Depresyonda motor aktivitenin makine öğrenmesi ile değerlendirilmesi

Yıl 2024, Cilt: 13 Sayı: 1, 49 - 59, 15.01.2024

Selim Aras Neriman Aras Mustafa Alptekin Engin

https://doi.org/10.28948/ngumuh.1351103

Öz

Psikiyatrik hastalıkların neredeyse tümünde olduğu gibi depresyonun da klinik olarak değerlendirilmesi gözleme ve subjektif hasta şikâyetlerine dayanmaktadır. Psikomotor retardasyon (gerileme) depresyonun önde gelen semptomlarından biridir ve bunun göstergesi olarak depresyonlu hastalarda fiziksel aktivite azalır. Bu çalışmada, depresyonu olan ve olmayan bireylerin günlük fiziksel aktivite verileri ile oluşturulmuş bir veri setini referans olarak kullanarak, depresyon tanısı için makine öğrenimi temelli objektif bir tanı destekleyici yöntem geliştirmek amaçlanmıştır. Geniş bir öznitelik araştırması yapıldıktan sonra, Fisher Öznitelik Seçimi ile en iyi dört öznitelik belirlenmiş ve Toplu Torbalı Ağaç yöntemini kullanarak 0,88 doğruluk ile referans çalışmasından daha iyi bir sınıflandırma sonucu elde edilmiştir. Ayrıca, referans çalışma ile karşılaştırmak için sınırlandırılan dört öznitelikten daha fazlası seçildiğinde doğruluğun 0,90’nın üzerine çıktığı belirlenmiştir. Böylece, fiziksel aktivite verilerini kullanarak geliştirilen makine öğrenimi temelli yöntemle depresyonu olan ve olmayan bireyleri yüksek doğruluk payı ile ayırt edilmesi başarılmıştır. Bu çalışma, aktivite verilerinin depresyonda tanı destekleyici bir araç olarak kullanılabileceğine dair umut verici sonuçlar ortaya koymuştur. Elde edilen sonuçlar, fiziksel aktivite gibi farklı biyobelirteçlerin de makine öğrenimi ile birlikte kullanıldığında, psikiyatrik değerlendirmedeki objektif tanı destekleyici kriterlerin eksikliğini giderebilecek potansiyele sahip olduğunu göstermektedir.

Anahtar Kelimeler

Makine öğrenmesi, öznitelik, depresyon, fiziksel aktivite, psikomotor retardasyon

Evaluation of motor activity in depression with machine learning

Öz

The clinical assessment of depression is based on observation and subjective patient complaints of almost all psychiatric disorders. Psychomotor retardation is one of the leading symptoms of depression, and as an indicator of this, physical activity is reduced in depressed patients. In this study, we aimed to develop a machine learning-based objective diagnostic support method for diagnosing depression using a dataset of daily physical activity data of individuals with and without depression as a reference. After detailed feature searches, we identified the four best features by Fisher Feature Selection. Using the Ensemble Bagged Tree method, we achieved a better classification result than the reference study, with an accuracy of 0.88. In addition, we found that the accuracy exceeded 0.90 when more than the four features we limited to compare with the reference study were selected. Thus, we could distinguish between individuals with and without depression with high accuracy with the machine learning-based method, which we developed using physical activity data. This study has shown promising results that activity data can be used as a diagnostic tool for depression. Our results show that different biomarkers, such as physical activity, when used with machine learning, can potentially overcome the lack of objective diagnostic support criteria in psychiatric evaluation.

Anahtar Kelimeler

Machine learning, feature, depression, physical activity, psychomotor retardation

