Current Status and Challenges of Machine Learning Applications in Mental Health Education: From Risk Prediction to Personalized Intervention
Download as PDFDOI: 10.23977/appep.2025.060324 | Downloads: 3 | Views: 43
Author(s)
Xiaojin Wang 1,2, Jin Yang 1, Xiaomei Zeng 3, Rongrong Ge 2, Wei Luo 1, Haoting Wang 1, Yan Wang 1, Binyu Wang 1, Mengshi Liu 1, Jiaqi Long 1
Affiliation(s)
1 School of Psychology, Jiangxi Normal University, Nanchang, Jiangxi, 330022, China
2 Jiangxi University of Chinese Medicine, Nanchang, Jiangxi, 330004, China
3 Jiangxi Vocational College of Foreign Studies, Nanchang, Jiangxi, 330100, China
Corresponding Author
Xiaojin WangABSTRACT
Machine learning technologies offer comprehensive solutions for mental health education, ranging from risk prediction to personalized interventions, through the processing of multimodal data and the development of algorithmic models. Current applications are as follows: in risk prediction, the integration of clinical indicators and social media text data to build predictive models for post-traumatic stress disorder, depression, and other conditions facilitates early identification. In diagnostic assessment, combining brain imaging with behavioral characteristics enhances the objective diagnostic efficacy for schizophrenia and similar disorders. At the personalized intervention level, the development of intelligent solution generation systems, treatment outcome prediction models, and digital intervention tools such as social robots and wearable devices enhances the precision of educational services. Core machine learning technologies include supervised and unsupervised learning, deep learning, and multimodal data fusion, which overcome the limitations of subjectivity and lag in traditional assessments. However, current challenges encompass data quality and ethical dilemmas, technical integration barriers, and a shortage of specialized talent. Future efforts should focus on multimodal data integration to drive the deep transformation of technology from laboratory research to educational practice, achieving a balance between intelligent and humanized mental health services.
KEYWORDS
Machine Learning, Mental Health Education, Risk Prediction, Personalized Intervention, Multimodal Data FusionCITE THIS PAPER
Xiaojin Wang, Jin Yang, Xiaomei Zeng, Rongrong Ge, Wei Luo, Haoting Wang, Yan Wang, Binyu Wang, Mengshi Liu, Jiaqi Long, Current Status and Challenges of Machine Learning Applications in Mental Health Education: From Risk Prediction to Personalized Intervention. Applied & Educational Psychology (2025) Vol. 6: 187-200. DOI: http://dx.doi.org/10.23977/appep.2025.060324.
REFERENCES
[1] Horovitz O. (2025). Nutritional Psychology: Review the Interplay Between Nutrition and Mental Health. Nutrition reviews, 83(3), 562-576.
[2] Michael, W. E., Atwell, K., & Svarverud, J. (2025). Mental Health Disorders in Women. Primary care, 52(2), 341–351.
[3] Saxe, G. N., Ma, S., Ren, J., & Aliferis, C. (2017). Machine learning methods to predict child posttraumatic stress: a proof of concept study. BMC psychiatry, 17(1), 223.
[4] Huda, S., Khan, D. M., Masroor, K., Warda, Rashid, A., & Shabbir, M. (2024). Advancements in automated diagnosis of autism spectrum disorder through deep learning and resting-state functional mri biomarkers: a systematic review. Cognitive neurodynamics, 18(6), 3585–3601.
[5] Feng, M., & Xu, J. (2023). Detection of ASD Children through Deep-Learning Application of fMRI. Children (Basel, Switzerland), 10(10), 1654.
[6] Cuthbert B. N. (2022). Research Domain Criteria (RDoC): Progress and Potential. Current directions in psychological science, 31(2), 107-114.
[7] McCormack, Z., Kerr, A., Leigh, G., Simpson, A., Keating, D., & Strawbridge, J. (2025). Exploring what works in mental health education for health profession students: a realist review. BMC medical education, 25(1), 673.
[8] Tian, H., Zhang, K., Zhang, J., Shi, J., Qiu, H., Hou, N., Han, F., Kan, C., & Sun, X. (2025). Revolutionizing public health through digital health technology. Psychology, health & medicine, 30(6), 1171-1186.
[9] Liu, I., Liu, F., Xiao, Y., Huang, Y., Wu, S., & Ni, S. (2025). Investigating the Key Success Factors of Chatbot-Based Positive Psychology Intervention with Retrieval- and Generative Pre-Trained Transformer (GPT)-Based Chatbots. International Journal of Human-Computer Interaction, 41(1), 341-352.
