Fathoming the Mind: Mental Disorders Predictions Through fMRI Analysis with Machine Learning Algorithms
Abstract
Mental health disorders affect a significant portion of the global population, making early detection and prevention an urgent challenge. Functional Magnetic Resonance Imaging (fMRI) offers a non-invasive means of mapping brain activity, while machine learning (ML) techniques provide powerful tools for analyzing its high-dimensional data. This paper presents a focused review of studies published between 2018 and 2023 that apply ML algorithms to fMRI data in the context of mental health. Unlike broader surveys, our approach selectively examines recent contributions, emphasizing the disorders investigated, the algorithms employed, and the reported performance metrics. We synthesize results across methods such as Support Vector Machines, Random Forests, and Neural Networks, highlighting both their advantages and limitations. By consolidating findings into comparative tables, we aim to provide a structured overview that clarifies current trends, methodological challenges, and promising directions. This work contributes a Computer Science–oriented perspective on the use of ML in fMRI analysis, identifying open issues related to generalizability, interpretability, and scalability that must be addressed in future research.
References
[1] Mental Health Statistics 2024 - Quick Facts & Statistics About Mental Health. Available at: https://www.ehproject.org/mental-health/mental-health-statistics-2023, 2023.
[2] Akrami, H., Cui, W., Kim, P. E., Heck, C. N., Irimia, A., Jebri, K., Nair, D., Leahy, R. M., and Joshi, A. Prediction of Post Traumatic Epilepsy using MRI-based Imaging Markers. bioRxiv (2024), 2024–01.
[3] Aljobouri, H. K., Jaber, H. A., Kocak, O. M., Algin, O., and Cankaya, I. Clustering fMRI data with a robust unsupervised learning algorithm for neuroscience data mining. Journal of neuroscience methods 299 (2018), 45–54.
[4] Christopher deCharms, R. Applications of real-time fMRI. Nature Reviews Neuro-science 9, 9 (2008), 720–729.
[5] CONN ToolBox. CONN ToolBox. Available at: https://web.conn-toolbox.org/resources/citing-conn.
[6] dos Santos, J. D. M., and dos Santos, J. P. M. Explaining ANN-modeled fMRI Data with Path-Weights and Layer-Wise Relevance Propagation.
[7] Eslami, T., and Saeed, F. Auto-ASD-network: a technique based on deep learning and support vector machines for diagnosing autism spectrum disorder using fMRI data. In Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (2019), pp. 646–651.
[8] Eurostat. Mental health and related issues statistics. Available at: https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Mental health and related issues statistics, 2021.
[9] Fiorenzato, E., Moaveninejad, S., Weis, L., Biundo, R., Antonini, A., and Porcaro, C. Brain Dynamics Complexity as a Signature of Cognitive Decline in Parkinson’s Disease. Movement Disorders (2023).
[10] Frances-Villora, J. V., Bataller-Mompean, M., Mjahad, A., Rosado-Munoz,A., Gutierrez Martin, A., Teruel-Marti, V., Villanueva, V., Hampel, K. G., and Guerrero-Martinez, J. F. Real-time localization of epileptogenic foci EEG signals: an FPGA-based implementation. Applied Sciences 10, 3 (2020), 827.
[11] Jiang, X., Cao, B., Li, C., Jia, L., Jing, Y., Cai, W., Zhao, W., Sun, Q., Wu, F., Kong, L., et al. Identifying misdiagnosed bipolar disorder using support vector machine: feature selection based on fMRI of follow-up confirmed affective disorders. Translational Psychiatry 14, 1 (2024), 9.
[12] Jolliffe, Ian T. Principal component analysis for special types of data. Springer, 2002.
[13] Kwong, K. K. Record of a single fMRI experiment in May of 1991. Neuroimage 62, 2 (2012), 610–612.
[14] Lee, J.-H., Oh, S., Jolesz, F. A., Park, H., and Yoo, S.-S. Application of independent component analysis for the data mining of simultaneous EEG–fMRI: preliminary experience on sleep onset. International Journal of Neuroscience 119, 8 (2009), 1118–
1136.
