Pupil Diameter and Machine Learning for Depression Detection: a comparative study with deep learning models

• Autorzy: Mohamed Islam , El-Wakad Mohamed , Abbas Khaled , Aboamer Mohamed , Mohamed Nader A. Rahman

Identyfikatory

DOI

10.35784/acs-2024-41

• Języki publikacji: EN

Abstrakty

EN

According to the World Health Organization, the Global Mental Health Report estimated that between 251 and 310 million individuals worldwide experienced depression during the first year of the COVID-19 pandemic. Most methods for detecting depression rely on clinical diagnoses and surveys. However, the American Psychiatric Association reports that over 50% of patients do not receive appropriate treatment. This study aims to utilize machine learning and pupil diameter features to identify depression and evaluate the accuracy of these classifiers in comparison to our previous deep learning model. While limited research has explored the use of pupillary diameter as a classification tool for distinguishing between individuals with and without depression, several studies have focused on EEG signals for this purpose. The study involved 58 participants, with 29 classified as depressed and 29 as healthy. The classification was based on statistical features extracted from the Hilbert-Huang Transform. Results showed a significant improvement in average accuracy compared to the authors’ prior work, with the current study achieving 77.72% accuracy, compared to 64.78% in their previous research. Machine learning methods, particularly Bagging, outperformed deep learning models such as AlexNet when classifying data from the left and right eyes individually (90.91% vs. 78.57% for the left eye; 90.91% vs. 71.43% for the right eye). However, when combining data from both eyes, deep learning using AlexNet demonstrated superior performance (98.28% accuracy compared to 93.75% using Bagging with statistical features from both eyes). Despite the higher accuracy of deep learning, machine learning is recommended for its faster execution times.

Słowa kluczowe

EN

Pupil Diameter; PD; Major Depressive Disorder; MDD; Machine Learning; ML; Hilbert-Huang transform; HHT; Cross-Validation; CV

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2024
• Tom: Vol. 20, no. 4
• Strony: 77--99
• Opis fizyczny: Bibliogr. 43 poz., fig., tab.

Twórcy

autor

Mohamed Islam

• Helwan University, Faculty of Engineering, Biomedical Engineering Department, Cairo, Egypt; Higher Technological Institute, Biomedical Engineering Department, 10th of Ramadan City, Egypt

• https://orcid.org/0009-0001-4408-7190

autor

El-Wakad Mohamed

• Future University, Faculty of Engineering and Technology, Biomedical Engineering Department, New Cairo, Egypt

• https://orcid.org/0000-0003-2637-1048

autor

Abbas Khaled

• Higher Technological Institute, Electronics and Communication Department, 10th Ramadan City, Egypt

• https://orcid.org/0009-0002-0913-4163

autor

Aboamer Mohamed

• Majmaah University, College of Applied Medical Sciences, Medical Equipment Technology Department, Majmaah 11952, Saudi Arabia

• https://orcid.org/0000-0002-4433-776X

autor

Mohamed Nader A. Rahman

• Misr University for Science and Technology, Faculty of Engineering, Biomedical Engineering Department, Giza, Egypt

