Control Systems and Computers

Control Systems and Computers, 2024, Issue 3 (307), pp.

UDC 004.62; 004.8; 616-07

E.I. Aliiev, Postgraduate Student, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi ave., 37, Kyiv, Ukraine, 03056, ORCID: https://orcid.org/0000-0003-2132-9959, e.aliiev-fbmi@lll.kpi.ua

K.S. Bovsunovska, Senior Lecturer, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi ave., 37, Kyiv, 03056, Ukraine, 03056, ORCID: https://orcid.org/0000-0003-0936-2246, period0@ukr.net

I.M. Dykan, Doctor of Medical Sciences, Chief Researcher, Institute of Nuclear Medicine and Diagnostic Radiology of National Academy of Medical Sciences of Ukraine, Platona Maiborody st., 32, Kyiv, Ukraine, 04050, ORCID: https://orcid.org/0000-0001-8544-8653, irinadykan@gmail.com

S.A. Mykhailenko, Student, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi ave., 37, Kyiv, Ukraine, 03056, ORCID: https://orcid.org/0009-0005-8045-7354, svetlanamykhailenko27@gmail.com

O.M. Omelchenko, PhD (Biol.), Institute of Nuclear Medicine and Diagnostic Radiology of National Academy of Medical Sciences of Ukraine, Platona Maiborody st., 32, Kyiv, Ukraine, 04050, ORCID: https://orcid.org/0000-0002-0089-3166, ol.omelchenko@gmail.com

V.A. Pavlov, PhD (Eng.), Associate Professor, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi ave., 37, Kyiv 03056, Ukraine, ORCID: https://orcid.org/0000-0002-3293-5308, pavlov.vladimir264@gmail.com

DETERMINING PREDICTORS FOR PATIENT DIAGNOSIS WITH PTSD USING THE PARAMETERS OF ONE-DIMENSIONAL FIRST-ORDER MODELS FOR BOLD SIGNALS FROM BRAIN STRUCTURES AND GMDH

Introduction. The use of functional magnetic resonance imaging (fMRI) allows for the assessment of processes occurring in the brain. By analyzing the examination results, it is possible to establish the parameters of connections between brain structures, and changes in the values of these parameters can be used as diagnostic conclusion predictors for PTSD-patients.

Purpose. To identify predictors for the classification of the PTSD diagnosis using the connectivity parameters of BOLD signals from brain structures.

Methods. The technology for identifying predictors of PTSD diagnosis is based on a) the formation of connectivity parameters of BOLD signals from brain structures obtained during resting-state scanning, b) the use of classifier-oriented selection based on inter-class variance and mRMR criteria to select informative features, and c) the classification of PTSD diagnosis using a logistic regression algorithm optimized by the Group Method of Data Handling.

Results. The technology proposed in this work enabled the selection of informative features and the identification of their predictive forms, resulting in the formation of classifiers for the diagnosis of PTSD with high accuracy, sensitivity, and specificity.

Conclusion. A technology for the formation, selection, and use of connectivity parameters of BOLD signals from brain structures has been proposed for differentiating healthy individuals from those who suffer with PTSD. A list of the most informative features of PTSD and their predictive forms in the form of generalized variables has been obtained, which can be used for diagnostic conclusions. The results obtained indicate the presence of a specific type of connection between the brain areas identified in the study based on levels of excitation (parameters а₀ of the models) and the alteration of these levels in the context of PTSD.

Download full text! (On Ukrainian)

Keywords: Class-oriented feature selection, diagnostic prediction, PTSD, Group Method of Data Handling, logistic regression.

