comprehensive psychiatry. 2013;54(1):1-6. https://doi.org/10.1016/j.comppsych.2012.06.006
  11. Yan B, Xu X, Liu M, Zheng K, Liu J, Li J, Wei L, Zhang B, Lu H, Li B. Quantitative Identification of Major Depression Based on Resting-State Dynamic Functional Connectivity: A Machine Learning Approach. Frontiers in Neuroscience. 2020;14:191. https://doi.org/10.3389/fnins.2020.00191
  12. Fried EI, Nesse RM. Depression sum-scores don't add up: why analyzing specific depression symptoms is essential. BMC Medicine. 2015;13(1):72. https://doi.org/10.1186/s12916-015-0325-4
  13. Cocchi M, Tonello L, Rasenick MM. Human depression: a new approach in quantitative psychiatry. Annals of General Psychiatry. 2010;9(1):25. https://doi.org/10.1186/1744-859X-9-25
  14. Beames JR, Kikas K, Werner-Seidler A. Prevention and early intervention of depression in young people: an integrated narrative review of affective awareness and Ecological Momentary Assessment. BMC Psychology. 2021;9:113. https://doi.org/10.1186/s40359-021-00614-6
  15. Triantafyllidis A, Kondylakis H, Katehakis D, Kouroubali A, Alexiadis A, Segkouli S, Votis K, Tzovaras D. Smartwatch interventions in healthcare: A systematic review of the literature. International Journal of Medical Informatics. 2024;190:105560. https://doi.org/10.1016/j.ijmedinf.2024.105560
  16. Adil M, Atiq I, Younus S. Effectiveness of the Apple Watch as a mental health tracker. Journal of Global Health. 2024 Feb 9;14:03010. https://doi.org/10.7189/jogh.14.03010
  17. Hölzle SS, Reineke T, Hoch S, Roether B, Francis M, Anquez Traxler C, Symma N. Basic Requirements and Framework Conditions of Real-World Data (RWD) on Herbal Medicinal Products. Planta Medica. 2024;90(14):1056-1058. https://doi.org/10.1055/a-2409-3125
  18. Liu F, Panagiotakos D. Real-world data: a brief review of the methods, applications, challenges and opportunities. BMC Medical Research Methodology. 2022;22(1):287. https://doi.org/10.1186/s12874-022-01768-6
  19. Emmert SF, Yang Z, Feng H, Tripathi S, Dehmer M. An Introductory Review of Deep Learning for Prediction Models With Big Data. Frontiers in Artificial Intelligence. 2020;3:4. https://doi.org/10.3389/frai.2020.00004
  20. Yoon KI, Ko DK, Lim SC. Real-time Video Prediction Using GANs with Guidance Information for Time-delayed Robot Teleoperation. International Journal of Control, Automation and Systems. 2023;21(7):2387-2397. https://doi.org/10.1007/s12555-022-0358-3
  21. Oprea S, Martinez-Gonzalez P, Garcia-Garcia A, Castro-Vargas JA, Orts-Escolano S, Garcia-Rodriguez J, Argyros A. A Review on Deep Learning Techniques for Video Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022;44(6):2806-2822. https://doi.org/10.1109/TPAMI.2020.3045007
  22. Geraghty AWA, Santer M, Beavis C, Williams SJ, Kendrick T, Terluin B, Little P, Moore M. 'I mean what is depression?' A qualitative exploration of UK general practitioners' perceptions of distinctions between emotional distress and depressive disorder. BMJ Open. 2019;9. https://doi.org/10.1136/bmjopen-2019-032644
  23. Thériault R, Ben-Shachar MS, Patil I, Lüdecke D, Wiernik BM, Makowski D. Check your outliers! An introduction to identifying statistical outliers in R with easystats. Behavior Research Methods. 2024;56:4162-4172. https://doi.org/10.3758/s13428-024-02356-w
  24. Casares MÁ, Díez-Gómez A, Pérez-Albéniz A, Lucas-Molina B, Fonseca-Pedrero E. Depressive and anxious symptoms in Spanish adolescents: Normative data for the PHQ-9 and GAD-7. Clínica y Salud, 2024;35(2):77-83. https://doi.org/10.5093/clysa2024a13
  25. Jafarzadeh H, Mahdianpari M, Gill E, Mohammadimanesh F, Homayouni S. Bagging and Boosting Ensemble Classifiers for Classification of Multispectral, Hyperspectral and PolSAR Data: A Comparative Evaluation. Remote Sensing. 2021;13(21):4405 https://doi.org/10.3390/rs13214405
  26. Sun Z, Wang G, Li P, Wang H, Zhang M, Liang X. An improved random forest based on the classification accuracy and correlation measurement of decision trees. Expert Systems with Applications. 2024;237:121549. https://doi.org/10.1016/j.eswa.2023.121549
  27. Iranzad R, Liu X. A review of random forest-based feature selection methods for data science education and applications. International Journal of Data Science and Analytics. 2024; Published online 03 February 2024.
  28. Niazkar M, Menapace A, Brentan B, Piraei R, Jimenez D, Dhawan P, Righetti M. Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023). Environmental Modelling & Software. 2024;174:105971. https://doi.org/10.1016/j.envsoft.2024.105971
  29. Truong VH, Tangaramvong S, Papazafeiropoulos G. An efficient LightGBM-based differential evolution method for nonlinear inelastic truss optimization. Expert Systems with Applications. 2024;237:121530. https://doi.org/10.1016/j.eswa.2023.121530
  30. Ahmed U, Khan AR, Mahmood A, Rafiq I, Ghannam R, Zoha A. Short-term global horizontal irradiance forecasting using weather classified categorical boosting. Applied Soft Computing. 2024;155:111441. https://doi.org/10.1016/j.asoc.2024.111441
  31. Shah R, Pawar A, Kumar M. Enhancing Machine Learning Model Using Explainable AI. Advances in Data and Information Sciences. 2024;287-29. https://doi.org/10.1007/978-981-99-6906-7_25