Kaynakça

• Z. S. Syed, K. Sidorov, and D. Marshall, Depression severity prediction based on biomarkers of psychomotor retardation. Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge, pp. 37-43, Mountain View, CA, USA, 2017.
• American Psychiatric Association, Desk reference to the diagnostic criteria from DSM-5 (R). Arlington, TX: American Psychiatric Association Publishing, 2013.
• D. Schrijvers, E. R. A. de Bruijn, Y. Maas, C. De Grave, B. G. C. Sabbe, and W. Hulstijn, Action monitoring in major depressive disorder with psychomotor retardation, Cortex, 44(5), 569–579, 2008. https://doi.org/ 10.1016/j.cortex.2007.08.014.
• W. H. Liu, L. Z. Wang, H. R. Shang, Y. Shen, Z. Li, E. F. Cheung, R. C. Chan, The influence of anhedonia on feedback negativity in major depressive disorder, Neuropsychologia, 53, 213–220, 2014. https://doi.org/10.1016/j.neuropsychologia.2013.11.023.
• S. A. Almaghrabi, S. R. Clark, and M. Baumert, Bio-acoustic features of depression: A review, Biomed. Signal Process. Control, 85, 105020, 1-16 2023. https://doi.org/10.1016/j.bspc.2023.105020.
• D. Bennabi, P. Vandel, C. Papaxanthis, T. Pozzo, and E. Haffen, Psychomotor retardation in depression: a systematic review of diagnostic, pathophysiologic, and therapeutic implications, Biomed Res. Int., 2013, 158746, 1-13, 2013. https://doi.org/10.1155/ 2013/158746.
• T. Bracht, A. Federspiel, S. Schnell, H. Horn, O. Höfle, R. Wiest, T. Dierk, W. Strik, T. J. Müller, S. Walther, Cortico-cortical white matter motor pathway microstructure is related to psychomotor retardation in major depressive disorder, PLoS One, 7(12), 1-8. e52238, 2012.
• S. Calugi, G. B. Cassano, A. Litta, P. Rucci, A. Benvenuti, M. Miniati, L. Lattanzi, V. Mantua, V. Lombardi, A. Fagiolini, and E. Frank, Does psychomotor retardation define a clinically relevant phenotype of unipolar depression?, J. Affect. Disord., 129(1–3), 296–300, 2011.
• S. Walther, S. Hügli, O. Höfle, A. Federspiel, H. Horn, T. Bracht, R. Wiest, W. Strik, and T. J. Müller, Frontal white matter integrity is related to psychomotor retardation in major depression, Neurobiol. Dis., 47(1), 13–19, 2012.
• D. Schrijvers, W. Hulstijn, and B. G. C. Sabbe, Psychomotor symptoms in depression: a diagnostic, pathophysiological and therapeutic tool, J. Affect. Disord., 109(1–2), 1–20, 2008.
• I. B. Hickie, S. L. Naismith, P. B. Ward, C. L. Little, M. Pearson, and E. M. Scott, Psychomotor slowing in older patients with major depression: relationships with blood flowin the caudate nucleus andwhite matter lesions, Psychiatry Res., 155(3), 211–220, 2009.
• T. F. Quatieri and N. Malyska, Vocal-source biomarkers for depression: A link to psychomotor activity Proc, Conf. Int. Speech Commun. Assoc., Interspeech, International Speech Communication Association (ISCA), pp. 1059–1062, 2012.
• N. Cummins, S. Scherer, J. Krajewski, S. Schnieder, J. Epps, and T. F. Quatieri, A review of depression and suicide risk assessment using speech analysis, Speech Commun., 71, 10–49, 2015.
• D. Shin, W. I. Cho, C. H. K. Park, S. J. Rhee, M. J. Kim, H. Lee, N. S. Kim, and Y. M. Ahn, Detection of minor and major depression through voice as a biomarker using machine learning, J. Clin. Med., 10(14), 3046, 2021. https://doi.org/10.3390/jcm10143046.
• S. Suparatpinyo and N. Soonthornphisaj, Smart voice recognition based on deep learning for depression diagnosis, Artificial Life and Robotics, 28(2), 332–342, 2023. https://doi.org/10.1007/s10015-023-00852-4
• H. Tian, Z. Zhu, and X. Jing, Deep learning for depression recognition from speech, Mob. Netw. Appl., 1-16, 2023.
• P. J. Benson, S. A. Beedie, E. Shephard, I. Giegling, D. Rujescu, and D. St. Clair, Simple viewing tests can detect eye movement abnormalities that distinguish schizophrenia cases from controls with exceptional accuracy, Biol. Psychiatry, 72(9), 716–724, 2012.
