Choice of machine learning models for predicting the development of psychological disorders in people with hypothireosis and hyperthireosis
DOI:
https://doi.org/10.30837/2522-9818.2024.2.076Keywords:
hypothyroidism; hyperthyroidism; psychological disorders; forecasting; linear additive convolution; Pareto principle; random forest; decision tree; Gini index.Abstract
The subject of this article is endocrinological diseases, namely, the analysis of complications in people with hypothyroidism and hyperthyroidism. It is known that these diseases occur asymptomatically or in a way that may indicate other possible diseases, so people do not suspect what exactly they are suffering from. Later, the diseases develop to the point where complications occur in the body, some of the most dangerous of which are psychological disorders: depression, mania, aggression, etc. Therefore, the aim of this work is to develop methods for predicting the occurrence of neurological deterioration in people who have already been diagnosed with endocrinological diseases. The article solves the problem of choosing the best models for predicting the occurrence of psychological disorders in people with endocrinological problems. Machine learning methods that are widespread in the medical field were analyzed and one of them was chosen that more optimally solves all the tasks of the task. The selection of criteria took into account potential problems with medical and psychological data. The method used was linear additive convolution, which is used to select the best alternatives according to the results, with the Pareto principle, which aims to exclude less suitable alternatives because all the features have lower values than in other options. For the experiment, all features were converted into quantitative ones to calculate convolution values. The evaluation criteria are given in the paper. The following results were obtained: the forecasting model in further study of this problem will be a random forest. Conclusions: the forecasting methods were studied and a more optimal model was chosen using linear additive convolution, namely, the random forest algorithm, its advantages and disadvantages were considered. A more detailed analysis of its development will be presented in the following articles. A mathematical description of the chosen forecasting method is provided, which includes potential ways of implementation and steps for building an algorithm for one of these methods.
References
References
Pobihun, N.G. (2020), "Research on the impact of physical activity and stress on the thyroid gland in hypothyroidism". Scientific and Practical Journal, 3(№ 4 (12)), P. 97–101. available at: https://art-of-medicine.ifnmu.edu.ua/index.php/aom/article/view/402
Mubashir Alam, K., Tasnim Ahsan, Urooj Lal, R., Ruqshanda Jabeen, and Saad Farooq. (2017), "Subclinical hypothyroidism: frequency, clinical manifestations, and indications for treatment". Pakistan Journal of Medical Sciences, 33(4), P. 818–822. DOI: 10.12669/pjms.334.12921
Feldman, A.Z., Shrestha, R.T., & Geneslaw, J.V. (2013), "Neuropsychiatric manifestations of thyroid diseases". Endocrinology and Metabolism Clinics of North America, 42(3), P. 453–476. DOI: 10.1016/j.ecl.2013.05.005
Almeida, O.P., Alfonso, H., Flicker, L., Hankey, G., Chubb, S.A.P., & Yeap, B.B. (2011), "Thyroid hormones and depression". The American Journal of Geriatric Psychiatry, 19(9), P. 763–770. DOI: 10.1097/jgp.0b013e31820dcad5
Bunevicius, R., & Prange, A.J. (2010), "Thyroid diseases and mental disorders: cause and effect or only comorbidity?", Current Opinion in Psychiatry, 23(4), P. 363–368. DOI: 10.1097/yco.0b013e3283387b50
Yarach, D., Kukharska, A., Raevska-Rager, A., & Latska, K. (2012), "Cognitive functions and mood during chronic thyrotropin-suppressive L-thyroxine therapy in patients with differentiated thyroid carcinoma". Journal of Endocrinological Research, 35(8), P. 760–765.
Demartini, B., Ranieri, R., Masu, A., Selle, V., Scaroni, C., & Gambini, O. (2014), "Depressive symptoms and major depressive disorder in patients with subclinical hypothyroidism". Journal of Nervous and Mental Disease, 202(8), P. 603–607. DOI: 10.1097/nmd.0000000000000168
Kozhyna, N.M., Tovazhnyanska, O.L., Markova, M.V., Zelenska, K.O., & Kauka, O.I. (2020), "Features of primary hypothyroidism in forcibly displaced persons as a basis for the formation of cognitive and anxiety-depressive disorders". Problems of Endocrine Pathology, 73(3), P. 25–32. DOI: https://doi.org/10.21856/j-PEP.2020.3.03
Marian, G., Nica, E.A., Ionescu, B.E., & Guinea, D. (2009), "Hyperthyroidism – cause of depression and psychosis: clinical case". Journal of Medicine and Life, 2(4), P. 440–442.
