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.

The monograph focuses on the challenges of assessing the individual operational readiness of soldiers to perform a military task. The authors proceeded from the fact that the psycho-emotional state of a soldier is one of the decisive factors that affect the success of the military task during the stay in combat conditions. This is confirmed by the combat experience of the Armed Forces of Ukraine in joint operations, and especially after the start of a large-scale invasion by Russia. One of the most effective solutions in providing medical rehabilitation care is patient-centered remote rehabilitation—hybrid e-rehabilitation, which requires: online facilities for telediagnosis, telemetry and intervention based on patient capabilities, advanced Internet interaction, intelligent information technologies and services, effective methods of cognitive support in the “Physical therapist–Patient–Multidisciplinary team” system, statistical processing of large amounts of information, etc. Therefore, along with traditional methods of rehabilitation, a patient-centered Smart system of telemedicine support for hybrid e-rehabilitation activities (as part of the UkrVectōrēs and vHealth services) has been developed.

Introduction. Analysis of changes in armed struggle in Russia's war against Ukraine in 2024 (Assessment of Russia's offensive campaign, December 20, 2024 | Institute for the Study of War, The first robotic operation on the battlefield: ISW noted the technological progress of the Armed Forces of Ukraine; War in Ukraine – how many Ukrainian and Russian military personnel died - UNIAN) indicates that the aggressor is maintaining a strategy of attrition, an increase in the number of groups, the intensity of fire exposure using the massive use of reconnaissance and strike high-precision weapons, a significant increase in the vulnerability of weapons, equipment and military personnel, an increase in sanitary and psychogenic losses, an increase in the need for mobilization resources, a decrease in the professional and physical qualities of the mobilizer, and increased requirements for training to perform combat missions in real time. The purpose of the paper is to create a technology for objective assessment and prediction of the functional state and stress resistance of individual servicemen and entire units, simple and suitable for use without special training near the front line, in training camps, etc. Results. A functional state model based on 26,976 ECG from military and civilians is proposed. Based on 23 parameters and t-SNE/UMAP transformations, 2 clusters were identified. Members of the first one are significantly more likely to suffer from high stress and deterioration of functional state when the second cluster is related to higher stress resistance. The model provides a generalized express assessment and prediction of the functional state psycho-emotional and resource-energy components as well as a more accurate assessment calculated according to the presented algorithm. The model implementation is based on using small portable ECG devices able to register 1-channel ECG signal from fingers without the need to undress and attach electrodes. Simplicity of use is important in the field and front conditions. Conclusions. The developed technology for predicting stress and fatigue resistance based on simple, rapid objective measurement is already being used in practice and is receiving positive feedback in units of various specializations. The ability to predict stress resistance based on objective measurements does not replace the need for a professional psychologist to treat stress. However, it can become an additional simple and powerful tool for better allocation of human resources and forecasting the future combat capabilities of units. It is important that the model can be used already in the training camp, that is, before the servicemen receive real combat experience. Keywords: functional state of soldiers, combat stress, psychophysiological state of soldiers, objective assessment of condition, ECG analysis, machine learning, medical data analysis.