[15] Lee, M. H., Kim, N., Yoo, J., Kim, H.-K., Son, Y.-D., Kim, Y.-B., Oh, S. M., Kim, S., Lee, H., Jeon, J. E., et al. Multitask fMRI and machine learning approach improve prediction of differential brain activity pattern in patients with insomnia disorder.
Scientific Reports 11, 1 (2021), 9402.
[16] Lin, C., Huang, C.-M., Chang, W., Chang, Y.-X., Liu, H.-L., Ng, S.-H., Lin, H.-L., Lee, T. M.-C., Lee, S.-H., and Wu, S.-C. Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI. Brain and Behavior 14, 1 (2024), e3348.
[17] Liu, R., Huang, Z.-a., Jiang, M., and Tan, K. C. Multi-LSTM networks for accurate classification of ADHD from resting-state fMRI data. In 2020 2nd International Conference on Industrial Artificial Intelligence (IAI) (2020), IEEE, pp. 1–6.
[18] Mahrukh, R., Shakil, S., and Malik, A. S. Sentiments analysis of fMRI using automatically generated stimuli labels under naturalistic paradigm. Scientific Reports 13, 1 (2023), 7267.
[19] Mao, Z., Su, Y., Xu, G., Wang, X., Huang, Y., Yue, W., Sun, L., and Xiong, N. Spatio-temporal deep learning method for ADHD fMRI classification. Information Sciences 499 (2019), 1–11.
[20] MELODIC. Multivariate Exploratory Linear Optimized Decomposition into Independent Components. Available at: https://web.mit.edu/fsl v5.0.10/fsl/doc/wiki/MELODIC.html.
[21] Mikolas, P., Marxen, M., Riedel, P., Br¨ ockel, K., Martini, J., Huth, F., Berndt, C., Vogelbacher, C., Jansen, A., Kircher, T., et al. Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features. Psychological Medicine 54, 2 (2024), 278–288.
[22] Moll, J., Green, S., Deakin, J. F., Thomaz, C. E., Zahn, R., et al. Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression. 1872-7123 (2015).
[23] National Institutes of Mental Health. Mental Disorders in America. Available at: https://www.nimh.nih.gov/health/statistics/mental-illness, 2021.
[24] Ogawa, S. Finding the BOLD effect in brain images. Neuroimage 62, 2 (2012), 608–609.
[25] Pan, N., Qin, K., Patino, L. R., Tallman, M. J., Lei, D., Lu, L., Li, W., Blom, T. J., Bruns, K. M., Welge, J. A., et al. Aberrant brain network topology in youth with a familial risk for bipolar disorder: a task-based fMRI connectome study. Journal of Child Psychology and Psychiatry (2024).
[26] Park, K. M., Kim, K. T., Lee, D. A., Motamedi, G. K., and Cho, Y. W. Structural and functional multilayer network analysis in restless legs syndrome patients. Journal of Sleep Research (2023), e14104.
[27] Penny, W. D., Friston, K. J., Ashburner, J. T., Kiebel, S. J., and Nichols, T. E. Statistical parametric mapping: the analysis of functional brain images. Elsevier, 2011.
[28] Poldrack, R. A. The future of fMRI in cognitive neuroscience. Neuroimage 62, 2 (2012), 1216–1220.
[29] Rashid, M., Singh, H., and Goyal, V. The use of machine learning and deep learning algorithms in functional magnetic resonance imaging—a systematic review. Expert
Systems 37, 6 (2020), e12644.
[30] Regier, D. A., First, M., Marshall, T., and Narrow, W. E. The American Psychiatric Association (APA) classification of mental disorders: strengths, limitations and future perspectives. Psychiatric diagnosis and classification (2002), 47–78.
[31] Reiter, M. A., Jahedi, A., Fredo, A. J., Fishman, I., Bailey, B., and Muller, R.-A. Performance of machine learning classification models of autism using resting- state fMRI is contingent on sample heterogeneity. Neural Computing and Applications
33 (2021), 3299–3310.
[32] Rockville, M. Mental health: A report of the Surgeon General. US Department of Health and Human Services (1999).
