سامانه مدیریت نشریات علمی دانشگاه صنعتی شاهرود

Rezaee, Khosro. (1404). A Hybrid Deep Learning Framework for Detecting Bipolar Disorder Through Persian Handwriting Patterns. , 13(2), 119-133. doi: 10.22044/jadm.2025.15456.2658
Khosro Rezaee. "A Hybrid Deep Learning Framework for Detecting Bipolar Disorder Through Persian Handwriting Patterns". , 13, 2, 1404, 119-133. doi: 10.22044/jadm.2025.15456.2658
Rezaee, Khosro. (1404). 'A Hybrid Deep Learning Framework for Detecting Bipolar Disorder Through Persian Handwriting Patterns', , 13(2), pp. 119-133. doi: 10.22044/jadm.2025.15456.2658
Rezaee, Khosro. A Hybrid Deep Learning Framework for Detecting Bipolar Disorder Through Persian Handwriting Patterns. , 1404; 13(2): 119-133. doi: 10.22044/jadm.2025.15456.2658

A Hybrid Deep Learning Framework for Detecting Bipolar Disorder Through Persian Handwriting Patterns

Journal of AI and Data Mining
دوره 13، شماره 2، تیر 2025، صفحه 119-133    اصل مقاله (1.48 M)
نوع مقاله: Original/Review Paper
شناسه دیجیتال (DOI): 10.22044/jadm.2025.15456.2658
نویسنده
Khosro Rezaee*
Department of Biomedical Engineering, Meybod University, Meybod, Iran.
چکیده
Bipolar disorder (BD) remains a pervasive mental health challenge, demanding innovative diagnostic approaches beyond traditional, subjective assessments. This study pioneers a non-invasive handwriting-based diagnostic framework, leveraging the unique interplay between psychological states and motor expressions in writing. Our hybrid deep learning model, combining ResNet for intricate feature extraction and external attention mechanisms for global pattern analysis, achieves a remarkably high accuracy 99%, validated through Leave-One-Subject-Out (LOSO) cross-validation. Augmented with advanced data preprocessing and augmentation techniques, the framework adeptly addresses dataset imbalances and handwriting variability. For the first time, Persian handwriting serves as a medium, bridging cultural gaps in BD diagnostics. This work not only establishes handwriting as a transformative tool for mental health diagnostics but also sets the stage for accessible, scalable, and culturally adaptive solutions in global mental healthcare.
کلیدواژه‌ها
Bipolar Disorder Diagnosis؛ Handwriting Analysis؛ Deep Learning Applications؛ Persian Handwriting؛ Artificial Intelligence in Mental Health
مراجع
  • Kato, K. Baba, W. Guo, Y. Chen, and T. Nosaka, "Impact of bipolar disorder on health-related quality of life and work productivity: Estimates from the national health and wellness survey in Japan," Journal of Affective Disorders, vol. 295, pp. 203–214, 2021.
  • Nierenberg, B. Agustini, O. Köhler-Forsberg, C. Cusin, D. Katz, L. Sylvia, A. Peters, and M. Berk, "Diagnosis and Treatment of Bipolar Disorder: A Review," JAMA, vol. 330, no. 14, pp. 1370–1380, 2023.
  • He, C. Hu, Z. Ren, L. Bai, F. Gao, and J. Lyu, "Trends in the incidence and DALYs of bipolar disorder at global, regional, and national levels: Results from the global burden of disease study 2017," Journal of Psychiatric Research, vol. 125, pp. 96–105, 2020.
  • Yang et al., "Differentiation between bipolar disorder and major depressive disorder in adolescents: from clinical to biological biomarkers," Frontiers in Human Neuroscience, vol. 17, 2023.
  • L. P. S. P. Paramita, S. S. Hillaly, T. Y. Susanto, R. Komalasari, A. A. N. Wirakusuma, D. B. Cahyono, and P. H. P. Jati, "Optimized risk scores for early detection of bipolar disorder based on crowdsourced text data," in 2023 IEEE 9th Information Technology International Seminar (ITIS), 2023, pp. 1–6.
  • Laksshman, R. R. Bhat, V. Viswanath, and X. Li, "DeepBipolar: Identifying genomic mutations for bipolar disorder via deep learning," Human Mutation, vol. 38, no. 9, pp. 1217–1224, 2017.
