Graph Machine Learning (GraphML) para la detección temprana de riesgos para la salud mental: una revisión sistemática de literatura
DOI:
https://doi.org/10.61347/ei.v5i2.400Palabras clave:
Aprendizaje automático sobre grafos, depresión, detección temprana, Graph Machine Learning, redes neuronales sobre grafosResumen
La detección temprana de riesgos en salud mental constituye un desafío debido a la complejidad de las relaciones entre factores clínicos, conductuales y contextuales. El objetivo de esta investigación fue sintetizar y analizar la evidencia científica sobre la aplicación de Graph Machine Learning (GraphML) en la detección temprana de riesgos en salud mental, considerando las arquitecturas utilizadas, los trastornos abordados, las métricas de desempeño, las estrategias de validación y las principales limitaciones. Se realizó una revisión sistemática siguiendo las directrices PRISMA 2020, mediante búsquedas en Scopus y Web of Science de estudios originales publicados entre 2021 y 2026. Tras aplicar los criterios de elegibilidad y evaluar el riesgo de sesgo mediante la herramienta PROBAST, se incluyeron 27 estudios en la síntesis cualitativa. Los resultados evidenciaron un predominio de arquitecturas basadas en redes convolucionales de grafos (GCN), seguidas de redes de atención de grafos (GAT), GraphSAGE y modelos híbridos multimodales, aplicados principalmente a depresión, ansiedad, estrés e ideación suicida. Las métricas más utilizadas fueron exactitud, F1-score y área bajo la curva (AUC), con resultados predictivos favorables, especialmente en modelos que integraron datos clínicos, neuroimágenes, señales fisiológicas e información digital. Sin embargo, se identificaron limitaciones relacionadas con la validación externa, el desequilibrio de clases, la heterogeneidad de los datos y la interpretabilidad. Se concluyó que GraphML presenta potencial para apoyar la detección temprana de riesgos en salud mental, aunque su aplicación clínica requiere mayor validación multicéntrica, explicabilidad y reproducibilidad metodológica.
Descargas
Citas
Ali, O., Abdelbaki, W., Shrestha, A., Elbasi, E., Alryalat, M., & Dwivedi, Y. (2023). A systematic literature review of artificial intelligence in the healthcare sector: Benefits, challenges, methodologies, and functionalities. Journal of Innovation & Knowledge, 8(1), 100333. https://doi.org/10.1016/j.jik.2023.100333
Boll, H., Amirahmadi, A., Ghazani, M., de Morais, W., de Freitas, E., Soliman, A., Etminani, F., Byttner, S., & Recamonde-Mendoza, M. (2024). Graph neural networks for clinical risk prediction based on electronic health records: A survey. Journal of Biomedical Informatics, 151, 104616. https://doi.org/10.1016/j.jbi.2024.104616
Bollen, J., ten Thij, M., Lorenzo-Luaces, L., & Rutter, L. (2022). Beyond risk: Individual mental health trajectories from large-scale social media data. In F. Crestani, D. E. Losada, & J. Parapar (Eds.), Early detection of mental health disorders by social media monitoring: The first five years of the eRisk project (pp. 265–287). Springer International Publishing. https://doi.org/10.1007/978-3-031-04431-1_12
Cao, M., Yang, M., Qin, C., Zhu, X., Chen, Y., Wang, J., & Liu, T. (2021). Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data. Biomedical Signal Processing and Control, 70, 103015. https://doi.org/10.1016/j.bspc.2021.103015
Chan, Y. H., Girish, D., Gupta, S., Xia, J., Kasi, C., He, Y., Wang, C., & Rajapakse, J. C. (2025). Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review. NeuroImage, 319, 121422. https://doi.org/10.1016/j.neuroimage.2025.121422
Chen, W., Yang, J., Sun, Z., Zhang, X., Tao, G., Ding, Y., Gu, J., Bu, J., & Wang, H. (2024). DeepASD: A deep adversarial-regularized graph learning method for ASD diagnosis with multimodal data. Translational Psychiatry, 14(1), 375. https://doi.org/10.1038/s41398-024-02972-2