• S. Brakemeier, A. Sprenger, I. Meyhöfer, J. E. McDowell, L. H. Rubin, S. K. Hill, M. S. Keshavan, G. D. Pearlson, C. A. Tamminga, E. S. Gershon, S. S. Keedy, J. A. Sweeney, B. A. Clementz, and R. Lencer, Smooth pursuit eye movement deficits as a biomarker for psychotic features in bipolar disorder—Findings from the PARDIP study, Bipolar Disord., 22(6), 602–611, 2020. https://doi.org/10.1111/bdi.12865
• M. Gao, R. Xin, Q. Wang, D. Gao, J. Wang, and Y. Yu, Abnormal eye movement features in patients with depression: Preliminary findings based on eye tracking technology, Gen. Hosp. Psychiatry, 84, 25–30, 2023.https://doi.org/10.1016/j.genhosppsych.2023.04.010
• E. S. Kangas, E. Vuoriainen, S. Lindeman, and P. Astikainen, Auditory event-related potentials in separating patients with depressive disorders and non-depressed controls: A narrative review, Int. J. Psychophysiol., 179, 119–142, 2022. https://doi.org/10.1016/j.ijpsycho.2022.07.003
• F. Li and Y. Ding, Data mining in cognitive function training of depression patients applications, in 2019 10th International Conference on Information Technology in Medicine and Education (ITME), pp. 98-101, Qingdao, China, 2019.
• Y. Baek, K. Jung, and S. Lee, Effects of sleep restriction on subjective and physiological variables in middle-aged Korean adults: an intervention study, Sleep Med., 70, 60–65, 2020.
• J.-G. Choi, I. Ko, and S. Han, Depression level classification using machine learning classifiers based on actigraphy data, IEEE Access, 9, 116622–116646, 2021. https://doi.org/10.1109/access.2021.3105393
• J. Kim, T. Nakamura, H. Kikuchi, K. Yoshiuchi, T. Sasaki, and Y. Yamamoto, Covariation of depressive mood and spontaneous physical activity in major depressive disorder: toward continuous monitoring of depressive mood, IEEE J. Biomed. Health Inform., 19 (4), 1347–1355, 2015.
• M. Abbas, J.-C. Roy, G. Robert, and R. L. Bouquin Jeannes, Utility of actimetry to detect apathy in old-age depression: A pilot study, in 2022 30th European Signal Processing Conference (EUSIPCO), pp.1203-1207, Belgrade, Serbia, 2022.
• R. K. Thelagathoti and H. H. Ali, A correlation network Model for analyzing mobility data in depression related studies, 16th International Conference on Health Informatics HEALTHINF, pp. 416–423, 2023
• E. Garcia-Ceja, M. Riegler, P. Jakobsen, J. Tørresen, T. Nordgreen, K. J. Oedegaard, and O. B. Fasmer, 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, 2018.
• M. Raihan, A. K. Bairagi, and S. Rahman, A machine learning based study to predict depression with monitoring actigraph watch data, 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1-5, 2021.
• A. Arora, P. Chakraborty, and M. P. S. Bhatia, 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. Technol., 15 (2), 797-802, 2023.
• M. M. Misgar and M. P. S. Bhatia, Detection of depression from IoMT time series data using UMAP features, in 2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp. 623-628, Greater Noida, India, 2022,
• L. Ladha and T. Deepa, Feature selection methods and algorithms, International Journal on Computer Science and Engineering, 3(5), 1787–1797, 2011.
• I. Guyon, S. Gunn, M. Nikravesh, and L. A. Zadeh, Feature Extraction: Foundations and Applications. Berlin, Germany, Springer, 2006.
• G. Roffo, S. Melzi, U. Castellani, and A. Vinciarelli, Infinite latent feature selection: A probabilistic latent graph-based ranking approach, IEEE International Conference on Computer Vision (ICCV), pp. 1407-1415, Venice, Italy, 2017.
• G. Roffo, S. Melzi, U. Castellani, A. Vinciarelli, and M. Cristani, Infinite Feature Selection: A graph-based feature filtering approach, IEEE Trans. Pattern Anal. Mach. Intell., 43(12), 4396–4410, 2021.
• H. Liu and H. Motoda, Eds., Computational Methods of Feature Selection. Chapman and Hall/CRC, 2007.
