Building Predictive Models for Schizophrenia Diagnosis with Peripheral Inflammatory Biomarkers

Building Predictive Models for Schizophrenia Diagnosis with Peripheral Inflammatory Biomarkers Full article

Journal

Biomedicines
ISSN: 2227-9059

Output data

Year: 2023, Volume: 11, Number: 7, Article number : 1990, Pages count : DOI: 10.3390/biomedicines11071990

Tags

schizophrenia; biomarkers; artificial intelligence; machine learning; predictive model; deep neural network; logistic regression; decision trees; support vector machine; k-nearest neighbors

Authors

Kozyrev E.A. ¹ , Ermakov E.A. ² , Boiko A.S. ³ , Mednova I.A. ³ , Kornetova E.G. ^3,4 , Bokhan N.A. ^3,5 , Ivanova S.A. ^3,5

Affiliations

1	Budker Institute of Nuclear Physics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
2	Institute of Chemical Biology and Fundamental Medicine, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
3	Mental Health Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences, 634014 Tomsk, Russia
4	University Hospital, Siberian State Medical University, 634050 Tomsk, Russia
5	Psychiatry, Addiction Psychiatry and Psychotherapy Department, Siberian State Medical University, 634050 Tomsk, Russia

Machine learning and artificial intelligence technologies are known to be a convenient tool for analyzing multi-domain data in precision psychiatry. In the case of schizophrenia, the most commonly used data sources for such purposes are neuroimaging, voice and language patterns, and mobile phone data. Data on peripheral markers can also be useful for building predictive models. Here, we have developed five predictive models for the binary classification of schizophrenia patients and healthy individuals. Data on serum concentrations of cytokines, chemokines, growth factors, and age were among 38 parameters used to build these models. The sample consisted of 217 schizophrenia patients and 90 healthy individuals. The models architecture was involved logistic regression, deep neural networks, decision trees, support vector machine, and k-nearest neighbors algorithms. It was shown that the algorithm based on a deep neural network (consisting of five layers) showed a slightly higher sensitivity (0.87 ± 0.04) and specificity (0.52 ± 0.06) than other algorithms. Combining all variables into a single classifier showed a cumulative effect that exceeded the effectiveness of individual variables, indicating the need to use multiple biomarkers to diagnose schizophrenia. Thus, the data obtained showed the promise of using data on peripheral biomarkers and machine learning methods for diagnosing schizophrenia

Kozyrev E.A. , Ermakov E.A. , Boiko A.S. , Mednova I.A. , Kornetova E.G. , Bokhan N.A. , Ivanova S.A.
Building Predictive Models for Schizophrenia Diagnosis with Peripheral Inflammatory Biomarkers
Biomedicines. 2023. V.11. N7. 1990 . DOI: 10.3390/biomedicines11071990 WOS Scopus РИНЦ OpenAlex

Published print:

Jul 14, 2023

Web of science:	WOS:001034862300001
Scopus:	2-s2.0-85169768345
Elibrary:	54277775
OpenAlex:	W4384299154

DB	Citing
Elibrary	3
OpenAlex	3
Web of science	2