Skip to main content
SpringerLink
Log in

Identifying digital biomarkers in actigraph based sequential motor activity data for assessment of depression: a model evaluating SVM in LSTM extracted feature space

  • Original Research
  • Published:
International Journal of Information Technology Aims and scope Submit manuscript

Abstract

This research puts forward a methodology for depression assessment using actigraph recordings of motor activity. High level features of motor activity are extracted using Long-Short Term Memory (LSTM) which are paired with statistical features to deliver valuable digital biomarkers. Overlapping sliding window is used to input sequences into LSTM to capture superior features in activity recordings. The predictive ability of these digital biomarkers is evaluated using Support Vector Machine (SVM). The hybrid framework is validated on benchmark, Depresjon dataset and achieves accuracy of 95.57%. Effectiveness of overlapping sliding window and statistical features is evaluated, and their significance is validated. It is validated that the concept of overlapping sliding window improves performance accuracy by 3.51% and the use of discriminative statistical features improves model performance by 1.08%. It is concluded that the proposed methodology based on feature extraction, statistical features and overlapping sliding window outperforms state-of-the-art techniques as well as baseline deep learning algorithms for depression detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Pandey S, Sharma S, Wazir S (2022) Mental healthcare chatbot based on natural language processing and deep learning approaches: ted the therapist. Int J Inf Technol 14:3757–3766.

  2. Arora A, Chakraborty P, Bhatia MPS (2022) Intervention of wearables and smartphones in real time monitoring of sleep and behavioral health: an assessment using adaptive neuro-fuzzy technique. Arab J Sci Eng 47(2):1999–2024

    Article  Google Scholar 

  3. Kumar A, Sharma K, Sharma A (2021) Hierarchical deep neural network for mental stress state detection using IoT based biomarkers. Pattern Recognit Lett 145:81–87

    Article  Google Scholar 

  4. Kumar A, Sharma A, Arora A (2019) Anxious depression prediction in real-time social data. arXiv preprint. arXiv:1903.10222

  5. Yamin M (2018) IT applications in healthcare management: a survey. Int J Inform Technol 10(4):503–509

    Article  Google Scholar 

  6. Bahbouh NM, Compte SS, Valdes JV, Sen AAA (2022) An empirical investigation into the altering health perspectives in the internet of health things. Int J Inf Technol 15:67–77.

  7. Lou Z, Wang L, Jiang K, Wei Z, Shen G (2020) Reviews of wearable healthcare systems: materials, devices and system integration. Mater Sci Eng 140:100523

    Article  Google Scholar 

  8. Papa A, Mital M, Pisano P, Del Giudice M (2020) E-health and wellbeing monitoring using smart healthcare devices: an empirical investigation. Technol Forecast Soc Chang 153:119226

    Article  Google Scholar 

  9. Sasaki JE, John D, Freedson PS (2011) Validation and comparison of ActiGraph activity monitors. J Sci Med Sport 14(5):411–416

    Article  Google Scholar 

  10. Thakur D, Biswas S (2021) Feature fusion using deep learning for smartphone based human activity recognition. Int J Inform Technol 13(4):1615–1624

    Article  Google Scholar 

  11. Dzieżyc M, Gjoreski M, Kazienko P, Saganowski S, Gams M (2020) Can we ditch feature engineering? End-to-end deep learning for affect recognition from physiological sensor data. Sensors 20(22):6535

    Article  Google Scholar 

  12. Jakobsen P, Garcia-Ceja E, Riegler M, Stabell LA, Nordgreen T, Torresen J et al (2020) Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls. Plos One 15(8):e0231995

    Article  Google Scholar 

  13. Rodríguez-Ruiz JG, Galván-Tejada CE, Zanella-Calzada LA, Celaya-Padilla JM, Galván-Tejada JI, Gamboa-Rosales H, Soto-Murillo MA et al (2020) Comparison of night, day and 24 h motor activity data for the classification of depressive episodes. Diagnostics 10(3):162

    Article  Google Scholar 

  14. Burton C, McKinstry B, Tătar AS, Serrano-Blanco A, Pagliari C, Wolters M (2013) Activity monitoring in patients with depression: a systematic review. J Affect Disord 145(1):21–28

    Article  Google Scholar 

  15. George SV, Kunkels YK, Booij S, Wichers M (2021) Uncovering complexity details in actigraphy patterns to differentiate the depressed from the non-depressed. Sci Rep 11(1):1–11

