Artificial Intelligence Applications in Public Health: 2nd Edition

Purpose: While hybrid quantum–classical neural networks (HNNs) are a promising avenue for quantum advantage, the critical influence of the classical backbone architecture on their performance remains poorly understood. This study investigates the role of lightweight convolutional neural network architectures, focusing on LCNet, in determining the stability, generalization, and effectiveness of hybrid models augmented with quantum layers for medical applications. The objective is to clarify the architectural compatibility between quantum and classical components and provide guidelines for backbone selection in hybrid designs. Methods: We constructed HNNs by integrating a four-qubit quantum circuit (with trainable rotations) into scaled versions of LCNet (050, 075, 100, 150, 200). These models were rigorously evaluated on CIFAR-10 and MedMNIST using stratified 5-fold cross-validation, assessing accuracy, AUC, and robustness metrics. Performance was assessed with accuracy, macro- and micro-averaged area under the ROC curve (AUC), per-class accuracy, and out-of-fold (OoF) predictions to ensure unbiased generalization. In addition, training dynamics, confusion matrices, and performance stability across folds were analyzed to capture both predictive accuracy and robustness. Results: The experiments revealed a strong dependence of hybrid network performance on both backbone architecture and model scale. Across all tests, LCNet-based hybrids achieved the most consistent benefits, particularly at compact and medium configurations. From LCNet050 to LCNet100, hybrid models maintained high macro-AUC values exceeding 0.95 and delivered higher mean accuracies with lower variance across folds, confirming enhanced stability and generalization through quantum integration. On the DermaMNIST dataset, these hybrids achieved accuracy gains of up to seven percentage points and improved AUC by more than three points, demonstrating their robustness in imbalanced medical settings. However, as backbone complexity increased (LCNet150 and LCNet200), the classical architectures regained superiority, indicating that the advantages of quantum layers diminish with scale. The mostconsistent gains were observed at smaller and medium LCNet scales, where hybridization improved accuracy and stability across folds. This divergence indicates that hybrid networks do not necessarily follow the “bigger is better” paradigm of classical deep learning. Per-class analysis further showed that hybrids improved recognition in challenging categories, narrowing the gap between easy and difficult classes. Conclusions: The study demonstrates that the performance and stability of hybrid quantum–classical neural networks are fundamentally determined by the characteristics of their classical backbones. Across extensive experiments on CIFAR-10 and DermaMNIST, LCNet-based hybrids consistently outperformed or matched their classical counterparts at smaller and medium scales, achieving higher accuracy and AUC along with notably reduced variability across folds. These improvements highlight the role of quantum layers as implicit regularizers that enhance learning stability and generalization—particularly in data-limited or imbalanced medical settings. However, the observed benefits diminished with increasing backbone complexity, as larger classical models regained superiority in both accuracy and convergence reliability. This indicates that hybrid architectures do not follow the conventional “larger-is-better” paradigm of classical deep learning. Overall, the results establish that architectural compatibility and model scale are decisive factors for effective quantum–classical integration. Lightweight backbones such as LCNet offer a robust foundation for realizing the advantages of hybridization in practical, resource-constrained medical applications, paving the way for future studies on scalable, hardware-efficient, and clinically reliable hybrid neural networks. Full article

COVID-19 remains a global health challenge, with severe cases often leading to complications and fatalities. The objective of this study was to assess supervised machine learning algorithms for predicting severe COVID-19 based on demographic, clinical, biochemical, and genetic variables, with the aim of identifying the most informative prognostic markers. For Machine Learning (ML) analysis, we utilized a dataset comprising 226 observations with 68 clinical, biochemical, and genetic features collected from 226 patients with confirmed COVID-19 (54—moderate, 142—severe and 30 with mild disease). The target variable was disease severity (mild, moderate, severe). The feature set included demographic variables (age, sex), genetic markers (single-nucleotide polymorphisms (SNPs) in FGB (rs1800790), NOS3 (rs2070744), and TMPRSS2 (rs12329760)), biochemical indicators (IL-6, endothelin-1, D-dimer, fibrinogen, among others), and clinical parameters (blood pressure, body mass index, comorbidities). The target variable was disease severity. To identify the most effective predictive models for COVID-19 severity, we systematically evaluated multiple supervised learning algorithms, including logistic regression, k-nearest neighbors, decision trees, random forest, gradient boosting, bagging, naïve Bayes, and support vector machines. Model performance was assessed using accuracy and the area under the receiver operating characteristic curve (AUC-ROC). Among the predictors, IL-6, presence of depression/pneumonia, LDL cholesterol, AST, platelet count, lymphocyte count, and ALT showed the strongest correlations with severity. The highest predictive accuracy, with negligible error rates, was achieved by ensemble-based models such as ExtraTreesClassifier, HistGradientBoostingClassifier, BaggingClassifier, and GradientBoostingClassifier. Notably, decision tree models demonstrated high classification precision at terminal nodes, many of which yielded a 100% probability for a specific severity class. Full article