• M. Zaffalon and M. Hutter, Robust feature selection using distributions of mutual information, in Proceedings of the 18th International Conference on Uncertainty in Artificial Intellegence (UAI-2002), San Francisco, CA, pp. 577–584, 2002.
• Q. Gu, Z. Li, and J. Han, Generalized Fisher score for feature selection, arXiv [cs.LG], 2012.
• M. A. Hall, Correlation-based Feature Selection for Machine Learning. Hamilton, 1999.
• K. Bhavsar, V. Vakharia, R. Chaudhari, J. Vora, D. Y. Pimenov, and K. Giasin, A comparative study to predict bearing degradation using discrete wavelet transform (DWT), tabular generative adversarial networks (TGAN) and machine learning models, Machines, 10(3), pp.1-18, 2022.
• J. Brownlee, Machine learning algorithms from scratch with Python, Machine Learning Mastery, 2016.
• J. S. L. Senanayaka, H. Van Khang, and K. G. Robbersmyr, Towards online bearing fault detection using envelope analysis of vibration signal and decision tree classification algorithm, 20th International Conference on Electrical Machines and Systems (ICEMS), pp. 1-6 Sydney, NSW, Australia, 2017,
• C. Cortes, and V. Vapnik, Support-vector networks. Machine Learning, 20(3), 273–297, 1995. https://doi.org/10.1007/bf00994018
• F. Cheng, C. Yang, H. Zhu, Y. Li, and F. Zhang, A concentration interval identification method of cobalt ions based on optimal spectral bands selection and naive Bayes classification, China Automation Congress (CAC), pp. 7762-7766, Beijing, China, 2021.
• I. A. P. Banlawe, J. C. Dela Cruz, J. C. P. Gaspar, and E. J. I. Gutierrez, Decision tree learning algorithm and naïve Bayes classifier algorithm comparative classification for mango pulp weevil mating activity, IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS), pp. 317-322, Shah Alam, Malaysia, 2021.
• W. Jinjia, J. Shaonan, and Z. Yaqian, Quadratic discriminant analysis based on graphical lasso for activity recognition, in 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), pp. 70-74, Wuxi, China, 2019.
• M. Zakariah and Y. A. Alotaibi, Unipolar and bipolar depression detection and classification based on actigraphic registration of motor activity using machine learning and uniform manifold approximation and projection methods, Diagnostics (Basel), 13(14), 2323, 2023. https://doi.org/10.3390/diagnostics13142323
• P. Jakobsen, E. Garcia-Ceja, M. Riegler, L. A. Stabell, T. Nordgreen, J. Torresen, O. B. Fasmer, and K. J. Oedegaard,, Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls, PLoS One, 15, 8, e0231995, 1-16 2020.
• A. Aminifar, F. Rabbi, V. K. I. Pun, and Y. Lamo, Monitoring motor activity data for detecting patients’ depression using data augmentation and privacy-preserving distributed learning, Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., pp. 2163–2169, Mexico 2021.
• A. Kumar, S. R. Sangwan, A. Arora, and V. G. Menon, Depress-DCNF: A deep convolutional neuro-fuzzy model for detection of depression episodes using IoMT, Appl. Soft Comput., 122, 108863, 1-16, 2022.
• L. A. Zanella-Calzada, C. E. Galván-Tejada, N. M. Chávez-Lamas, M. D. C. Gracia-Cortés, R. Magallanes-Quintanar, J. M. Celaya-Padilla, J. I. Galván-Tejada, and H. Gamboa-Rosales, Feature extraction in motor activity signal: Towards a depression episodes detection in unipolar and bipolar patients, Diagnostics (Basel), 9(1), 1-13, 2019.
• C. H. Espino-Salinas, C. E. Galván-Tejada, H. Luna-García, H. Gamboa-Rosales, J. M. Celaya-Padilla, L. A. Zanella-Calzada, and J. I. G. Tejada, Two-dimensional Convolutional Neural Network for depression episodes detection in real time using motor activity time series of depresjon dataset, Bioengineering, 9(9), 1-17, 2022.
• O. Aydemir, A new performance evaluation metric for classifiers: polygon area metric. Journal of Classification, 38, 16-26. 2021. https://doi.org/10. 1007/s00357-020-09362-5