1. Harnett, N. G. et al. (2021). “Prognostic neuroimaging biomarkers of trauma-related psychopathology: resting-state fMRI shortly after trauma predicts future PTSD and depression symptoms in the AURORA study”. Neuropsychopharmacology [online], 46(7), 1263–1271.: DOI: 10.1038/s41386-020-00946-8.
2. Abrol, A., Hassanzadeh, R., Plis, S. and Calhoun, V. (2021). “Deep learning in resting-state fMRI”. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 1–5 November 2021, Mexico [online]. IEEE. DOI: 10.1109/embc46164.2021.9630257.
3. Hladkyi, Y., Radchenko, O., Pavlov, V., Matviichuk, O. and Horodetska, O. (2023). “A classifier of the Random Forest type based on GMDH, logistic transformation and positional voting”. In: 2023 IEEE 18th International Conference on Computer Science and Information Technologies (CSIT), 19–21 October 2023, Lviv, Ukraine [online]. IEEE. DOI: 10.1109/csit61576.2023.10324054.
4. Matviichuk, O., Nosovets, O., Linnik, M., Davydko, O., Pavlov, V. and Nastenko, I. (2021). “Class-Oriented Features Selection Technology in Medical Images Classification Problem on the Example of Distinguishing Between Tuberculosis Sensitive and Resistant Forms”. In: 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), 22–25 September 2021, LVIV, Ukraine [online]. IEEE. DOI: 10.1109/csit52700.2021.9648747.
5. Zandvakili, A., Barredo, J., Swearingen, H. R., Aiken, E. M., Berlow, Y. A., Greenberg, B. D., Carpenter, L. L. and Philip, N. S. (2020). “Mapping PTSD symptoms to brain networks: a machine learning study”. Translational Psychiatry [online]. 10(1). DOI: 10.1038/s41398-020-00879-2.
6. Sheynin, S., Wolf, L., Ben-Zion, Z., Sheynin, J., Reznik, S., Keynan, J. N., Admon, R., Shalev, A., Hendler, T. and Liberzon, I. (2021). “Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors”. NeuroImage [online]. 238, Article DOI: 10.1016/j.neuroimage.2021.118242.
7. Liu, F., Xie, B., Wang, Y., Guo, W., Fouche, J.-P., Long, Z., Wang, W., Chen, H., Li, M., Duan, X., Zhang, J., Qiu, M. and Chen, H. (2014). “Characterization of Post-traumatic Stress Disorder Using Resting-State fMRI with a Multi-level Parametric Classification Approach”. Brain Topography [online]. 28(2), 221–237. DOI: 10.1007/s10548-014-0386-2.
8. Zhang, Q., Yu, Y., Chen, W., Chen, T., Zhou, Y. and Li, H. (2016). “Outdoor experiment of flexible sandwiched graphite-PET sheets based self-snow-thawing pavement”. Cold Regions Science and Technology [online]. 122, 10–17. DOI: 10.1016/j.coldregions.2015.10.016.
9. Zhu, Z., Lei, D., Qin, K., Suo, X., Li, W., Li, L., DelBello, M. P., Sweeney, J. A. and Gong, Q. (2021). “Combining Deep Learning and Graph-Theoretic Brain Features to Detect Posttraumatic Stress Disorder at the Individual Level”. Diagnostics [online]. 11(8), 1416. DOI: 10.3390/diagnostics11081416.
10. Yang, J. (2021). “An Integrative Review of Simulation used in Psychiatric Nursing Education: Focusing on Psychiatric Nursing Learning Objectives and Core Competencies of Nurses”. Korean Association For Learner-Centered Curriculum And Instruction [online]. 21(7), 535–548. DOI: 10.22251/jlcci.2021.21.7.535.
11. Saba, T., Rehman, A., Shahzad, M. N., Latif, R., Bahaj, S. A. and Alyami, J. (2022). “Machine learning for post-traumatic stress disorder identification utilizing resting-state functional magnetic resonance imaging”. Microscopy Research and Technique [online]. DOI: 10.1002/jemt.24065.
12. Harricharan, S., Nicholson, A.A., Thome, J., Densmore, M., McKinnon, M.C., Théberge, J., Frewen, P.A., Neufeld, R.W.J. and Lanius, R.A. (2019). “PTSD and its dissociative subtype through the lens of the insula: Anterior and posterior insula resting-state functional connectivity and its predictive validity using machine learning”. Psychophysiology [online]. 57(1). DOI: 10.1111/psyp.13472.
