A PRELIMINARY MACHINE LEARNING APPROACH TO UNDERSTANDING THE RELATIONSHIP BETWEEN GLYCEMIC DYSREGULATION, BIOCHEMICAL MARKERS, AND SCHIZOPHRENIA SEVERITY SCORES
DOI:
https://doi.org/10.22551/05fdj088Abstract
Schizophrenia is a multifaceted psychiatric disorder associated with significant metabolic disturbances, including glycemic dysregulation and systemic inflammation. This study aims to explore the relationship between glycemic control, biochemical markers, and schizophrenia severity using a machine learning approach. Materials and methods: A cross-sectional study was conducted on 70 patients diagnosed with schizophrenia, evaluating fasting glucose levels, lipid profiles, inflammatory markers (CRP, ESR), and clinical severity scores (BPRS, PANSS). Statistical and machine learning models, including regression and random forest algorithms, were employed to identify key predictors of psychiatric severity. Results: Results indicated that 18.6% of participants exhibited hyperglycemia, which was significantly correlated with higher BPRS and PANSS scores (p<0.05). Elevated CRP levels were detected in 45% of participants with moderate-to-severe symptoms, reinforcing the role of systemic inflammation in schizophrenia pathophysiology. Machine learning models identified glycemic status and systemic inflammation as key predictors of psychiatric severity, with behavioral dysregulation strongly linked to hyperglycemia. Furthermore, psychiatric symptom severity was positively associated with metabolic disturbances, particularly among individuals exhibiting irritability and agitation. Conclusions: These findings highlight a bidirectional relationship between metabolic dysfunction and schizophrenia severity, suggesting that glycemic control and inflammation may serve as important clinical biomarkers. The integration of machine learning techniques offers a novel approach to identifying metabolic predictors of psychiatric severity, potentially informing personalized treatment strategies.
References
1. Luvsannyam E, Jain MS, Pormento MKL, et al. Neurobiology of schizophrenia: a comprehensive review. Cureus 2022; 14(4): e23959 / doi: 10.7759/cureus.23959.
2. Boiko AS, Mednova IA, Kornetova EG, et al. Metabolic hormones in schizophrenia patients with antipsychotic-induced metabolic syndrome. J Pers Med 2022; 12(10): 1655 / doi: 10.3390/jpm12101655.
3. Prestwood TR, Asgariroozbehani R, Wu S, et al. Roles of inflammation in intrinsic pathophysiology and antipsychotic drug-induced metabolic disturbances of schizophrenia. Behav Brain Res 2021; 402: 113101 / doi: 10.1016/j.bbr.2020.113101.
4. Vancampfort D, Correll CU, Galling B, et al. Diabetes mellitus in people with schizophrenia, bipolar disorder and major depressive disorder: a systematic review and large-scale meta-analysis. World Psychiatry 2016; 15(2): 166-174 / doi: 10.1002/wps.20309.
5. Mikulska J, Juszczyk G, Gawrońska-Grzywacz M, Herbet M. HPA axis in the path mechanism of depression and schizophrenia: new therapeutic strategies based on its participation. Brain Sci 2021; 11(10): 1298 / doi: 10.3390/brainsci11101298.
6. Tomasik J, Lago SG, Vázquez-Bourgon J, et al. Association of insulin resistance with schizophrenia polygenic risk score and response to antipsychotic treatment. JAMA Psychiatry. 2019; 76(8): 864-867 / doi: 10.1001/jamapsychiatry.2019.0304.
7. Al-Sayyar A, Hammad MM, Williams MR, Al-Onaizi M, Abubaker J, Alzaid F. Neurotransmitters in type 2 diabetes and the control of systemic and central energy balance. Metabolites 2023; 13(3): 384 / doi: 10.3390/metabo13030384.
8. Khandaker GM, Pearson RM, Zammit S, Lewis G, Jones PB. Association of serum interleukin 6 and C-reactive protein in childhood with depression and psychosis in young adult life: a population-based longitudinal study. JAMA Psychiatry 2014; 71(10): 1121-1128 / doi: 10.1001/jamapsychiatry. 2014.1332.
9. Maiuolo J, Gliozzi M, Musolino V, et al. From metabolic syndrome to neurological diseases: role of autophagy. Front Cell Dev Biol 2021; 9: 651021 / doi: 10.3389/fcell.2021.651021.
10. Khandaker GM, Stochl J, Zammit S, Lewis G, Dantzer R, Jones PB. Association between circulating levels of C-reactive protein and positive and negative symptoms of psychosis in adolescents in a general population birth cohort. J Psychiatr Res 2021; 143: 534-542 / doi: 10.1016/j.jpsychires.2020.11.028.
