Mental health prediction using large language models

Mental health is widely discussed topic in every community. Early detection of mental illness is very essential as it will severely affect the individual, family and society. Apart from the traditional method of collecting information through questionnaire, symptoms can be detected through the online text posted by the patient. In this instinct, advances in AI can be utilized for mental health prediction. The different techniques in AI are best utilized for this purpose. The large language models are now capable of analyzing the contents of social media post. The recommendation model can make use of this information and predict the current mental status of the individual. In the future, it is planned to do mental health prediction using multimodal data.

[1]  Chung, Jetli, and Jason Teo. "Mental health prediction using machine learning: taxonomy, applications, and challenges." Applied Computational Intelligence and Soft Computing 2022.1 (2022): 9970363. [2]  Mohamed, E. Syed, et al. "A hybrid mental health prediction model using Support Vector Machine, Multilayer Perceptron, and Random Forest algorithms." Healthcare Analytics 3 (2023): 100185. [3]  Mutalib, Sofianita, Nor Safika Mohd Shafiee, and Shuzlina Abdul-Rahman. "Mental health prediction models using machine learning in higher education institution." Turkish Journal of Computer and Mathematics Education 12.5 (2021): 1782-1792. [4]  S. Graham, C. Depp, E. E. Lee, C. Nebeker, X. Tu, H.-C. Kim, and D. V. Jeste, “Artificial intelli gence for mental health and mental illnesses: an overview,” Current psychiatry reports, vol. 21, no. 11, pp. 1–18, 2019. [5]  S. Madan, F. J. Zimmer, H. Balabin, S. Schaaf, H. Fröhlich, J. Fluck, I. Neuner, K. Math iak, M. Hofmann-Apitius, and P. Sarkheil, “Deep learning-based detection of psychiatric at tributes from germanmentalhealthrecords,” International Journal of Medical Informatics, vol. 161, p. 104724, 2022. [6]  Ogunseye, Elizabeth Oluyemisi, et al. "Predictive analysis of mental health conditions using AdaBoost algorithm." ParadigmPlus 3.2 (2022): 11-26. [7]  Fudholi, Dhomas Hatta. "Mental health prediction model on social media data using CNN-BILSTM." Kinetik: Game technology, information system, computer network, computing, electronics, and control (2024): 29-44. [8]  Joanna C Yau, Benjamin Girault, Tiantian Feng, Karel Mundnich, Amrutha Nadarajan, Brandon M Booth, Emilio Ferrara, Kristina Lerman, Eric Hsieh, and Shrikanth Narayanan. Tiles-2019: A longitudinal physi ologic and behavioral data set of medical residents in an intensive care unit. Scientific Data, 9(1):536, 2022 [9]  Petter Jakobsen, Enrique Garcia Ceja, Lena Antonsen Stabell, Ketil Joachim Oedegaard, Jan Oystein Berle, Vajira Thambawita, Steven Alexan der Hicks, P˚ al Halvorsen, Ole Bernt Fasmer, and Michael Alexander Riegler. Psykose: A motor activity database of patients with schizophrenia. In 2020 IEEE 33rd International Symposium on Computer-Based Med ical Systems (CBMS), pages 303–308. IEEE, 2020 [10]  Lang He, Mingyue Niu, Prayag Tiwari, Pekka Marttinen, Rui Su, Jiewei Jiang, Chenguang Guo, Hongyu Wang, Songtao Ding, Zhongmin Wang, et al. Deep learning for depression recognition with audiovisual cues: A review. Information Fusion, 80:56–86, 2022.