Dmytro Chumachenko

Regional tuberculosis (TB) surveillance requires analytical tools that distinguish outcome definitions, preserve temporal ordering, and characterize geographic heterogeneity. This study developed an information system integrating regression modeling and regional clustering for Ukrainian surveillance indicators. The primary predictive outcome was the quarterly regional count of patients whose multidrug-resistant or rifampicin-resistant TB (MDR/RR-TB) diagnosis was laboratory confirmed for the first time during the reporting quarter. Predictive performance was evaluated using rolling-origin one-quarter-ahead temporal validation, with Random Forest, k-nearest-neighbor regression, Gradient Boosting, a voting ensemble, and simple operational benchmarks compared on the same temporally held-out observations. Several leading approaches showed similar predictive performance, and paired region-level tests did not establish statistically significant superiority of a single model after correction for multiple comparisons. K-means clustering was used as a descriptive representation of regional heterogeneity; the selected three-group representation was stable for the illustrative 2021 analysis, although internal validation criteria did not uniquely identify three clusters as optimal. The study provides a reproducible workflow for temporally validated comparison of recorded surveillance counts together with descriptive regional grouping rather than a new learning algorithm or a causal model of TB transmission.

Large language models (LLMs) offer opportunities for scalable financial guidance, but hallucinations, numerical errors, insufficient grounding, and unstable decisions limit their use in high-stakes financial settings. This study develops and evaluates a multiagent AI framework for retirement-oriented financial guidance using synthetic profiles modelled on displaced Ukrainians in Poland. The framework combines retrieval-augmented generation (RAG), structured profile generation, deterministic budget calculations, and an architecturally separate Evaluator Agent. The primary computational evaluation comprised 500 synthetic advisory cases. Additional experiments included a paired no-RAG ablation on 50 fixed profiles and a repeated-run stability analysis of 100 fixed profiles replayed five times. Under the predefined automated routing criteria, 327 cases were accepted, 170 required review, and 3 were flagged. After the deterministic budget overwrite, a separate deterministic arithmetic check found zero profile-to-answer mismatches. In the paired ablation, the mean final composite score was 8.40 with RAG and 7.08 without RAG. The difference was driven primarily by larger deterministic penalty deductions and grounding-gate failures without RAG, while the mean of the five LLM rubric dimensions did not improve with RAG. In repeated runs, only 14% of profiles retained identical routing across all five replays. The deterministic arithmetic pathway remained invariant, while generation, retrieval, model-based evaluation, and threshold-based routing varied across repeated execution. The framework is therefore interpreted as a controlled computational testbed and quality-assurance architecture rather than a validated autonomous financial advisor.

The spread of infectious diseases under wartime and resource-constrained conditions creates a need for analytical tools that support both population-level epidemiological monitoring and preliminary patient-level image analysis. This study develops and evaluates a web-based analytical framework incorporating two complementary modules: infectious-disease forecasting and chest X-ray image analysis. For epidemiological forecasting, ARIMA, deep neural network (DNN), and long short-term memory (LSTM) models were evaluated to compare statistical, feed-forward neural-network, and recurrent neural-network approaches to one-month-ahead prediction using Ukrainian epidemiological data from 2020 to 2023. For chest X-ray analysis, YOLOv8 and YOLOv11 nano and small configurations were compared in a proof-of-concept experiment involving five pulmonary categories. The two analytical modules were integrated at the application level within a common web-based interface providing data upload, model selection, analysis, and result visualization. Under the adopted one-month-ahead hold-out evaluation, DNN and LSTM generally provided lower forecasting errors than the ARIMA baseline. In the image-analysis experiment, YOLOv11s produced the highest validation mAP@0.5:0.95 among the evaluated configurations, reaching 0.74. However, the public chest X-ray dataset had been augmented by its provider before acquisition, and the present image-analysis evaluation used training and validation partitions without an independent test subset for final performance assessment. Therefore, the reported image-analysis metrics characterize only the adopted validation partition, may overestimate performance on independent data, and should not be interpreted as estimates of clinical or external generalization. In addition, the manually prepared bounding-box annotations were not independently verified by a qualified clinical expert. Accordingly, the image-analysis component should be regarded as a proof-of-concept computational evaluation rather than a clinically validated diagnostic system. The developed prototype demonstrates the technical feasibility of providing epidemiological forecasting and preliminary chest X-ray image analysis within a common application environment for emergency and resource-constrained settings.