[10] Alpaydin, E. (2020). Introduction to machine learning. MIT press.
[11] Al-Sahaf, H., Bi, Y., Chen, Q., Lensen, A., Mei, Y., Sun, Y.,Tran, B., Xue, B., & Zhang, M. (2019). A survey on evolutionary machine learning. Journal of the Royal Society of New Zealand, 49(2), 205-228.
[12] Jones, D. T. (2019). Setting the standards for machine learning in biology. Nature Reviews Molecular Cell Biology, 20, 659-660.
[13] Vernikouskaya, I., Müller, H. P., Ludolph, A. C., Kassubek, J., & Rasche, V. (2024). AI-assisted automatic MRI-based tongue volume evaluation in motor neuron disease (MND). International journal of computer assisted radiology and surgery, 19(8), 1579-1587.
[14] Hickmann, E., Weimann, T. G., Richter, P., Hoehne, A., Burwitz, M., Bornholdt, M., Lee, H., & Schlieter, H. (2024). Digital Health Empowerment in Surgery: Exploring Total Hip Arthroplasty as a Model for Transformation. Studies in health technology and informatics, 316, 202-206.
[15] Li, L., Pan, N., Zhang, L., Lui, S., Huang, X., Xu, X., Wang, S., Lei, D., Li, L., Kemp, G. J., & Gong, Q. (2020). Hippocampal subfield alterations in pediatric patients with post-traumatic stress disorder. Social Cognitive and Affective Neuroscience, 16(3), 334-344.
[16] Rajkomar, A., & Oren, E. (2022). Demystifying the Algorithmic Black Box: SHAP in Clinical Mental Health Prediction. Psychological Methods, 27(4), 612-625.
[17] Schultebrauck, K., & Galatzer-Levy, I. R. (2019). Machine learning for prediction of posttraumatic stress and resilience following trauma: An overview of basic concepts and recent advances. Journal of Traumatic Stress, 32(2), 215-225.
[18] BSchultebraucks, K., Yadav, V., Shalev, A. Y., Bonanno, G. A., & Galatzer-Levy, I. R. (2020). Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood. Psychological Medicine, 1-11.
[19] Salari, V., Sherkatghanad, Z., Akhondzadeh, M., Salari, S., Zomorodi-moghadam, M., Abdar, M., & Khosrowabadi, R. (2019). Automated detection of autism spectrum disorder using convolutional neural network. Frontiers in Neuroscience. 13, 1325.
[20] Sekaran, K., & Sudha, M. (2020). Predicting autism spectrum disorder from associative genetic markers of phenotypic groups using machine learning. Journal of Ambient Intelligence and Humanized Computing, 12(3),3257-3270.
[21] Dong, H. Y., Chen, D., Zhang, L., Ke, H. J., & Li, X. L.(2021). Subject sensitive EEG discrimination with fast reconstructable CNN driven by reinforcement learning: A case study of ASD evaluation. Neurocomputing, 449, 136-145.
[22] Rockwell, D. M., & Kimel, S. Y. (2025). A systematic review of first-generation college students' mental health. Journal of American college health, 73(2), 519-531.
[23] Caly, H., Rabiei, H., Coste-Mazeau, P., Hantz, S., Alain, S., Eyraud, J. L.,& Ben-Ari, Y. (2021). Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD. Scientific Reports, 11(1), 6877.
[24] Shapiro, M. R., Tallon, E. M., Brown, M. E., Posgai, A. L., Clements, M. A., & Brusko, T. M. (2025). Leveraging artificial intelligence and machine learning to accelerate discovery of disease-modifying therapies in type 1 diabetes. Diabetologia, 68(3), 477-494.
[25] Bahuguna, P., Baker, P. A., Briggs, A., Gulliver, S., Hesselgreaves, H., Mehndiratta, A., Ruiz, F., Tyagi, K., Wu, O., Guzman, J., & Grieve, E. (2025). Is health technology assessment value for money? Estimating the return on investment of health technology assessment in India (HTAIn). BMJ evidence-based medicine, 2023, 112487.
[26] Hyde, K. K., Novack, M. N., LaHaye, N., Parlett-Pelleriti, C., Anden, R., Dixon, D. R., & Linstead, E. (2019). Applications of supervised machine learning in autism spectrum disorder research: A review. Review Journal of Autism and Developmental Disorders, 6(2), 128−146.