The management of public health projects in a BANI (brittle, anxious, non-linear, incomprehensible) environment, exemplified by the ongoing war in Ukraine, presents unprecedented challenges due to fragile systems, heightened uncertainty, and complex socio-political dynamics. This study proposes an AI-driven framework to enhance the resilience and effectiveness of public health interventions under such conditions. By integrating a coupled SEIR–Infodemic–Panicdemic Model with war-specific factors, we simulate the interplay of infectious disease spread, misinformation dissemination, and panic dynamics over 1500 days in a Ukrainian city (Kharkiv). The model incorporates time-varying parameters to account for population displacement, healthcare disruptions, and periodic war events, reflecting the evolving conflict context. Sensitivity and risk–opportunity analyses reveal that disease transmission, misinformation, and infrastructure damage significantly exacerbate epidemic peaks, while AI-enabled interventions, such as fact-checking, mental health support, and infrastructure recovery, offer substantial mitigation potential. Qualitative assessments identify technical, organisational, ethical, regulatory, and military risks, alongside opportunities for predictive analytics, automation, and equitable healthcare access. Quantitative simulations demonstrate that risks, like increased displacement, can amplify infectious peaks by up to 28.3%, whereas opportunities, like enhanced fact-checking, can reduce misinformation by 18.2%. These findings provide a roadmap for leveraging AI to navigate BANI environments, offering actionable insights for public health practitioners in Ukraine and other crisis settings. The study underscores AI’s transformative role in fostering adaptive, data-driven strategies to achieve sustainable health outcomes amidst volatility and uncertainty. Full article

This study explores the potential of unsupervised machine learning algorithms to identify latent cardiac risk profiles by analyzing ECG-derived parameters from two general groups: clinically healthy individuals (Norm dataset, n = 14,863) and patients hospitalized with heart failure (patients’ dataset, n = 8220). Each dataset includes 153 ECG and heart rate variability (HRV) features, including both conventional and novel diagnostic parameters obtained using a Universal Scoring System. The study aims to apply unsupervised clustering algorithms to ECG data to detect latent risk profiles related to heart failure, based on distinctive ECG features. The focus is on identifying patterns that correlate with cardiac health risks, potentially aiding in early detection and personalized care. We applied a combination of Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and Hierarchical Density-Based Spatial Clustering (HDBSCAN) for unsupervised clustering. Models trained on one dataset were applied to the other to explore structural differences and detect latent predispositions to cardiac disorders. Both Euclidean and Manhattan distance metrics were evaluated. Features such as the QRS angle in the frontal plane, Detrended Fluctuation Analysis (DFA), High-Frequency power (HF), and others were analyzed for their ability to distinguish different patient clusters. In the Norm dataset, Euclidean distance clustering identified two main clusters, with Cluster 0 indicating a lower risk of heart failure. Key discriminative features included the “ALPHA QRS ANGLE IN THE FRONTAL PLANE” and DFA. In the patients’ dataset, three clusters emerged, with Cluster 1 identified as potentially high-risk. Manhattan distance clustering provided additional insights, highlighting features like “ST DISLOCATION” and “T AMP NORMALIZED” as significant for distinguishing between clusters. The analysis revealed distinct clusters that correspond to varying levels of heart failure risk. In the Norm dataset, two main clusters were identified, with one associated with a lower risk profile. In the patients’ dataset, a three-cluster structure emerged, with one subgroup displaying markedly elevated risk indicators such as high-frequency power (HF) and altered QRS angle values. Cross-dataset clustering confirmed consistent feature shifts between groups. These findings demonstrate the feasibility of ECG-based unsupervised clustering for early risk stratification. The results offer a non-invasive tool for personalized cardiac monitoring and merit further clinical validation. These findings emphasize the potential for clustering techniques to contribute to early heart failure detection and personalized monitoring. Future research should aim to validate these results in other populations and integrate these methods into clinical decision-making frameworks. Full article