• https://orcid.org/0000-0001-7680-306X

Bibliografia

• [1] Aboamer, M. A., Azar, A. T., Mohamed, A. S. A., Bär, K.-J., Berger, S., & Wahba, K. (2014). Nonlinear features of heart rate variability in paranoid schizophrenic. Neural Computing and Applications, 25(7), 1535-1555. https://doi.org/10.1007/s00521-014-1621-1
• [2] Anas, E. M. A., Lee, S. Y., & Hasan, M. K. (2010). Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions. BioMedical Engineering OnLine, 9, 43. https://doi.org/10.1186/1475-925X-9-43
• [3] Benvenuto, J., Jin, Y., Casale, M., Lynch, G., & Granger, R. (2002). Identification of diagnostic evoked response potential segments in Alzheimer’s disease. Experimental Neurology, 176(2), 269-276. https://doi.org/10.1006/exnr.2002.7930
• [4] Ding, X., Yue, X., Zheng, R., Bi, C., Li, D., & Yao, G. (2019). Classifying major depression patients and healthy controls using EEG, eye tracking and galvanic skin response data. Journal of Affective Disorders, 251, 156-161. https://doi.org/10.1016/j.jad.2019.03.058
• [5] Drysdale, A. T., Grosenick, L., Downar, J., Dunlop, K., Mansouri, F., Meng, Y., Fetcho, R. N., Zebley, B., Oathes, D. J., Etkin, A., Schatzberg, A. F., Sudheimer, K., Keller, J., Mayberg, H. S., Gunning, F. M., Alexopoulos, G. S., Fox, M. D., Pascual-Leone, A., Voss, H. U., … Liston, C. (2017). Resting-state connectivity biomarkers define neurophysiological subtypes of depression. Nature Medicine, 23, 28-38. https://doi.org/10.1038/nm.4246
• [6] Gregory, J. A. (1985). Shape Preserving Spline Interpolation. NASA. Langley Research Center Computational Geometry and Computer-Aided Design.
• [7] Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N. J., Kern, R., Picus, M., Hoyer, S., van Kerkwijk, M. H., Brett, M., Haldane, A., del Río, J. F., Wiebe, M., Peterson, P., … Oliphant, T. E. (2020). Array programming with NumPy. Nature, 585, 357-362. https://doi.org/10.1038/s41586-020-2649-2
• [8] Huang, N. E., & Attoh-Okine, N. O. (Eds.). (2005). The Hilbert-Huang Transform in Engineering. CRC Press. https://doi.org/10.1201/9781420027532
• [9] Huang, N. E., & Shen, S. S. P. (2005). Hilbert-huang Transform And Its Applications. World Scientific. https://doi.org/10.1142/5862
• [10] Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., Yen, N.-C., Tung, C. C., & Liu, H. H. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971), 903-995. https://doi.org/10.1098/rspa.1998.0193
• [11] Ismail, I., El-Wakad, M. T., Shafie, K. A., Aboamer, M. A., & Mohamed, N. A. R. (2024). Major depressive disorder: Early detection using deep learning and pupil diameter. Indonesian Journal of Electrical Engineering and Computer Science, 35(2), 916-932. https://doi.org/10.11591/ijeecs.v35.i2.pp916-932
• [12] Jones, N. P., Siegle, G. J., & Mandell, D. (2015). Motivational and emotional influences on cognitive control in depression: A pupillometry study. Cognitive, Affective, & Behavioral Neuroscience, 15, 263-275. https://doi.org/10.3758/s13415-014-0323-6
• [13] Junsheng, C., Dejie, Y., & Yu, Y. (2006). Research on the intrinsic mode function (IMF) criterion in EMD method. Mechanical Systems and Signal Processing, 20(4), 817-824. https://doi.org/10.1016/j.ymssp.2005.09.011
• [14] Kamel, M. S., & Selim, S. Z. (1994). A relaxation approach to the fuzzy clustering problem. Fuzzy Sets and Systems, 61(2), 177-188. https://doi.org/10.1016/0165-0114(94)90232-1
• [15] Kowalski, P., & Smyk, R. (2018). Review and comparison of smoothing algorithms for one-dimensional data noise reduction. 2018 International Interdisciplinary PhD Workshop (IIPhDW) (pp. 277-281). IEEE. https://doi.org/10.1109/IIPHDW.2018.8388373