Chen, Z., Wu, J., Pu, L., Li, S., Zhang, Y., Yao, D., & Yan, H. (2026). MAF-GNN: Graph neural network-based multi-atlas brain functional information fusion for major depressive disorder diagnosis with rs-fMRI. Information Processing & Management, 63(3), 104524. https://doi.org/10.1016/j.ipm.2025.104524
Cripps, R., Hayes, J., Pitman, A., Osborn, D., & Werbeloff, N. (2020). Characteristics and risk of repeat suicidal ideation and self-harm in patients who present to emergency departments with suicidal ideation or self-harm: A prospective cohort study. Journal of Affective Disorders, 273, 358–363. https://doi.org/10.1016/j.jad.2020.03.130
Cruz-Gonzalez, P., He, A., Lam, E., Ng, I., Li, M., Hou, R., Chan, J., Sahni, Y., Guasch, N., Miller, T., Lau, B., & Vidaña, D. (2025). Artificial intelligence in mental health care: A systematic review of diagnosis, monitoring, and intervention applications. Psychological Medicine, 55, e18. https://doi.org/10.1017/S0033291724003295
Dong, G., Tang, M., Cai, L., Barnes, L., & Boukhechba, M. (2021). Semi-supervised graph instance transformer for mental health inference. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1221–1228). IEEE. https://doi.org/10.1109/ICMLA52953.2021.00198
Du, Z. (2024). Research on the synergistic nurturing mechanism of ideological work and student management in colleges and universities under the binary structure. Applied Mathematics and Nonlinear Sciences, 9(1), 1–18. https://doi.org/10.2478/amns.2023.2.01485
Fisher, H., Jaffe, N., Pidvirny, K., Tierney, A., Vaidean, M., Dongre, P., & Webb, C. (2026). Language-based detection of depression with machine learning: Systematic review and meta-analysis. npj Digital Medicine, 9(1), 273. https://doi.org/10.1038/s41746-026-02448-1
Fu, C., Qian, F., Su, Y., Su, K., Song, S., Niu, M., Shi, J., Liu, Z., Liu, C., Ishi, C., & Ishiguro, H. (2025). Facial action units guided graph representation learning for multimodal depression detection. Neurocomputing, 619, 129106. https://doi.org/10.1016/j.neucom.2024.129106
He, M., Bakker, E., & Lew, M. (2024). DPD (DePression Detection) Net: A deep neural network for multimodal depression detection. Health Information Science and Systems, 12(1), 53. https://doi.org/10.1007/s13755-024-00311-9
Ibitoye, A., Ravindran, S., Afe, O., & Abiodun, A. (2025). Predicting digital addiction patterns with machine learning for personalised mental health support. Journal of Social Computing, 6(4), 359–377. https://doi.org/10.23919/JSC.2025.0020
Jena, M., Khan, N., Lee, M., & Rho, S. (2026). Neuro-symbolic graph learning for causal inference and continual learning in mental-health risk assessment. Computer Modeling in Engineering & Sciences, 146(1), 44. https://doi.org/10.32604/cmes.2025.075119
Jiang, D. (2026). Predicting student mental health through entropy-based features and interpretable cross-attention transformer networks. PLOS ONE, 21(4), e0347294. https://doi.org/10.1371/journal.pone.0347294
Kanakala, S., Prashanthi, V., Chinnaiah, V., Sharada, K., & Sumalatha, M. (2025). FMindMonitorAI: An AI-driven framework for social media-based mental health analysis using MindFusionNet. International Research Journal of Multidisciplinary Scope, 6(3), 1587–1610. https://doi.org/10.47857/irjms.2025.v06i03.04620
Kavitha, P., & Shakkeera, L. (2026). 2D-CNN-GACL-ECGNet graph attention: A robust framework for electrocardiogram-based stress detection. IAES International Journal of Artificial Intelligence (IJ-AI), 15(2), 1529–1538. https://doi.org/10.11591/ijai.v15.i2.pp1529-1538
Kim, J., & Sohn, M. (2022). Graph representation learning-based early depression detection framework in smart home environments. Sensors, 22(4), 1545. https://doi.org/10.3390/s22041545
Kim, S., Bong, S., Yun, S., Kim, D., Yoo, J., Choi, K., Park, H., Jeon, H., Kim, J., Jang, J., & Jeong, B. (2025). Neurobiologically interpretable causal connectome for predicting young adult depression: A graph neural network study. Journal of Affective Disorders, 377, 225–234. https://doi.org/10.1016/j.jad.2025.02.076