13. Nicholson, A.A., Densmore, M., McKinnon, M.C., Neufeld, R.W.J., Frewen, P.A., Theberge, J., Jetly, R., Richardson, J.D. and Lanius, R.A. (2018). “Machine learning multivariate pattern analysis predicts classification of posttraumatic stress disorder and its dissociative subtype: a multimodal neuroimaging approach”. Psychological Medicine [online]. 49(12), 2049–2059. DOI: 10.1017/s0033291718002866.
14. Zhu, H., Yuan, M., Qiu, C., Ren, Z., Li, , Wang, J., Huang, X., Lui, S., Gong, Q., Zhang, W. and Zhang, Y. (2020). “Multivariate classification of earthquake survivors with post-traumatic stress disorder based on large-scale brain networks”. Acta Psychiatrica Scandinavica [online]. 141(3), pp. 285–298. DOI: 10.1111/acps.13150.
15. Qing, Z., Zhang, X., Ye, M., Wu, S., Wang, X., Nedelska, Z., Hort, J., Zhu, B. and Zhang, B. (2019). “The Impact of Spatial Normalization Strategies on the Temporal Features of the Resting-State Functional MRI: Spatial Normalization Before rs-fMRI Features Calculation May Reduce the Reliability”. Frontiers in Neuroscience [online]. 13. DOI: 10.3389/fnins.2019.01249.
16. Behzadi, Y., Restom, K., Liau, J. and Liu, T.T. (2007). “A component based noise correction method (CompCor) for BOLD and perfusion based fMRI”. NeuroImage [online]. 37(1), 90–101. DOI: 10.1016/j.neuroimage.2007.04.042.
17. Friston, K. J., Holmes, A. P., Poline, J.-B., Grasby, P.J., Williams, S.C.R., Frackowiak, R.S.J. and Turner, R., (1995). “Analysis of fMRI Time-Series Revisited”. NeuroImage [online]. 2(1), 45–53. DOI: 10.1006/nimg.1995.1007.
18. Giff, A., Noren, G., Magnotti, J., Lopes, A.C., Batistuzzo, M.C., Hoexter, M., Greenberg, B., Marsland, R., Miguel, E.C., Rasmussen, S. and McLaughlin, N. (2023). “Spatial normalization discrepancies between native and MNI152 brain template scans in gamma ventral capsulotomy patients”. Psychiatry Research: Neuroimaging [online]. 329, 111595. DOI: 10.1016/j.pscychresns.2023.111595.
19. Mowinckel, A. M. and Vidal-Piñeiro, D. (2020). “Visualization of Brain Statistics With R Packages ggseg and ggseg3d”. Advances in Methods and Practices in Psychological Science [online]. 3(4), 466–483. DOI: 10.1177/2515245920928009.
20. Hilger, K., Winter, N.R., Leenings, R., Sassenhagen, J., Hahn, T., Basten, U. and Fiebach, C.J. (2020). “Predicting intelligence from brain gray matter volume”. Brain Structure and Function [online]. 225(7), 2111–2129. DOI: 10.1007/s00429-020-02113-7.
21. Wu, C.Q., Cowan, F.M., Jary, S., Thoresen, M., Chakkarapani, E. and Spencer, A.P.C. (2023). “Cerebellar growth, volume and diffusivity in children cooled for neonatal encephalopathy without cerebral palsy”. Scientific Reports [online]. 13(1). DOI: 10.1038/s41598-023-41838-3.
22. Nieto-Castanon, A. (2020). “FMRI minimal preprocessing pipeline”. In: Handbook of functional connectivity Magnetic Resonance Imaging methods in CONN [online]. Hilbert Press. pp. 3–16. DOI: 10.56441/hilbertpress.2207.6599.
23. Morfini, F., Whitfield-Gabrieli, S. and Nieto-Castanon, A. (2023). “Functional connectivity MRI quality control procedures in CONN”. Frontiers in Neuroscience [online]. 17. DOI: 10.3389/fnins.2023.1092125.
24. Khalaf, G. (2022). “Improving the Ordinary Least Squares Estimator by Ridge Regression”. OALib [online]. 9(05), 1–8. DOI: 10.4236/oalib.1108738.
25. Hallquist, M.N., Hwang, K. and Luna, B. (2013). “The nuisance of nuisance regression: Spectral misspecification in a common approach to resting-state fMRI preprocessing reintroduces noise and obscures functional connectivity”. NeuroImage [online]. 82, 208–225. DOI: 10.1016/j.neuroimage.2013.05.116.
26. Nieto-Castanon, A., (2020). “FMRI denoising pipeline”. In: Handbook of functional connectivity Magnetic Resonance Imaging methods in CONN [online]. Hilbert Press. pp. 17–25. DOI: 10.56441/hilbertpress.2207.6600.
27. Whitfield-Gabrieli, S. and Nieto-Castanon, A. (2012). “Conn: A Functional Connectivity Toolbox for Correlated and Anticorrelated Brain Networks”. Brain Connectivity [online]. 2(3), 125–141. DOI: 10.1089/brain.2012.0073.

Received 26.07.2024