Fuzzy models for predicting neuroses in higher education teachers and students
Year: 2026
Type: article
Abstract: The purpose of the research is to develop fuzzy models for predicting neuroses in higher education teachers and students. These models will improve the effectiveness of research by reducing the volume and eliminating duplication of traditional questionnaires while maintaining high prediction accuracy. Methods . The study included an analysis of psychological, pedagogical, and sociological data, and a systematization of risk factors (academic and professional stress, digital workload, and socioeconomic conditions). To build the models, we selected a hybrid fuzzy decision rule synthesis methodology developed at the Department of Biomedical Engineering at Southwestern State University. This methodology defined the corresponding membership functions for each feature and aggregated them into a final decision rule. Model performance was assessed using confidence measures for the classification results and validation samples. Results . Using an expert method, we developed a set of predictors for predicting neurotic disorders in teachers and students. The model included both traditional and specific risk factors. Digital hygiene and occupational stress parameters were also considered. Based on the resulting set of features, a mathematical model for classifying the risk of developing neuroses was synthesized, providing a confidence measure for the decision rule of at least 0.92. The results confirm that the proposed models provide high-quality predictions of neuroses in teachers and students while significantly reducing respondent burden. Conclusion In the course of the studies, models for predicting neuroses in university teachers and students, which are distinguished by their use of indicators characterizing the work process and level of information load in conjunction with generally accepted medical risk factors, provided a confidence level of at least 0.9 in correct decision making, allowing them to be recommended for use in medical practice
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7160504166