The rapid integration of artificial intelligence into higher education has increased the need to distinguish routine AI use from preparedness to use this technology responsibly and ethically. The study examines responsible AI preparedness as a dimension of continuous digital professional learning in Ukrainian higher education by analysing differences in perceived ethical AI learning needs across career stages and levels of AI use and their association with institutional AI-policy environments. Cross-sectional survey data from 2,004 respondents representing Ukrainian higher education institutions were analysed using descriptive statistics, chi-squared tests, Cramér’s V, cumulative-link ordinal logistic regression, interaction models, adjusted predicted probabilities, and binary logistic regression. AI use was widespread: 74.0% used AI at least periodically, while 33.1% reported high ethical AI learning needs and 42.2% substantial gaps in institutional rules or guidance. Among active AI users, 472 respondents were classified as active but underprepared, representing 31.8% of active users and 23.6% of the HEI sample. In the binary logistic model restricted to active users, reporting no institutional AI policy was associated with 47.3% higher odds of high ethical learning need (OR = 1.47, 95% CI [1.11, 1.95]), while policy uncertainty was associated with 64.2% higher odds (OR = 1.64, 95% CI [1.26, 2.14]). In the cumulative-link ordinal model for the full HEI sample, ethical learning needs were higher among respondents aged 50–59 (OR = 1.64) and 60–69 (OR = 1.86) than among those aged 18–29. Research experience significantly moderated the association between AI-use intensity and perceived learning need (LR χ²(3) = 8.82, p = 0.032). The findings support targeted professional learning.

In the contemporary world, artificial intelligence (AI) is driving profound changes across global institutional, technological, and social processes. However, countries’ readiness for its integration varies substantially by economic development, regional characteristics, and digital maturity. Accordingly, this article aims to assess the alignment between the AI publication footprint, based on Scopus publication data, and national AI readiness, measured by the IMF AI Preparedness Index, across 173 countries, classified by geographic region and income level. The application of analysis of variance (ANOVA), the Kruskal–Wallis test and post hoc comparisons, correlation, regression, and cluster analysis enabled the identification of multidimensional relationships between scientific activity and the four key dimensions of digital maturity: digital infrastructure, human capital/labor market, innovation/economic integration, and regulation/ethics. The results revealed a strong overall global correlation between AI publication footprint and national AI readiness (r = 0.68, R² = 0.46), with the highest level of alignment observed in high-income countries’ readiness (r = 0.67, R² = 0.45), and regions such as the Americas (r = 0.72, R² = 0.51) and Europe (r = 0.57, R² = 0.33). At the same time, lower-income countries demonstrate weak or statistically insignificant relationships, indicating persistent structural barriers. Cluster analysis identified four types of countries, ranging from those with high levels of digital maturity to those with lower levels of national AI readiness. These findings highlight diverse national development trajectories and the need for differentiated policy approaches. However, the AI Publication Footprint is based on absolute cumulative Scopus publication counts and should be interpreted as a proxy for AI knowledge-production capacity rather than a normalized measure of research intensity or actual AI adoption. Given the cross-sectional and primarily bivariate design, the results indicate associations rather than causal effects and do not directly capture educational outcomes. The findings may have implications for education and sustainability by suggesting that disparities in infrastructure, human capital, innovation capacity, and responsible governance may shape the conditions for inclusive and sustainable AI-enabled education; these implications require direct empirical testing. Accordingly, the study emphasizes the need for adaptive policy frameworks that account for regional and economic disparities.

Background: Managing an epidemic demands policies that respond at the pace of the outbreak. Conventional rule‑based interventions struggle to keep up, prompting interest in reinforcement learning (RL) for designing non‑pharmaceutical interventions (NPIs). However, current evidence is fragmented across diverse models and reporting styles. Objectives: To systematically map how RL is applied for epidemic NPI design, describe modeling choices, algorithm architectures, evaluation practices, and identify trends and research gaps. Methods: Peer-reviewed studies (2014–2025, English) that applied deep RL to select NPIs were retrieved from IEEE Xplore, ACM Digital Library, ScienceDirect, and Scopus, searched on December 23, 2025. Reference list scanning supplemented database results. Predefined data items (bibliographic details, epidemic and RL model characteristics, experiments, validation methods, outcomes) were charted and summarized descriptively. Results: Of 512 retrieved records, 10 met the inclusion criteria, and three additional studies were identified via reference-list scanning, yielding 13. Five employed value‑based methods, four policy‑gradient, and four hybrid; one study additionally incorporated model-based planning. Six simulations relied on compartmental models, six on agent‑based models, and one on a hybrid model. Action spaces were predominantly discrete restriction levels. Five studies incorporated sequence-modeling techniques to include temporal context into a state space. Eleven studies designed reward functions as a trade-off between pandemic severity and socio-economic cost. According to the reviewed studies, RL policies across various settings outperform heuristic, rule-based, and historical baselines in reducing infections, deaths, or lockdown duration while limiting economic loss. Conclusions: RL shows promise for adaptive epidemic control. Comparison is hampered by simplified economic costs, inconsistent calibration rigor, varied evaluation metrics, and limited uncertainty or policy robustness analysis. Future work should establish common benchmark environments and reporting standards, incorporate empirically grounded economic and behavioral models, adopt uncertainty-aware and probabilistic RL, develop more sophisticated control spaces, investigate more advanced algorithms, and validate learned policies prospectively to enable real-world deployment.