Dabldey, A.R., & Sippel, R.S. (2020), "Hyperthyroidism". Gland Surgery, 9(1), P. 124-135. DOI: 10.21037/gs.2019.11.01
Soiri, I.N., & Reidpat, D.D. (2013), "Health forecasting review", Environmental Health and Preventive Medicine, №18, P. 1–9. https://doi.org/10.1007/s12199-012-0294-6
Armstrong, J.S. (2001), "Principles of forecasting: A handbook for researchers and practitioners". Norwell: Kluwer Academic Publishers. 458 р.
Savchuk, O. (2021), "Application of machine learning in clinical psychology". available at: https://ojs.tdmu.edu.ua/index.php/kl-stomat/article/download/6147/5624/21744
Hodovanyets, O.I. & Rozhko, M.M. (2015), "Features of the formation of the dental arch system in children with diffuse non-toxic goiter", Bulletin of Biology and Medicine Issues, Vol. 2, Issue 2(119), P. 37–39.
Zelinska, N.B., Tereshchenko, A.V., & Rudenko, N.G. (2013), "The state of providing specialized assistance to children with endocrine pathology in Ukraine in 2012 and prospects for its development". Ukrainian Journal of Pediatric Endocrinology, No 3, P. 31–39.
Lytvynenko, O. (2021), "Innovative approaches to processing psychological data using machine learning". available at: https://openarchive.nure.ua/server/api/core/bitstreams/86aa5c34-6f0f-44a4-ac51-76e7d191e085/content
Livingston, E.H. (2019), "Subclinical hypothyroidism". JAMA, 322(2), 180 р. DOI: 10.1001/jama.2019.9508
Kyslyi, O. (2021), "Using machine learning methods in psychological research". available at: https://ami-ejournal.cdu.edu.ua/article/view/4158/4438
Zbarazhskyi, M. (2021), "Analysis of psychological data using machine learning techniques". available at: https://ojs.tdmu.edu.ua/index.php/visnyk-nauk-dos/article/view/8460/7880
Ivanov, I. (2021), "Advanced machine learning techniques in psychology". available at: https://ela.kpi.ua/items/20f948bd-5b8a-420e-a86e-70d86be50866
Kyslyi, O. (2020), "Using machine learning methods in psychological research. Artificial Intelligence Methods". available at: https://ami-ejournal.cdu.edu.ua/article/view/4158/4438
Petrov, A. (2021), "Applications of machine learning in psychological studies". available at: https://ela.kpi.ua/server/api/core/bitstreams/17dfafd7-9874-4b51-b865-f20ea63e5076/content
Cutler, A., & Zhao, G. (2001), "PERT – Perfect Random Tree Ensembles". Computing Science and Statistics, № 33, P. 490–497.
Babak, V.P., Biletskyi, A.Ya., Prystavka, O.P., & Prystavka, P.O. (2001), "Statistical data processing". Kyiv: MIVVTS. 388 р.
Breiman, L. (2001), "Random Forests". Machine Learning, P. 45.
Mochurad, L. & Ilkiv, A. (2022), "Advanced method of medical classification using parallelization algorithms". Computer Systems and Information Technologies, (1), P. 23–31. DOI: 10.31891/CSIT-2022-1-3
Ittermann, T., Fiolka, H., Baumeister, S.E., Appel, K., & Graabe, H.J. (2015), "Diagnosed thyroid diseases associated with depression and anxiety". Social Psychiatry and Psychiatric Epidemiology, 50(9), P. 1417–1425. DOI: 10.1007/s00127-015-1043-0
Martino, J.P. (1972), "Forecasting the progress of technologies". New York, New York: Gordon and Breach Science Publishers. № 2. 15 р.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
