Predicting psychological resilience and mental health from multimodal wearable sensor data using graph neural networks
Abstract
Early diagnosis of mental vulnerability is still a problem since most clinical evaluations are based on the subjective aspects of evaluation like self-report and not on the objective physiological indications. The idea of psychological resilience which is a fundamental protective factor against stress related disorders has been connected to the autonomic regulation and daily behavioral patterns, but the objective method of calculating on such a scale is yet to be established. This paper presents a multimodal graph neural network, which combines the wearable derived physiological signals to forecast trait level resilience and stress as well as state level. The ongoing heart activity, electrodermal activity, and motion data of adult participants were gathered and matched with resilient score proven validated scores. Participant specific graphs were created whereby physiological modalities were the nodes and the inter signal dependencies were the edges. Statistical analysis showed that there were significant physiological disparities that were related to resilience. High resilience group members had much better values of root mean square of successive differences and physical activity per day (mean difference on 1000 extra steps per day, p = 0.003). The proposed graph neural network (GNN) performed well in classification tasks in terms of area under the receiver operating characteristic curve (0.80 +- 0.02) to differentiate high and low resilience, which was significantly better than that of logistic regression (0.60), random forest (0.65), and long short-term memory models (0.72), with the difference being supported by DeLong test (p < 0.01). Graph based learning also offers added benefits of discrimination and physiologically explainable output and thus can facilitate its future as a scalable and objective digital mental health monitoring and early risk stratification tool.
Full text article
References
[1] Morales-Rodríguez FM, Martínez-Ramón JP, Méndez I, Ruiz-Esteban C. Stress, coping, and resilience before and after COVID-19: A predictive model based on artificial intelligence in the university environment. Frontiers in Psychology. 2021 May 4;12:647964. https://doi.org/10.3389/fpsyg.2021.647964
[2] Zhu R, Zhao K, Yang H, Lin W, Zhou C, Ai B, Li Y, Zhou J. Aligraph: A comprehensive graph neural network platform. arXiv preprint arXiv:1902.08730. 2019 Feb 23. https://doi.org/10.14778/3352063.3352127
[3] Gessl AS, Schlögl S, Mevenkamp N. On the perceptions and acceptance of artificially intelligent robotics and the psychology of the future elderly. Behaviour & Information Technology. 2019 Nov 2;38(11):1068-87. https://doi.org/10.1080/0144929X.2019.1566499
[4] Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems. 2019;32.
[5] You J, Ying R, Leskovec J. Position-aware graph neural networks. InInternational conference on machine learning 2019 May 24 (pp. 7134-7143). PMLR.
[6] Hu Q, Lu Y, Pan Z, Wang B. How does AI use drive individual digital resilience? A conservation of resources (COR) theory perspective. Behaviour & Information Technology. 2023 Nov 18;42(15):2654-73. https://doi.org/10.1080/0144929X.2022.2137698
[7] Rane N, Choudhary S, Rane J. Artificial intelligence for enhancing resilience. Journal of Applied Artificial Intelligence. 2024 Sep 9;5(2):1-33. https://doi.org/10.48185/jaai.v5i2.1053
[8] Xhonneux LP, Qu M, Tang J. Continuous graph neural networks. InInternational conference on machine learning 2020 Nov 21 (pp. 10432-10441). PMLR.
[9] Martínez-Ramón JP, Morales-Rodríguez FM, Pérez-López S. Burnout, resilience, and COVID-19 among teachers: predictive capacity of an artificial neural network. Applied Sciences. 2021 Sep 3;11(17):8206. https://doi.org/10.3390/app11178206
[10] Nooripour R, Hosseinian S, Hussain AJ, Annabestani M, Maadal A, Radwin LE, Hassani-Abharian P, Pirkashani NG, Khoshkonesh A. How resiliency and hope can predict stress of Covid-19 by mediating role of spiritual well-being based on machine learning. Journal of religion and health. 2021 Aug;60(4):2306-21. https://doi.org/10.1007/s10943-020-01151-z
[11] Wang X, Zhang M. How powerful are spectral graph neural networks. InInternational conference on machine learning 2022 Jun 28 (pp. 23341-23362). PMLR.
[12] Liu M, Gao H, Ji S. Towards deeper graph neural networks. InProceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining 2020 Aug 23 (pp. 338-348). https://doi.org/10.1145/3394486.3403076
[13] Dwivedi VP, Joshi CK, Luu AT, Laurent T, Bengio Y, Bresson X. Benchmarking graph neural networks. Journal of Machine Learning Research. 2023;24(43):1-48.
[14] Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. Computational capabilities of graph neural networks. IEEE Transactions on Neural Networks. 2008 Dec 9;20(1):81-102. https://doi.org/10.1109/TNN.2008.2005141
[15] Bessadok A, Mahjoub MA, Rekik I. Graph neural networks in network neuroscience. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022 Sep 26;45(5):5833-48. https://doi.org/10.1109/TPAMI.2022.3209686
[16] Gao C, Zheng Y, Li N, Li Y, Qin Y, Piao J, Quan Y, Chang J, Jin D, He X, Li Y. A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems. 2023 Mar 3;1(1):1-51. https://doi.org/10.1145/3568022
[17] Wu L, Chen Y, Shen K, Guo X, Gao H, Li S, Pei J, Long B. Graph neural networks for natural language processing: A survey. Foundations and Trends in Machine Learning. 2023 Jan 25;16(2):119-328. https://doi.org/10.1561/2200000096
[18] Liao W, Bak-Jensen B, Pillai JR, Wang Y, Wang Y. A review of graph neural networks and their applications in power systems. Journal of Modern Power Systems and Clean Energy. 2021 Aug 20;10(2):345-60. https://doi.org/10.35833/MPCE.2021.000058
[19] Luan S, Hua C, Lu Q, Zhu J, Zhao M, Zhang S, Chang XW, Precup D. Revisiting heterophily for graph neural networks. Advances in neural information processing systems. 2022 Dec 6;35:1362-75.