[33] Rodrigues, I. D., de Carvalho, E. A., Santana, C. P., and Bastos, G. S. Machine Learning and rs-fMRI to Identify Potential Brain Regions Associated with Autism Severity. Algorithms 15, 6 (2022), 195.
[34] Rolland, X., Maurel, P., and Maumet, C. Towards efficient fMRI data re-use: can we run between-group analyses with datasets processed differently with SPM? In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (2022), IEEE, pp. 1–4.
[35] Saurabh, S., and Gupta, P. Deep learning-based modified bidirectional LSTM network for classification of ADHD disorder. Arabian Journal for Science and Engineering 49, 3 (2024), 3009–3026.
[36] Sethuraman, S. K., Malaiyappan, N., Ramalingam, R., Basheer, S., Rashid, M., and Ahmad, N. Predicting Alzheimer’s Disease Using Deep Neuro-Functional Networks with Resting-State fMRI. Electronics 12, 4 (2023), 1031.
[37] Soros, P., and Witt, K. Book review: Introduction to neuroimaging analysis, 2018.
[38] Sunil, G., Gowtham, S., Bose, A., Harish, S., and Srinivasa, G. Graph neural network and machine learning analysis of functional neuroimaging for understanding schizophrenia. BMC Neuroscience 25, 1 (2024), 2.
[39] Wang, J., Li, T., Sun, Q., Guo, Y., Yu, J., Yao, Z., Hou, N., and Hu, B. Automatic Diagnosis of Major Depressive Disorder Using a High-and Low-Frequency Feature Fusion Framework. Brain Sciences 13, 11 (2023), 1590.
[40] Zhao, M., Yan, W., Luo, N., Zhi, D., Fu, Z., Du, Y., Yu, S., Jiang, T., Calhoun, V. D., and Sui, J. An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data. Medical Image Analysis 78 (2022), 102413.
[41] Zhu, Q., Lin, G., Sun, Y., Wu, Y., Zhou, Y., and Feng, Q. Functional magnetic resonance imaging progressive deformable registration based on a cascaded convolutional
neural network. Quantitative Imaging in Medicine and Surgery 11, 8 (2021), 3569.
[2] Akrami, H., Cui, W., Kim, P. E., Heck, C. N., Irimia, A., Jebri, K., Nair, D., Leahy, R. M., and Joshi, A. Prediction of Post Traumatic Epilepsy using MRI-based Imaging Markers. bioRxiv (2024), 2024–01.
[3] Aljobouri, H. K., Jaber, H. A., Kocak, O. M., Algin, O., and Cankaya, I. Clustering fMRI data with a robust unsupervised learning algorithm for neuroscience data mining. Journal of neuroscience methods 299 (2018), 45–54.
[4] Christopher deCharms, R. Applications of real-time fMRI. Nature Reviews Neuro-science 9, 9 (2008), 720–729.
[5] CONN ToolBox. CONN ToolBox. Available at: https://web.conn-toolbox.org/resources/citing-conn.
[6] dos Santos, J. D. M., and dos Santos, J. P. M. Explaining ANN-modeled fMRI Data with Path-Weights and Layer-Wise Relevance Propagation.
[7] Eslami, T., and Saeed, F. Auto-ASD-network: a technique based on deep learning and support vector machines for diagnosing autism spectrum disorder using fMRI data. In Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (2019), pp. 646–651.
[8] Eurostat. Mental health and related issues statistics. Available at: https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Mental health and related issues statistics, 2021.
[9] Fiorenzato, E., Moaveninejad, S., Weis, L., Biundo, R., Antonini, A., and Porcaro, C. Brain Dynamics Complexity as a Signature of Cognitive Decline in Parkinson’s Disease. Movement Disorders (2023).
[10] Frances-Villora, J. V., Bataller-Mompean, M., Mjahad, A., Rosado-Munoz,A., Gutierrez Martin, A., Teruel-Marti, V., Villanueva, V., Hampel, K. G., and Guerrero-Martinez, J. F. Real-time localization of epileptogenic foci EEG signals: an FPGA-based implementation. Applied Sciences 10, 3 (2020), 827.