Knipe, D., Padmanathan, P., Newton-Howes, G., Chan, L., & Kapur, N. (2022). Suicide and self-harm. The Lancet, 399(10338), 1903–1916. https://doi.org/10.1016/S0140-6736(22)00173-8
Li, L., Jiang, H., Wen, G., Cao, P., Xu, M., Liu, X., Yang, J., & Zaiane, O. (2022). TE-HI-GCN: An ensemble of transfer hierarchical graph convolutional networks for disorder diagnosis. Neuroinformatics, 20(2), 353–375. https://doi.org/10.1007/s12021-021-09548-1
Li, L., Wen, G., Cao, P., Liu, X., Zaiane, O. R., & Yang, J. (2023). Exploring interpretable graph convolutional networks for autism spectrum disorder diagnosis. International Journal of Computer Assisted Radiology and Surgery, 18(4), 663–673. https://doi.org/10.1007/s11548-022-02780-3
Lin, J., Tian, J., Wang, T., Li, D., & Jiang, X. (2025). Psychological crisis detection based on behavioral data: A new approach to non-contact measurement. BMC Psychology, 13(1), 1355. https://doi.org/10.1186/s40359-025-03604-0
Liu, R., Hou, X., Liu, S., Zhou, Y., Zhou, J., Qiao, K., Qi, H., Li, R., Yang, Z., Zhang, L., Cui, J., Jin, C., Yu, A., & Wang, G. (2025). Predicting antidepressant response via local-global graph neural network and neuroimaging biomarkers. npj Digital Medicine, 8(1), 515. https://doi.org/10.1038/s41746-025-01912-8
Liu, Y. (2024). Depression detection via a Chinese social media platform: A novel causal relation-aware deep learning approach. The Journal of Supercomputing, 80(8), 10327–10356. https://doi.org/10.1007/s11227-023-05830-y
Liu, Y., Zheng, J., Zeng, Y., Luo, F., & Tian, X. (2025). Graph learning based suicidal ideation detection via tree-drawing test. Frontiers in Psychiatry, 16, 1617650. https://doi.org/10.3389/fpsyt.2025.1617650
Mansoor, M., & Ansari, K. (2024). Early detection of mental health crises through artificial-intelligence-powered social media analysis: A prospective observational study. Journal of Personalized Medicine, 14(9), 958. https://doi.org/10.3390/jpm14090958
Mo, H., Wu, H., Rong, Q., Hu, Z., Yi, M., & Chen, P. (2025). An anxiety screening framework integrating multimodal data and graph node correlation. Artificial Intelligence in Medicine, 167, 103189. https://doi.org/10.1016/j.artmed.2025.103189
Moser, M., Ehrhart, M., & Resch, B. (2024). An explainable deep learning approach for stress detection in wearable sensor measurements. Sensors, 24(16), 5085. https://doi.org/10.3390/s24165085
Nordin, N., Zainol, Z., Mohd Noor, M., & Chan, L. (2022). Suicidal behaviour prediction models using machine learning techniques: A systematic review. Artificial Intelligence in Medicine, 132, 102395. https://doi.org/10.1016/j.artmed.2022.102395
Okesanya, O., Oso, T., Hassan, M., Adebayo, U., Vandy, A., Othman, Z., Ali, I., Ahmed, M., Musa, S., Eshun, G., & Lucero-Prisno, D., III. (2026). Applications of artificial intelligence and machine learning in the diagnosis and management of major depressive disorder: A systematic review. The Egyptian Journal of Neurology, Psychiatry and Neurosurgery, 62(1), 89. https://doi.org/10.1186/s41983-026-01156-7
Page, M., McKenzie, J., Bossuyt, P., Boutron, I., Hoffmann, T., Mulrow, C., Shamseer, L., Tetzlaff, J., Akl, E., Brennan, S., Chou, R., Glanville, J., Grimshaw, J., Hróbjartsson, A., Lalu, M., Li, T., Loder, E., Mayo-Wilson, E., McDonald, S., … Moher, D. (2021). The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ, 372, n71. https://doi.org/10.1136/bmj.n71
Park, Y., Park, S., & Lee, M. (2024). Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review. Journal of Affective Disorders, 361, 445–456. https://doi.org/10.1016/j.jad.2024.06.035
Patro, K., Routray, S., Madan Kumar, C., Kranthi Kumar, L., Rao, M., & Kottala, R. (2026). Att-MSR-GraphSAGE: An attention-guided multi-scale residual graph neural network for human-centric stress-factor modeling. IEEE Access, 14, 37435–37450. https://doi.org/10.1109/ACCESS.2026.3671315