[20] Rusch TK, Bronstein MM, Mishra S. A survey on oversmoothing in graph neural networks. arXiv preprint arXiv:2303.10993. 2023 Mar 20.
[21] Zeng X, Li S, Yousaf Z. Artificial intelligence adoption and digital innovation: how does digital resilience act as a mediator and training protocols as a moderator?. Sustainability. 2022 Jul 6;14(14):8286. https://doi.org/10.3390/su14148286
[22] Kong H, Jiang X, Zhou X, Baum T, Li J, Yu J. Influence of artificial intelligence (AI) perception on career resilience and informal learning. Tourism Review. 2024 Jan 18;79(1):219-33. https://doi.org/10.1108/TR-10-2022-0521
[23] Zheng X, Wang Y, Liu Y, Li M, Zhang M, Jin D, Yu PS, Pan S. Graph neural networks for graphs with heterophily: A survey. arXiv preprint arXiv:2202.07082. 2022 Feb 14.
[24] Fan W, Ma Y, Li Q, He Y, Zhao E, Tang J, Yin D. Graph neural networks for social recommendation. InThe world wide web conference 2019 May 13 (pp. 417-426). https://doi.org/10.1145/3308558.3313488
[25] Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems. 2020 Mar 24;32(1):4-24. https://doi.org/10.1109/TNNLS.2020.2978386
[26] Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. The graph neural network model. IEEE transactions on neural networks. 2008 Dec 9;20(1):61-80. https://doi.org/10.1109/TNN.2008.2005605
[27] Corso G, Stark H, Jegelka S, Jaakkola T, Barzilay R. Graph neural networks. Nature Reviews Methods Primers. 2024 Mar 7;4(1):17. https://doi.org/10.1038/s43586-024-00294-7
[28] Li Y, Cao F, Cao D, Liu J. Nursing students' post‐traumatic growth, emotional intelligence and psychological resilience. Journal of psychiatric and mental health nursing. 2015 Jun;22(5):326-32. https://doi.org/10.1111/jpm.12192
[29] Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks?. arXiv preprint arXiv:1810.00826. 2018 Oct 1.
[30] Veličković P. Everything is connected: Graph neural networks. Current Opinion in Structural Biology. 2023 Apr 1;79:102538. https://doi.org/10.1016/j.sbi.2023.102538
[31] Wu L, Cui P, Pei J, Zhao L, Guo X. Graph neural networks: foundation, frontiers and applications. InProceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining 2022 Aug 14 (pp. 4840-4841). https://doi.org/10.1145/3534678.3542609
[32] Liu Z, Zhou J. Introduction to graph neural networks. Springer Nature; 2022 May 31. https://doi.org/10.1007/978-981-16-6054-2_17
[33] Shchur O, Mumme M, Bojchevski A, Günnemann S. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868. 2018 Nov 14.
[34] Zhu J, Rossi RA, Rao A, Mai T, Lipka N, Ahmed NK, Koutra D. Graph neural networks with heterophily. InProceedings of the AAAI conference on artificial intelligence 2021 May 18 (Vol. 35, No. 12, pp. 11168-11176). https://doi.org/10.1609/aaai.v35i12.17332
[35] Reiser P, Neubert M, Eberhard A, Torresi L, Zhou C, Shao C, Metni H, van Hoesel C, Schopmans H, Sommer T, Friederich P. Graph neural networks for materials science and chemistry. Communications Materials. 2022 Nov 26;3(1):93. https://doi.org/10.1038/s43246-022-00315-6
[36] Agarwal C, Queen O, Lakkaraju H, Zitnik M. Evaluating explainability for graph neural networks. Scientific Data. 2023 Mar 18;10(1):144. https://doi.org/10.1038/s41597-023-01974-x
[37] Terblanche N, Molyn J, De Haan E, Nilsson VO. Coaching at Scale: Investigating the Efficacy of Artificial Intelligence Coaching. International Journal of Evidence Based Coaching & Mentoring. 2022 Jun 1;20(2).
[38] Pentina I, Xie T, Hancock T, Bailey A. Consumer-machine relationships in the age of artificial intelligence: Systematic literature review and research directions. Psychology & Marketing. 2023 Aug;40(8):1593-614. https://doi.org/10.1002/mar.21853
[39] de Terte I, Stephens C, Huddleston L. The development of a three part model of psychological resilience. Stress and Health. 2014 Dec;30(5):416-24. https://doi.org/10.1002/smi.2625
[40] Dohale V, Akarte M, Gunasekaran A, Verma P. Exploring the role of artificial intelligence in building production resilience: learnings from the COVID-19 pandemic. International Journal of Production Research. 2024 Aug 2;62(15):5472-88. https://doi.org/10.1080/00207543.2022.2127961
[41] Wingo AP, Fani N, Bradley B, Ressler KJ. Psychological resilience and neurocognitive performance in a traumatized community sample. Depression and anxiety. 2010 Aug;27(8):768-74. https://doi.org/10.1002/da.20675
[42] Gooding PA, Hurst A, Johnson J, Tarrier N. Psychological resilience in young and older adults. International journal of geriatric psychiatry. 2012 Mar;27(3):262-70. https://doi.org/10.1002/gps.2712
Authors
Copyright (c) 2025 International Journal of Applied Resilience and Sustainability (IJARS) 
This work is licensed under a Creative Commons Attribution 4.0 International License.