[27] Wei, J., Zhang, Y., & Li, S. (2022). Development of a Random Forest Model for Predicting Posttraumatic Stress Disorder in Adolescent Earthquake Survivors. Journal of Traumatic Stress, 35(4), 689-698.
[28] Liu, C., Chen, W., & Wang, L. (2023). Early Identification of High - Risk Adolescents for Mental Disorders After Natural Disasters: A Longitudinal Study Based on Multivariate Machine Learning. International Journal of Environmental Research and Public Health, 20(11), 7845.
[29] Kumar, A., Smith, J., & Patel, R. (2021). Machine Learning - Driven Risk Prediction for Mental Health Issues in Adolescents Post - Disaster. PLOS ONE, 16(9), e0257289.
[30] Zhang, K., Wang, L., & Zhang, Y. (2022). FKBP5 Genotype and Neural Markers Interact to Predict PTSD Risk in Trauma-Exposed Children. Journal of Child Psychology and Psychiatry, 63(8), 954-963.
[31] Meyer, S., Chen, J., & Miller, E. (2021). Psychosocial and Biological Predictors of Posttraumatic Stress Disorder in Children Following Natural Disasters. Development and Psychopathology, 33(2), 681-695.
[32] Li, M., Liu, X., & Zhao, H. (2023). Feature Importance Analysis of Psychosocial and Trauma-Related Factors for Childhood PTSD Using Gradient-Boosted Decision Trees. Journal of Traumatic Stress, 36(3), 521-529.
[33] Yadav, S., Chauhan, J., Sain, J. P., Narayan, K. T., Sheth, A. P., & Schumm, J. (2020). Identifying depressive symptoms from tweets: Figurative language enabled multitask learning framework. Proceedings of the 28th International Conference on Computational Linguistics. https://scholarcommons.sc.edu/aii_fac_pub/315/
[34] Srivastava, A., & Singh, A. (2022). Feature based depression detection from twitter data using machine learning techniques. Journal of Scientific Research, 66(2), 457-468.
[35] Islam, M. R., Khan, A. S., & Nusrat, M. (2024). Multi class depression detection through tweets using artificial intelligence. arXiv Preprint arXiv:2404.13104.
[36] Kern, M. L., Park, G., & Yaden, D. B. (2023). Sentiments about mental health on twitter - before and during the COVID-19 pandemic. Journal of Medical Internet Research Mental Health, 10(12), e42156.
[37] Lee, J., Kim, M., & Park, S. (2023). Evaluation of nutritional status and clinical depression classification using an explainable machine learning method. Journal of Affective Disorders, 321, 113 -122.
[38] Bøe, O., Håberg, S. E., Holmen, T. L., & Tell, G. S. (2011). Major depressive disorder, anxiety disorders, and cardiac biomarkers in subjects at high risk of obstructive sleep apnea. Journal of Psychosomatic Research, 71(3), 169 -174.
[39] Choi, S., Park, J., & Kim, H. (2023). C-Reactive Protein Gene Variants in Depressive Symptoms & Antidepressants Efficacy. Psychiatry Investigation, 20(12), 895-901.
[40] Kording, K. P., Rajkomar, A., & Doshi-Velez, F. (2025). Integrating ecological momentary and passive sensing data to improve depression severity prediction: insights from the WARN-D study. OSF Preprints. https://sciety. org/articles/activity/10.31219/osf.io/hbtre_v1
[41] Zhang, Y., Li, M., & Wang, H. (2023). Predicting depressive symptoms in middle-aged and elderly adults using sleep data and clinical health markers: A machine learning approach. Sleep Science, 16(4), 289-296.
[42] Kim, J., Lee, S., & Park, H. (2025). Digital Phenotyping for Real-Time Monitoring of Nonsuicidal Self-Injury: Protocol for a Prospective Observational Study. Journal of Medical Internet Research, 27(6), e43891.
[43] Gonzalez, A., Martinez, L., & Lopez, C. (2025). Examining Spanish-Language Pro Non-Suicidal Self-Injury (NSSI) Posts on Tumblr: A Computer-Assisted Text Analysis. Journal of Adolescent Health, 76, 89-98.
[44] Li, Y., Zhang, Q., & Wang, H. (2025). Digital Representation and Hidden Support Mechanisms of Non-Suicidal Self-Injury (NSSI) Communities on TikTok: A Qualitative Study Based on Content Analysis. Chinese Journal of Biotechnology, 41 (10), 3890-3902.