[11] Jiang, X., Cao, B., Li, C., Jia, L., Jing, Y., Cai, W., Zhao, W., Sun, Q., Wu, F., Kong, L., et al. Identifying misdiagnosed bipolar disorder using support vector machine: feature selection based on fMRI of follow-up confirmed affective disorders. Translational Psychiatry 14, 1 (2024), 9.
[12] Jolliffe, Ian T. Principal component analysis for special types of data. Springer, 2002.
[13] Kwong, K. K. Record of a single fMRI experiment in May of 1991. Neuroimage 62, 2 (2012), 610–612.
[14] Lee, J.-H., Oh, S., Jolesz, F. A., Park, H., and Yoo, S.-S. Application of independent component analysis for the data mining of simultaneous EEG–fMRI: preliminary experience on sleep onset. International Journal of Neuroscience 119, 8 (2009), 1118–
1136.
[15] Lee, M. H., Kim, N., Yoo, J., Kim, H.-K., Son, Y.-D., Kim, Y.-B., Oh, S. M., Kim, S., Lee, H., Jeon, J. E., et al. Multitask fMRI and machine learning approach improve prediction of differential brain activity pattern in patients with insomnia disorder.
Scientific Reports 11, 1 (2021), 9402.
[16] Lin, C., Huang, C.-M., Chang, W., Chang, Y.-X., Liu, H.-L., Ng, S.-H., Lin, H.-L., Lee, T. M.-C., Lee, S.-H., and Wu, S.-C. Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI. Brain and Behavior 14, 1 (2024), e3348.
[17] Liu, R., Huang, Z.-a., Jiang, M., and Tan, K. C. Multi-LSTM networks for accurate classification of ADHD from resting-state fMRI data. In 2020 2nd International Conference on Industrial Artificial Intelligence (IAI) (2020), IEEE, pp. 1–6.
[18] Mahrukh, R., Shakil, S., and Malik, A. S. Sentiments analysis of fMRI using automatically generated stimuli labels under naturalistic paradigm. Scientific Reports 13, 1 (2023), 7267.
[19] Mao, Z., Su, Y., Xu, G., Wang, X., Huang, Y., Yue, W., Sun, L., and Xiong, N. Spatio-temporal deep learning method for ADHD fMRI classification. Information Sciences 499 (2019), 1–11.
[20] MELODIC. Multivariate Exploratory Linear Optimized Decomposition into Independent Components. Available at: https://web.mit.edu/fsl v5.0.10/fsl/doc/wiki/MELODIC.html.
[21] Mikolas, P., Marxen, M., Riedel, P., Br¨ ockel, K., Martini, J., Huth, F., Berndt, C., Vogelbacher, C., Jansen, A., Kircher, T., et al. Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features. Psychological Medicine 54, 2 (2024), 278–288.
[22] Moll, J., Green, S., Deakin, J. F., Thomaz, C. E., Zahn, R., et al. Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression. 1872-7123 (2015).
[23] National Institutes of Mental Health. Mental Disorders in America. Available at: https://www.nimh.nih.gov/health/statistics/mental-illness, 2021.
[24] Ogawa, S. Finding the BOLD effect in brain images. Neuroimage 62, 2 (2012), 608–609.
[25] Pan, N., Qin, K., Patino, L. R., Tallman, M. J., Lei, D., Lu, L., Li, W., Blom, T. J., Bruns, K. M., Welge, J. A., et al. Aberrant brain network topology in youth with a familial risk for bipolar disorder: a task-based fMRI connectome study. Journal of Child Psychology and Psychiatry (2024).
[26] Park, K. M., Kim, K. T., Lee, D. A., Motamedi, G. K., and Cho, Y. W. Structural and functional multilayer network analysis in restless legs syndrome patients. Journal of Sleep Research (2023), e14104.
[27] Penny, W. D., Friston, K. J., Ashburner, J. T., Kiebel, S. J., and Nichols, T. E. Statistical parametric mapping: the analysis of functional brain images. Elsevier, 2011.
