Background. The digitalization of medicine generates vast arrays of heterogeneous data, including socio-economic and behavioral factors, which are essential for a comprehensive assessment of the population's mental health. Modern Russian low-code platforms, such as Loginom, enable the automation of this data analysis through the construction of visual scenarios, thereby facilitating the integration of analytics into the workflows of specialists who lack advanced IT skills.
Objective. To conduct an end-to-end analysis of social and medical data required for operational modeling and decisionmaking support in medicine, utilizing the capabilities of the Loginom platform as an accessible tool.
Materials and Methods. The study utilized an open database from a survey regarding the impact of social media on mental health (n=580 students; parameters included demographics, depression/anxiety levels, and self-rated health). The following scenarios were constructed in Loginom: automatic cleaning/categorization (handling missing values, data typing), correlation analysis (automated search and visualization of relationships), and regional comparative analytics (projection by states and economic parameters, with automated reporting). A key aspect is modeling without programming, which is critical for scalable digital solutions.
Results. A strong positive correlation was observed between anxiety and depression (Spearman's rank correlation coefficient 0.78, p<0.001), which remained stable across various data subsets. Economically developed regions demonstrated higher indicators for both general health and the frequency of reported anxiety; this finding can be translated into strategies for targeted preventive monitoring. Loginom enabled the generation of final reports and visualizations in less than one hour after data loading, confirming the suitability of low-code solutions for implementation in the routine practice of medical institutions.
Conclusion. The practical advantages of Loginom for rapid and transparent processing of large socio-medical datasets, the creation of flexible scenarios for mental health assessment, and the generation of recommendations for digital medical support have been demonstrated. This approach allows for the involvement of a greater number of specialists in working with medical IT tools and is relevant for health monitoring and management tasks within the context of the digital transformation of domestic healthcare. Replication of this methodology in regional centers is recommended, as well as the subsequent inclusion of economic and cultural parameters in the analytics to enhance interpretation accuracy.