    Article  Google Scholar 

  16. Sadeh A, Acebo C (2002) The role of actigraphy in sleep medicine. Sleep Med Rev 6(2):113–124

    Article  Google Scholar 

  17. Bender BG, Leung SB, Leung DY (2003) Actigraphy assessment of sleep disturbance in patients with atopic dermatitis: an objective life quality measure. J Allergy Clin Immunol 111(3):598–602

    Article  Google Scholar 

  18. Arora A, Chakraborty P, Bhatia MPS (2020) Analysis of data from wearable sensors for sleep quality estimation and prediction using deep learning. Arab J Sci Eng 45(12):10793–10812

    Article  Google Scholar 

  19. Leeder J, Glaister M, Pizzoferro K, Dawson J, Pedlar C (2012) Sleep duration and quality in elite athletes measured using wristwatch actigraphy. J Sports Sci 30(6):541–545

    Article  Google Scholar 

  20. Razavi N, Horn H, Koschorke P, Hügli S, Höfle O, Müller T, Walther S et al (2011) Measuring motor activity in major depression: the association between the Hamilton Depression Rating Scale and actigraphy. Psychiatry Res 190(2–3):212–216

    Article  Google Scholar 

  21. Korszun A, Young EA, Engleberg NC, Brucksch CB, Greden JF, Crofford LA (2002) Use of actigraphy for monitoring sleep and activity levels in patients with fibromyalgia and depression. J Psychosom Res 52(6):439–443

    Article  Google Scholar 

  22. Tazawa Y, Liang KC, Yoshimura M, Kitazawa M, Kaise Y, Takamiya A et al (2020) Evaluating depression with multimodal wristband-type wearable device: screening and assessing patient severity utilizing machine-learning. Heliyon 6(2):e03274

    Article  Google Scholar 

  23. Choi JG, Ko I, Han S (2021) Depression level classification using machine learning classifiers based on Actigraphy Data. IEEE Access 9:116622–116646

    Article  Google Scholar 

  24. Raihan M, Bairagi AK, Rahman S (2021) A machine learning based study to predict depression with monitoring Actigraph watch data. In: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT) (pp 1–5). IEEE

  25. Garcia-Ceja E, Riegler M, Jakobsen P, Tørresen J, Nordgreen T, Oedegaard KJ, Fasmer OB (2018) Depresjon: a motor activity database of depression episodes in unipolar and bipolar patients. In: Proceedings of the 9th ACM multimedia systems conference (pp 472–477)

  26. Rodríguez-Ruiz JG, Galván-Tejada CE, Vázquez-Reyes S, Gálvan-Tejada JI, Gamboa-Rosales H (2019) Nighttime depression episodes classification using a formal method: knowledge discovery in databases. In: 2019 7th International Conference in Software Engineering Research and Innovation (CONISOFT) (pp 207–212). IEEE

  27. Garcia-Ceja E, Riegler M, Jakobsen P, Torresen J, Nordgreen T, Oedegaard KJ, Fasmer OB (2018) Motor activity based classification of depression in unipolar and bipolar patients. In: 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS) (pp 316–321). IEEE

  28. Kulam S (2019) Time-series classification with uni-dimensional convolutional neural networks: an experimental comparison with long Short-Term Memory Networks (Master’s thesis)

  29. Frogner JI, Noori FM, Halvorsen P, Hicks SA, Garcia-Ceja E, Torresen J, Riegler MA (2019) October One-dimensional convolutional neural networks on motor activity measurements in detection of depression. In: Proceedings of the 4th International Workshop on Multimedia for Personal Health & Health Care (pp 9–15)

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Netaji Subhas University of Technology, New Delhi, India

    Anshika Arora, Pinaki Chakraborty & M. P. S. Bhatia

Authors
  1. Anshika Arora
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pinaki Chakraborty
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. P. S. Bhatia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anshika Arora.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Arora, A., Chakraborty, P. & Bhatia, M.P.S. Identifying digital biomarkers in actigraph based sequential motor activity data for assessment of depression: a model evaluating SVM in LSTM extracted feature space. Int. j. inf. tecnol. 15, 797–802 (2023). https://doi.org/10.1007/s41870-023-01162-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41870-023-01162-5

Keywords

Search

Navigation