[28] Poldrack, R. A. The future of fMRI in cognitive neuroscience. Neuroimage 62, 2 (2012), 1216–1220.
[29] Rashid, M., Singh, H., and Goyal, V. The use of machine learning and deep learning algorithms in functional magnetic resonance imaging—a systematic review. Expert
Systems 37, 6 (2020), e12644.
[30] Regier, D. A., First, M., Marshall, T., and Narrow, W. E. The American Psychiatric Association (APA) classification of mental disorders: strengths, limitations and future perspectives. Psychiatric diagnosis and classification (2002), 47–78.
[31] Reiter, M. A., Jahedi, A., Fredo, A. J., Fishman, I., Bailey, B., and Muller, R.-A. Performance of machine learning classification models of autism using resting- state fMRI is contingent on sample heterogeneity. Neural Computing and Applications
33 (2021), 3299–3310.
[32] Rockville, M. Mental health: A report of the Surgeon General. US Department of Health and Human Services (1999).
[33] Rodrigues, I. D., de Carvalho, E. A., Santana, C. P., and Bastos, G. S. Machine Learning and rs-fMRI to Identify Potential Brain Regions Associated with Autism Severity. Algorithms 15, 6 (2022), 195.
[34] Rolland, X., Maurel, P., and Maumet, C. Towards efficient fMRI data re-use: can we run between-group analyses with datasets processed differently with SPM? In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (2022), IEEE, pp. 1–4.
[35] Saurabh, S., and Gupta, P. Deep learning-based modified bidirectional LSTM network for classification of ADHD disorder. Arabian Journal for Science and Engineering 49, 3 (2024), 3009–3026.
[36] Sethuraman, S. K., Malaiyappan, N., Ramalingam, R., Basheer, S., Rashid, M., and Ahmad, N. Predicting Alzheimer’s Disease Using Deep Neuro-Functional Networks with Resting-State fMRI. Electronics 12, 4 (2023), 1031.
[37] Soros, P., and Witt, K. Book review: Introduction to neuroimaging analysis, 2018.
[38] Sunil, G., Gowtham, S., Bose, A., Harish, S., and Srinivasa, G. Graph neural network and machine learning analysis of functional neuroimaging for understanding schizophrenia. BMC Neuroscience 25, 1 (2024), 2.
[39] Wang, J., Li, T., Sun, Q., Guo, Y., Yu, J., Yao, Z., Hou, N., and Hu, B. Automatic Diagnosis of Major Depressive Disorder Using a High-and Low-Frequency Feature Fusion Framework. Brain Sciences 13, 11 (2023), 1590.
[40] Zhao, M., Yan, W., Luo, N., Zhi, D., Fu, Z., Du, Y., Yu, S., Jiang, T., Calhoun, V. D., and Sui, J. An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data. Medical Image Analysis 78 (2022), 102413.
[41] Zhu, Q., Lin, G., Sun, Y., Wu, Y., Zhou, Y., and Feng, Q. Functional magnetic resonance imaging progressive deformable registration based on a cascaded convolutional
neural network. Quantitative Imaging in Medicine and Surgery 11, 8 (2021), 3569.
Published
2026-05-15
How to Cite
ION, Iulia-Andreea.
Fathoming the Mind: Mental Disorders Predictions Through fMRI Analysis with Machine Learning Algorithms.
Studia Universitatis Babeș-Bolyai Informatica, [S.l.], v. 71, n. 1-2, p. 5-22, may 2026.
ISSN 2065-9601.
Available at: <https://www.cs.ubbcluj.ro/~studia-i/journal/journal/article/view/112>. Date accessed: 09 oct. 2026.
doi: https://doi.org/10.24193/subbi.2026.01.
Issue
Section
Articles
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Transfer of copyright agreement: When the article is accepted for publication, I, as the author and the representative of the coauthors, hereby agree to transfer to Studia Universitatis Babes-Bolyai, Series Informatica, all rights, including those pertaining to electronic forms and transmissions, under existing copyright laws, except for the following, which the authors specifically retain: the authors can use the material however they want as long as it fits the NC ND terms of the license. The authors have all rights for reuse according to the below license.