Paul, S., Saha, A., Hasan, M., Noori, S., & Moustafa, A. (2024). A systematic review of graph neural network in healthcare-based applications: Recent advances, trends, and future directions. IEEE Access, 12, 15145–15170. https://doi.org/10.1109/ACCESS.2024.3354809
Pigoni, A., Delvecchio, G., Turtulici, N., Madonna, D., Pietrini, P., Cecchetti, L., & Brambilla, P. (2024). Machine learning and the prediction of suicide in psychiatric populations: A systematic review. Translational Psychiatry, 14(1), 140. https://doi.org/10.1038/s41398-024-02852-9
Pinge, A., Gad, V., Jaisighani, D., Ghosh, S., & Sen, S. (2024). Detection and monitoring of stress using wearables: A systematic review. Frontiers in Computer Science, 6, 1478851. https://doi.org/10.3389/fcomp.2024.1478851
Polowczyk, A., Polowczyk, A., & Woźniak, M. (2026). Mental illness text classification based on late fusion combining BERT with Apriori-informed graph attention network. Computer Standards & Interfaces, 98, 104157. https://doi.org/10.1016/j.csi.2026.104157
Priyadarshana, Y., Liang, Z., & Piumarta, I. (2025). GEM: Graph attention encoder for multi-task depression severity detection in multi-party conversations. Social Network Analysis and Mining, 15(1), 76. https://doi.org/10.1007/s13278-025-01495-y
Razavi, M., Ziyadidegan, S., Mahmoudzadeh, A., Kazeminasab, S., Baharlouei, E., Janfaza, V., Jahromi, R., & Sasangohar, F. (2024). Machine learning, deep learning, and data preprocessing techniques for detecting, predicting, and monitoring stress and stress-related mental disorders: Scoping review. JMIR Mental Health, 11, e53714. https://doi.org/10.2196/53714
Ruan, Y., Liang, H., Yamamoto, S., & Lin, S. (2026). Machine learning in mental health promotion for older adults: A scoping review. BMC Geriatrics, 26, 821. https://doi.org/10.1186/s12877-026-07543-2
Shi, X., Pan, J., Yuan, D., Li, M., & Pan, Y. (2025). Advanced data analysis and prediction model for student mental health risk assessment. Frontiers in Psychology, 16, 1682083. https://doi.org/10.3389/fpsyg.2025.1682083
Vaida, M., & Huang, Z. (2026). Multimodal graph neural networks in healthcare: A review of fusion strategies across biomedical domains. Frontiers in Artificial Intelligence, 8, 1716706. https://doi.org/10.3389/frai.2025.1716706
Vidal, J., Iglesias, C., & Montenegro, I. (2025). Sesgos en la inteligencia artificial en el sector salud: Una revisión sistemática en el contexto iberoamericano. Revista Iberoamericana de la Propiedad Intelectual, (22), 123–154. https://doi.org/10.26422/RIPI.2025.2200.bar
Wang, S., Zhang, J., Zhang, R., Li, Z., Zhang, C., Zhao, Z., Pang, T., Gao, Z., Wang, Z., Yu, Y., Ren, W., & Wang, C. (2026). MAMF-GCN model for anxious and non-anxious depression classification and neuroimaging marker recognition. International Journal of Psychophysiology, 219, 113301. https://doi.org/10.1016/j.ijpsycho.2025.113301
Weber, M. (2025). Geometric machine learning. AI Magazine, 46(1), e12210. https://doi.org/10.1002/aaai.12210
Yokotani, K., Takano, M., Abe, N., & Kato, T. (2025). Predicting social anxiety disorder based on communication logs and social network data from a massively multiplayer online game: Using a graph neural network. Psychiatry and Clinical Neurosciences, 79(5), 274–281. https://doi.org/10.1111/pcn.13804
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57–81. https://doi.org/10.1016/j.aiopen.2021.01.001
Zhou, N., Yuan, Z., Zhou, H., Lyu, D., Wang, F., Wang, M., Lu, Z., Huang, Q., Chen, Y., Huang, H., Cao, T., Wu, C., Yang, W., & Hong, W. (2025). Using dynamic graph convolutional network to identify individuals with major depression disorder. Journal of Affective Disorders, 371, 188–195. https://doi.org/10.1016/j.jad.2024.11.035
Zhu, M., Quan, Y., & He, X. (2023). The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network. Frontiers in Human Neuroscience, 17, 1094592. https://doi.org/10.3389/fnhum.2023.1094592
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 Jorge Edwin Delgado Altamirano, Ciro Rodriguez Rodriguez
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