• [16] Kramarić, K., Šapina, M., Garcin, M., Milas, K., Pirić, M., Brdarić, D., Lukić, G., Milas, V., & Pušeljić, S. (2019). Heart rate asymmetry as a new marker for neonatal stress. Biomedical Signal Processing and Control, 47, 219-223. https://doi.org/10.1016/j.bspc.2018.08.027
• [17] Lendasse, A., Wertz, V., & Verleysen, M. (2003). Model selection with cross-validations and bootstraps-application to time series prediction with RBFN models. In O. Kaynak, E. Alpaydin, E. Oja, & L. Xu (Eds.), Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP 2003 (pp. 573-580). Springer. https://doi.org/10.1007/3-540-44989-2_68
• [18] Li, M., Cao, L., Zhai, Q., Li, P., Liu, S., Li, R., Feng, L., Wang, G., Hu, B., & Lu, S. (2020). Method of depression classification based on behavioral and physiological signals of eye movement. Wiley Online Library, 2020(1), 4174857. https://doi.org/10.1155/2020/4174857
• [19] Li, W., Ma, H., Wang, X., & Shi, D. (2014). Features Derived from Behavioral Experiments to Distinguish Mental Healthy People from Depressed People. Biomedical Engineering / 817: Robotics Applications. https://doi.org/10.2316/P.2014.818-021
• [20] Mao, J., & Jain, A. K. (1996). A self-organizing network for hyperellipsoidal clustering (HEC). IEEE Transactions on Neural Networks, 7(1), 16-29. https://doi.org/10.1109/72.478389
• [21] Newson, J. J., & Thiagarajan, T. C. (2019). EEG frequency bands in psychiatric disorders: A review of resting state studies. Frontiers in Human Neuroscience, 12. https://doi.org/10.3389/fnhum.2018.00521
• [22] Schultebraucks, K., Yadav, V., Shalev, A. Y., Bonanno, G. A., & Galatzer-Levy, I. R. (2022). Deep Learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood. Psychological Medicine, 52(5), 957-967. https://doi.org/10.1017/S0033291720002718
• [23] Schumann, A., Kralisch, C., & Bär, K.-J. (2015). Spectral decomposition of pupillary unrest using wavelet entropy. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6154-6157). IEEE. https://doi.org/10.1109/EMBC.2015.7319797
• [24] Selim, S. Z., & Alsultan, K. (1991). A simulated annealing algorithm for the clustering problem. Pattern Recognition, 24(10), 1003-1008. https://doi.org/10.1016/0031-3203(91)90097-O
• [25] Shen, R., Zhan, Q., Wang, Y., & Ma, H. (2021). Depression detection by analysing eye movements on emotional images. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7973-7977). IEEE. https://doi.org/10.1109/ICASSP39728.2021.9414663
• [26] Shen, S. S. P., Shu, T., Huang, N. E., Wu, Z., North, G. R., Karl, T. R., & Easterling, D. R. (2005). Hht analysis of the nonlinear and non-stationary annual cycle of daily surface air temperature data. Hilbert-Huang Transform and Its Applications, 5, 187-209. https://doi.org/10.1142/9789812703347_0009
• [27] Siegle, G. J., Granholm, E., Ingram, R. E., & Matt, G. E. (2001). Pupillary and reaction time measures of sustained processing of negative information in depression. Biological Psychiatry, 49(7), 624-636. https://doi.org/10.1016/S0006-3223(00)01024-6
• [28] Siegle, G. J., Steinhauer, S. R., Friedman, E. S., Thompson, W. S., & Thase, M. E. (2011). Remission prognosis for cognitive therapy for recurrent depression using the pupil: Utility and neural correlates. Biological Psychiatry, 69(8), 726-733. https://doi.org/10.1016/j.biopsych.2010.12.041
• [29] Siegle, G. J., Steinhauer, S. R., Stenger, V. A., Konecky, R., & Carter, C. S. (2003). Use of concurrent pupil dilation assessment to inform interpretation and analysis of fMRI data. NeuroImage, 20(1), 114-124. https://doi.org/10.1016/S1053-8119(03)00298-2