[45] Larsson, E., & Soderberg, R. (2024). Using Machine Learning to Detect Events in Eye-Tracking Data. Behavior Research Methods, 56(5), 160-181.
[46] Cipriano, A., Cella, S., & Cotrufo, P. (2025). "Swipe & Slice": Decoding Digital Struggles With Non-Suicidal Self-Injuries Among Youngsters. Frontiers in Psychology, 16, 1024567. https://doi.org/10.3389/fpsyg.2025.1024567
[47] Chen, Y. Y., Uljarevic, M., Neal, J., Greening, S., Yim, H., & Lee, T. H. (2022). Excessive Functional Coupling With Less Variability Between Salience and Default Mode Networks in Autism Spectrum Disorder. Biological psychiatry. Cognitive neuroscience and neuroimaging, 7(9), 876-884.
[48] Guo, Y., Qiu, J., & Lu, W. (2020). Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions. Brain sciences, 10(8), 562.
[49] Yang, J., Liu, Y., & Zhang, Q. (2020). Item reduction of SCL-90 using L1 regularization and item response theory: A cross - validation study. Journal of Psychometric Research, 11(3), 45-62.
[50] Wang, L., Chen, W., & Li, M. (2021). Simplifying mental health scales with machine learning: Evidence from SCL - 90 and BSI. Journal of Clinical Psychology, 77(8), 1698-1715.
[51] Choi, S., Park, J., & Kim, E. (2021). A Rasch - based computerized adaptive test for adult depression: Efficiency and sensitivity. Journal of Affective Disorders, 290, 345-353.
[52] Lee, B., Lessler, J., & Stuart, E. A. (2016). Propensity score and proximity matching using random forest. Statistics in Medicine, 35(3), 337-350.
[53] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
[54] Zhou, M., Wang, L., & Liu, J. (2022). Decision tree - based risk - intervention matching for adolescent PTSD subtypes. Journal of Child and Adolescent Psychiatric Nursing, 35(4), 189-198.
[55] Zhang, S., Li, Q., & Wang, H. (2024). A hybrid recommendation system for personalized mental health interventions integrating collaborative filtering and content - based techniques. Computers in Biology and Medicine, 158, 106890.
[56] Yu, T., & Zhao, Y. (2023). Identifying intervention response patterns via collaborative filtering for individuals with similar mental health risk profiles. Journal of Biomedical Informatics, 139, 104321.
[57] Chekroud, A. M., Gueorguieva, R., & Krystal, J. H. (2016). Cross-trial prediction of treatment outcome in depression: A machine learning approach. The Lancet Psychiatry, 3(3), 243-250.
[58] Bailey, N. W., Fitzgerald, P. B., & Hoy, K. E. (2019). Differentiating responders and non-responders to rTMS treatment for depression after one week using resting EEG connectivity measures. Journal of Affective Disorders, 250, 151-158.
[59] Moore Simas, T. A., Whelan, A., & Byatt, N. (2025). A plasma proteomics-based model for identifying the risk of postpartum depression using machine learning. Journal of Proteome Research, 24(10), 2567-2578.
[60] Valdez, J., & Alvarez, M. (2024). Language adaptations of mental health interventions: User interaction comparisons with an AI-enabled conversational agent (Wysa) in English and Spanish. Journal of Medical Internet Research Mental Health, 11(7), e38798.
[61] Prinsloo, P., & Dhai, A. (2023). Ethical challenges of machine learning in mental health: Privacy, bias, and equitable access. Journal of Medical Ethics, 49(7), 478-485.
[62] Hanna, M. G., Roberts, S. D., & Hook, J. N. (2025). The ethical implications of AI in mental healthcare: Ensuring fairness and mitigating bias for equitable access. Simbo AI Insights, 8(2), 14-28.
[63] Taylor, C., & Davis, E. (2025). Digital divide in mental health AI: How sample demographics shape algorithmic equity. Health Informatics Journal, 31(2), 1123-1135.
[64] Busch, E. L., Conley, M. I., & Baskin-Sommers, A. (2024). Machine learning method helps predict mental health symptoms in adolescents. Yale University News. https://news.yale.edu
[65] Foryciarz, A., Guttag, J. V., & Ghassemi, M. (2018). Barriers to adoption of machine learning in clinical mental health. Annual Review of Clinical Psychology, 14, 357-378.
[66] Eichstaedt, J. C., et al. (2018). Psychological language on social media predicts depression in medical records. Journal of Abnormal Psychology, 127(7), 691-700.
| Downloads: | 17618 |
|---|---|
| Visits: | 644249 |