11. Del Fabro L, Bondi E, Serio F, Maggioni E, D'Agostino A, Brambilla P. Machine learning methods to predict outcomes of pharmacological treatment in psychosis. Transl Psychiatry 2023; 13(1): 75 / doi: 10.1038/s41398-023-02371-z.
12. Zhuo C, Zhang Q, Wang L, et al. Insulin resistance/diabetes and schizophrenia: potential shared genetic factors and implications for better management of patients with schizophrenia. CNS Drugs 2024; 38(1): 33-44 / doi: 10.1007/s40263-023-01057-w.
13. Pillinger T, Beck K, Gobjila C, Donocik JG, Jauhar S, Howes OD. Impaired glucose homeostasis in first-episode schizophrenia: a systematic review and meta-analysis. JAMA Psychiatry 2017; 74(3): 261-269 / doi: 10.1001/jamapsychiatry.2016.3803.
14. González P, Lozano P, Ros G, Solano F. Hyperglycemia and oxidative stress: an integral, updated and critical overview of their metabolic interconnections. Int J Mol Sci. 2023 May 27; 24(11): 9352 / doi: 10.3390/ijms24119352.
15. Weinstein G, Maillard P, Himali JJ, et al. Glucose indices are associated with cognitive and structural brain measures in young adults. Neurology 2015; 84(23): 2329-2337 / doi: 10.1212/ WNL.00000000 00001655.
16. Goldsmith DR, Rapaport MH, Miller BJ. A meta-analysis of blood cytokine network alterations in psychiatric patients: comparisons between schizophrenia, bipolar disorder and depression. Mol Psy-chiatry 2016; 21(12): 1696-1709 / doi: 10.1038/mp.2016.3.
17. Shamsutdinova D. Applications of prediction modelling and machine learning to the nexus of type 2 diabetes and severe mental illness. London: King's College London; 2023.
18. Shamsutdinova D, Das-Munshi J, Ashworth M, Roberts A, Stahl D. Predicting type 2 diabetes preva-lence for people with severe mental illness in a multi-ethnic East London population. Int J Med Inform 2023; 172: 105019 / doi: 10.1016/j.ijmedinf.2023.105019.
19. Wang S, Yuan X, Pang L, Song P, Jia R, Song X. Establishment of an assistive diagnostic model for schizophrenia with oxidative stress biomarkers. Front Pharmacol 2023; 14: 1158254 / doi: 10.3389/ fphar.2023.1158254.
20. Sharaev MG, Malashenkova IK, Maslennikova AV, et al. Diagnosis of schizophrenia based on the data of various modalities: biomarkers and machine learning techniques (Review). Sovrem Tekhnologii Med 2022; 14(5): 53-75 / doi: 10.17691/stm2022.14.5.06.
21. Lee DY, Cho YH, Kim M, et al. Association between impaired glucose metabolism and long-term prognosis at the time of diagnosis of depression: impaired glucose metabolism as a promising bi-omarker proposed through a machine-learning approach. Eur Psychiatry 2023; 66(1): e21 / doi: 10.1192/j.eurpsy.2023.10.
22. Zaki JK, Lago SG, Rustogi N, et al. Diagnostic model development for schizophrenia based on pe-ripheral blood mononuclear cell subtype-specific expression of metabolic markers. Transl Psychiatry 2022; 12(1): 457 / doi: 10.1038/s41398-022-02229-w.
Additional Files
Published
Issue
Section
License
Copyright (c) 2025 The Medical-Surgical Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
COPYRIGHT
Once an article is accepted for publication, MSJ requests a transfer of copyrights for published articles.
COPYRIGHT TRANSFER FORM FOR
REVISTA MEDICO-CHIRURGICALĂ A SOCIETĂȚII DE MEDICI ȘI NATURALIȘTI DIN IAȘI /
THE MEDICAL-SURGICAL JOURNAL OF THE SOCIETY OF PHYSICIANS AND NATURALISTS FROM IASI
We, the undersigned authors of the manuscript entitled
_____________________________________________________________________________________
_____________________________________________________________________________________
warrant that this manuscript, which is submitted for publication in the REVISTA MEDICO-CHIRURGICALĂ, has not been published and it is not under consideration for publication in another journal.
- we give the consent for publication in the REVISTA MEDICO-CHIRURGICALĂ, in printed and electronic format and we transfer unconditioned and complete the copyright of this manuscript to the REVISTA MEDICO-CHIRURGICALĂ, in the event of its acceptance.
- the manuscript does not break the intellectual property rights of any other person.
- we have read the submitted version of the manuscript and we are fully responsible for the content.
Names and signatures of authors / copyright owners (the following sequence is the authorship of the article):
- ______________________________/_________________________
- ______________________________/_________________________
- ______________________________/_________________________
N.B. All the authors must sign this form