  • Metin, Ç. Uyulan, T. T. Ergüzel, S. Farhad, E. Çifçi, Ö. Türk, and N. Tarhan, "The deep learning method differentiates patients with bipolar disorder from controls with high accuracy using EEG data," Clinical EEG and Neuroscience, vol. 55, no. 2, pp. 167–175, 2024.
  • Crespo, A. Ibañez, M. F. Soriano, S. Iglesias, and J. I. Aznarte, "Handwriting movements for assessment of motor symptoms in schizophrenia spectrum disorders and bipolar disorder," PLoS ONE, vol. 14, no. 3, p. e0213657, 2019.
  • A. Y. Ayaz, O. Celbis, E. P. Zayman, R. Karlidağ, and B. S. Önar, "The use of handwriting changes for the follow-up of patients with bipolar disorder," Archives of Neuropsychiatry, vol. 59, no. 1, pp. 3–9, 2022.
  • Shin, M. Maniruzzaman, Y. Uchida, M. A. M. Hasan, A. Megumi, and A. Yasumura, "Handwriting-based ADHD detection for children having ASD using machine learning approaches," IEEE Access, vol. 11, pp. 84974–84984, 2023.
  • Jafarzadeh, P. Choobdar, and V. M. Safarzadeh, "Khayyam Offline Persian Handwriting Dataset," arXiv preprint arXiv:2406.01025, 2024.
  • Jamali, R. Kargar, S. Alipour, and M. Rostami Malkhalife, "Machine learning approach for bipolar disorder analysis and recognition based on handwriting digital images," AUT Journal of Mathematics and Computing, 2024.
  • Li, L. Cui, L. Cao, Y. Zhang, Y. Liu, W. Deng, and W. Zhou, "Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques," BMC Psychiatry, vol. 20, pp. 1–12, 2020.
  • Ceccarelli and M. Mahmoud, "Multimodal temporal machine learning for bipolar disorder and depression recognition," Pattern Analysis and Applications, vol. 25, no. 3, pp. 493–504, 2022.
  • de Siqueira Rotenberg, R. G. Borges-Junior, B. Lafer, R. Salvini, and R. da Silva Dias, "Exploring machine learning to predict depressive relapses of bipolar disorder patients," Journal of Affective Disorders, vol. 295, pp. 681–687, 2021.
  • N. Disha, S. Seema, S. U. Shenoy, and S. Rao, "Prediction of bipolar disorder using machine learning techniques," in 2022 2nd International Conference on Intelligent Technologies (CONIT), Jun. 2022, pp. 1–5.
  • Á. Luján, A. M. Torres, A. L. Borja, J. L. Santos, and J. M. Sotos, "High-precise bipolar disorder detection by using radial basis functions based neural network," Electronics, vol. 11, no. 3, p. 343, Jan. 2022.
  • A. I. Diaz, R. P. Vicerra, and A. A. Bandala, "Preprocessing image contouring optimization of handwriting recognition using genetic algorithm," in TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON), Auckland, New Zealand, Dec. 2021, pp. 756–759.
  • T. Anggraeny, Y. V. Via, and R. Mumpuni, "Image preprocessing analysis in handwritten Javanese character recognition," Bulletin of Electrical Engineering and Informatics, vol. 12, no. 2, pp. 860–867, 2023.
  • Fuglsby, C. P. Saunders, D. M. Ommen, J. Buscaglia, and M. P. Caligiuri, "Elucidating the relationships between two automated handwriting feature quantification systems for multiple pairwise comparisons," J. Forensic Sci., vol. 67, no. 2, pp. 642–650, 2022.
  • Dhieb, S. Njah, H. Boubaker, W. Ouarda, M. B. Ayed, and A. M. Alimi, "Towards a novel biometric system for forensic document examination," Computers & Security, vol. 97, p. 101973, 2020.
  • Simayi, M. Ibrayim, and A. Hamdulla, "Study the preprocessing effect on RNN-based online Uyghur handwritten word recognition," Wireless Networks, vol. 27, no. 8, pp. 1–12, 2021.
  • Singh, V. K. Chauhan, and E. H. B. Smith, "A self-controlled RDP approach for feature extraction in online handwriting recognition using deep learning," Appl. Intell., vol. 50, no. 7, pp. 2093–2104, 2020.
  • Hasan, M. A. Rahim, J. Shin, S. Nishimura, and M. N. Hossain, "Dynamics of digital pen-tablet: Handwriting analysis for person identification using machine and deep learning techniques," IEEE Access, vol. 12, pp. 8154–8177, 2024.