Accurate forecasting of COVID-19 case numbers is critical for timely and effective public health interventions. However, epidemiological data’s irregular and noisy nature often undermines the predictive performance. This study examines the influence of four smoothing techniques—the rolling mean, the exponentially weighted moving average, a Kalman filter, and seasonal–trend decomposition using Loess (STL)—on the forecasting accuracy of four models: LSTM, the Temporal Fusion Transformer (TFT), XGBoost, and LightGBM. Weekly case data from Ukraine, Bulgaria, Slovenia, and Greece were used to assess the models’ performance over short- (3-month) and medium-term (6-month) horizons. The results demonstrate that smoothing enhanced the models’ stability, particularly for neural architectures, and the model selection emerged as the primary driver of predictive accuracy. The LSTM and TFT models, when paired with STL or the rolling mean, outperformed the others in their short-term forecasts, while XGBoost exhibited greater robustness over longer horizons in selected countries. An ANOVA confirmed the statistically significant influence of the model type on the MAPE (p = 0.008), whereas the smoothing method alone showed no significant effect. These findings offer practical guidance for designing context-specific forecasting pipelines adapted to epidemic dynamics and variations in data quality. Full article

Mathematical modeling allows taking into account registered and hidden infections to make correct predictions of epidemic dynamics and develop recommendations that can reduce the negative impact on public health and the economy. A model for visible and hidden epidemic dynamics (published by the author in February 2025) has been generalized to account for the effects of re-infection and newborns. An analysis of the equilibrium points, examples of numerical solutions, and comparisons with the dynamics of real epidemics are provided. A stable quasi-equilibrium for the particular case of almost completely hidden epidemics was also revealed. Numerical results and comparisons with the COVID-19 epidemic dynamics in Austria and South Korea showed that re-infections, newborns, and hidden cases make epidemics endless. Newborns can cause repeated epidemic waves even without re-infections. In particular, the next epidemic peak of pertussis in England is expected to occur in 2031. With the use of effective algorithms for parameter identification, the proposed approach can ensure effective predictions of visible and hidden numbers of cases and infectious and removed patients. Full article

In the field of transplantology, where medical decisions are heavily dependent on complex data analysis, the challenge of small data has become increasingly prominent. Transplantology, which focuses on the transplantation of organs and tissues, requires exceptional accuracy and precision in predicting outcomes, assessing risks, and tailoring treatment plans. However, the inherent limitations of small datasets present significant obstacles. This paper introduces an advanced input-doubling classifier designed to improve survival predictions for allogeneic bone marrow transplants. The approach utilizes two artificial intelligence tools: the first Probabilistic Neural Network generates output signals that expand the independent attributes of an augmented dataset, while the second machine learning algorithm performs the final classification. This method, based on the cascading principle, facilitates the development of novel algorithms for preparing and applying the enhanced input-doubling technique to classification tasks. The proposed method was tested on a small dataset within transplantology, focusing on binary classification. Optimal parameters for the method were identified using the Dual Annealing algorithm. Comparative analysis of the improved method against several existing approaches revealed a substantial improvement in accuracy across various performance metrics, underscoring its practical benefits Full article

The global COVID-19 pandemic has generated extensive datasets, providing opportunities to apply machine learning for diagnostic purposes. This study evaluates the performance of five supervised learning models—Random Forests (RFs), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Logistic Regression (LR), and Decision Trees (DTs)—on a hospital-based dataset from the Concepción Department in Paraguay. To address missing data, four imputation methods (Predictive Mean Matching via MICE, RF-based imputation, K-Nearest Neighbor, and XGBoost-based imputation) were tested. Model performance was compared using metrics such as accuracy, AUC, F1-score, and MCC across five levels of missingness. Overall, RF consistently achieved high accuracy and AUC at the highest missingness level, underscoring its robustness. In contrast, SVM often exhibited a trade-off between specificity and sensitivity. ANN and DT showed moderate resilience, yet were more prone to performance shifts under certain imputation approaches. These findings highlight RF’s adaptability to different imputation strategies, as well as the importance of selecting methods that minimize sensitivity–specificity trade-offs. By comparing multiple imputation techniques and supervised models, this study provides practical insights for handling missing medical data in resource-constrained settings and underscores the value of robust ensemble methods for reliable COVID-19 diagnostics. Full article

Depression is one of the most common mental health disorders in the world, affecting millions of people. Early detection of depression is crucial for effective medical intervention. Multimodal networks can greatly assist in the detection of depression, especially in situations where in patients are not always aware of or able to express their symptoms. By analyzing text and audio data, such networks are able to automatically identify patterns in speech and behavior that indicate a depressive state. In this study, we propose two multimodal information fusion networks: early and late fusion. These networks were developed using convolutional neural network (CNN) layers to learn local patterns, a bidirectional LSTM (Bi-LSTM) to process sequences, and a self-attention mechanism to improve focus on key parts of the data. The DAIC-WOZ and EDAIC-WOZ datasets were used for the experiments. The experiments compared the precision, recall, f1-score, and accuracy metrics for the cases of using early and late multimodal data fusion and found that the early information fusion multimodal network achieved higher classification accuracy results. On the test dataset, this network achieved an f1-score of 0.79 and an overall classification accuracy of 0.86, indicating its effectiveness in detecting depression. Full article