• [30] Skowron, K., Budzyńska, A., Wiktorczyk-Kapischke, N., Chomacka, K., Grudlewska-Buda, K., Wilk, M., Wałecka-Zacharska, E., Andrzejewska, M., & Gospodarek-Komkowska, E. (2022). The role of psychobiotics in supporting the treatment of disturbances in the functioning of the nervous system - A systematic review. International Journal of Molecular Sciences, 23(14), 7820. https://doi.org/10.3390/ijms23147820
• [31] Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427-437. https://doi.org/10.1016/j.ipm.2009.03.002
• [32] Suslow, T., Hußlack, A., Kersting, A., & Bodenschatz, C. M. (2020). Attentional biases to emotional information in clinical depression: A systematic and meta-analytic review of eye tracking findings. Journal of Affective Disorders, 274, 632-642. https://doi.org/10.1016/j.jad.2020.05.140
• [33] Wang, J., Fan, Y., Zhao, X., & Chen, N. (2014). Pupillometry in chinese female patients with depression: A pilot study. International Journal of Environmental Research and Public Health, 11(2), 2236-2243. https://doi.org/10.3390/ijerph110202236
• [34] World Health Organization. (2022). World mental health report: Transforming mental health for all. https://www.who.int/publications/i/item/9789240049338
• [35] Yang, M., Wu, Y., Tao, Y., Hu, X., & Hu, B. (2023). Trial selection tensor canonical correlation analysis (TSTCCA) for depression recognition with facial expression and pupil diameter. IEEE Journal of Biomedical and Health Informatics, 1-12. https://doi.org/10.1109/JBHI.2023.3322271
• [36] Yu, B., & Yuan, B. (1995). A global optimum clustering algorithm. Engineering Applications of Artificial Intelligence, 8(2), 223-227. https://doi.org/10.1016/0952-1976(94)00067-W
• [37] Zeng, S., Niu, J., Zhu, J., & Li, X. (2019). A study on depression detection using eye tracking. In Y. Tang, Q. Zu, & J. G. Rodríguez García (Eds.), Human Centered Computing (pp. 516–523). Springer International Publishing. https://doi.org/10.1007/978-3-030-15127-0_52
• [38] Zhang, W.-R., Pandurangi, A. K., Peace, K. E., Zhang, Y.-Q., & Zhao, Z. (2011). MentalSquares: A generic bipolar Support Vector Machine for psychiatric disorder classification, diagnostic analysis and neurobiological data mining. International Journal of Data Mining and Bioinformatics, 5(5), 532-557. https://doi.org/10.1504/IJDMB.2011.043034
• [39] Zhao, L.-M., Li, R., Zheng, W.-L., & Lu, B.-L. (2019). Classification of five emotions from EEG and eye movement signals: Complementary representation properties. 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER) (pp. 611-614). IEEE. https://doi.org/10.1109/NER.2019.8717055
• [40] Zhong, J., Wang, D., Wu, H., Wang, P., Yang, M., Peng, H., & Hu, B. (2022). Filterable sample consensus based on angle variance for pupil segmentation. Digital Signal Processing, 130, 103695. https://doi.org/10.1016/j.dsp.2022.103695
• [41] Zhu, C., Li, B., Li, A., & Zhu, T. (2016). Predicting depression from internet behaviors by time-frequency features. 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI) (pp. 383-390). IEEE. https://doi.org/10.1109/WI.2016.0060
• [42] Zhu, J., Wang, Z., Gong, T., Zeng, S., Li, X., & Hu, B. (2020). An improved classification model for depression detection using EEG and eye tracking data. IEEE Transactions on NanoBioscience, 19(3), 527-537. https://doi.org/10.1109/TNB.2020.2990690
• [43] Zhu, J., Yang, C., Xie, X., Wei, S., Li, Y., Li, X., & Hu, B. (2023). Mutual information based fusion model (MIBFM): Mild depression recognition using EEG and pupil area signals. IEEE Transactions on Affective Computing, 14(3), 2102–2115. https://doi.org/10.1109/TAFFC.2022.3171782

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).