  • Brown and I. Lidzhade, "Handwriting recognition using deep learning with effective data augmentation techniques," in 2021 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD), 2021, pp. 1–9.
  • Pham, A. R. Setlur, S. Dingliwal, T. Lin, B. Póczos, K. Huang, Z. Li, J. Lim, C. McCormack, and T. Vu, "Robust handwriting recognition with limited and noisy data," in 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2020, pp. 301–306.
  • Hayashi, K. Gyohten, H. Ohki, and T. Takami, "A study of data augmentation for handwritten character recognition using deep learning," in 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2018, pp. 552–557.
  • Lv, "Handwritten digit recognition based on deep learning algorithms," in 2023 International Conference on Internet of Things, Robotics and Distributed Computing (ICIRDC), 2023, pp. 476–481.
  • Minz, R. Kanojia, T. Yadav, and N. Jayanthi, "Enhancing accuracy in handwritten text recognition with convolutional recurrent neural network and data augmentation techniques," in 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), 2023, pp. 803–808.
  • He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
  • S. Kawuma, E. Kumbakumba, V. Mabirizi, D. Nanjebe, K. Mworozi, A. O. Mukama, and L. Kyasimire, "Diagnosis and classification of tuberculosis chest X-ray images of children less than 15 years at Mbarara Regional Referral Hospital using deep learning," Journal of AI and Data Mining, vol. 12, no. 2, pp. 315–324, 2024.
  • H. Guo, Z. N. Liu, T. J. Mu, and S. M. Hu, "Beyond self-attention: External attention using two linear layers for visual tasks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5436–5447, 2022.
  • S. Cohen, R. Cont, A. Rossier, and R. Xu, "Scaling properties of deep residual networks," in Proc. Int. Conf. Mach. Learn. (ICML), Jul. 2021, pp. 2039–2048.
  • A. Jamali, "Bipolar vs non-bipolar handwriting dataset," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/ahmadalijamali/bipolar-vs-non-bipolar-handwriting/data
  • Magioncalda and M. Martino, "A unified model of the pathophysiology of bipolar disorder," Molecular Psychiatry, vol. 27, no. 1, pp. 202–211, 2022.
  • Wakelin and P. Oakes, "Clinicians’ perceptions of the bipolar disorder diagnosis: A Q-study," The Journal of Mental Health Training, Education and Practice, vol. 15, pp. 1–12, 2019.
  • Baki, H. Kaya, E. Ciftçi, H. Gulec, and A. A. Salah, "A multimodal approach for mania level prediction in bipolar disorder," IEEE Transactions on Affective Computing, vol. 13, pp. 2119–2131, 2022.
  • Ortiz, K. Bradler, and A. Hintze, "Episode forecasting in bipolar disorder: Is energy better than mood?," Bipolar Disorders, vol. 20, pp. 470–476, 2018.
  • J. Herrera et al., "Neural abnormalities in bipolar disorder: A meta-analysis of functional neuroimaging studies," European Psychiatry, 2024.
  • Shen, L. Zhang, C. Xu, J. Zhu, M. Chen, and Y. Fang, "Analysis of misdiagnosis of bipolar disorder in an outpatient setting," General Psychiatry, vol. 30, pp. 101–93, 2018.
  • Bansal, S. D. Mishra, and M. Singhal, "The impact of neurological disorders on handwriting: Implications for forensic document examination," Wiley Interdisciplinary Reviews: Forensic Science, vol. e1536, 2024.
  • Gerth and J. Festman, "Muscle activity during handwriting on a tablet: An electromyographic analysis of the writing process in children and adults," Children, vol. 10, no. 4, p. 748, 2023.
  • Wu, G. M. Goodwin, T. Lyons, and K. E. Saunders, "Identifying psychiatric diagnosis from missing mood data through the use of log-signature features," PLoS ONE, vol. 17, no. 11, p. e0276821, 2022.
  • Casalino, G. Castellano, F. Galetta, and K. Kaczmarek-Majer, "Dynamic incremental semi-supervised fuzzy clustering for bipolar disorder episode prediction," in International Conference on Discovery Science, Cham: Springer International Publishing, Oct. 2020, pp. 79–93.
آمار
تعداد مشاهده مقاله: 434
تعداد دریافت فایل اصل مقاله: 441