Arseniy Trukhanov

INTRODUCTION. The new scientific and social field called ‘biology of ageing and medicine for healthy longevity’, together with the associated technological and methodological developments, is paving the way for the creation of a new economic sector designed to increase ‘expected healthy life expectancy’ to over 70 years and to extend active professional and social longevity. AIM. To analyze the prerequisites for the creation of a new economic sector designed to increase ‘healthy life expectancy’, and its integration into the clinical healthcare system. MAIN PROVISIONS. The scientific and methodological basis for the medicine of healthy longevity could be drawn from the know-how and practical experience accumulated within the medical specialty of physical and rehabilitation medicine, which employs the principles of the WHO’s International Classification of Functioning (ICF) and the biopsychosocial model to assess functioning and quality of life. The proposals stem from an analysis of both international and domestic experiences in creating specialist centers and staff training in rehabilitation medicine. A distinctive feature of this emerging field is a multidisciplinary interaction between genetics, microbiology, and immunology — as fundamental sciences — and clinical specialties such as therapy, cardiology, neurology, endocrinology, dermatology, and others. CONCLUSION. The medicine of healthy longevity is the main vector and practical foundation for the future development of the health resort industry, which offers programs and services for monitoring age-related changes in the body, their early diagnosis and correction, managing the rate of aging of organs and systems, preventing the development of chronic age-related diseases, developing scientifically grounded protocols for managing biological age, and encouraging a culture of responsible self-care regarding one’s health.

Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) has exceptionally high mortality, largely because of late diagnosis, while established blood biomarkers such as CA19-9 have limited sensitivity for early detection. We evaluated whether modelling serum proteomic measurements as supervised pairwise statistical graphs using synolitic graph neural networks (SGNNs) could provide a useful framework for pre-diagnostic PDAC classification. Methods: We analysed 217 pre-diagnostic serum samples from UKCTOCS, comprising 100 PDAC samples from 75 women and 117 control samples, profiled for 97 proteins. Samples were divided into a development set collected 0–1 year before diagnosis (n = 110) and a temporal holdout set collected 1–2 years before diagnosis (n = 107); 25 PDAC participants contributed samples to both windows. The final SGNN used fold-internal mutual-information selection of 30 proteins, pairwise RBF-SVM-derived edge information, minimum-connected sparsification, and a 10-member GATv2 ensemble per cross-validation fold. Conventional machine-learning comparators were tuned using development data only. Results: The SGNN achieved a mean 5-fold development ROC-AUC of 75.33 ± 10.43%, lower than the tuned Random Forest (81.67%); the other tuned comparators achieved 77.67% (XGBoost), 77.17% (logistic regression), and 73.17% (SVM). Averaging predictions across the five-fold-specific SGNN ensembles yielded a temporal-holdout ROC-AUC of 64.35% (95% CI 52.6–74.6%). In the participant-independent subset of 25 PDAC cases not represented in development and 57 controls, ROC-AUC was 66.04% (95% CI 52.56–78.88%). Conclusions: SGNNs provide a feasible graph-based representation of pre-diagnostic proteomic data but did not outperform optimised conventional machine-learning methods within development cross-validation. The temporal and participant-independent performance estimates warrant further investigation in larger fully independent cohorts. A graph-specific predictive advantage was not directly tested—no such advantage was demonstrated in this dataset—and the clinical utility has not been established.

Background: Prostate cancer (PCa) is one of the most prevalent malignancies in men, and active surveillance (AS) is the recommended management strategy for low- and favourable intermediate-risk disease. Predicting which patients will progress during AS remains a clinical challenge. MRI-derived radiomics has shown promise for risk stratification, but conventional machine learning approaches treat radiomic features as independent variables and may not capture the complex inter-feature dependencies within imaging data. This study evaluates the application of Synolitic Graph Neural Networks (SGNNs) to baseline MRI-derived radiomic features for predicting prostate cancer progression on active surveillance. Methods: We studied 343 AS patients (73 progressors, 270 non-progressors) from a single-centre cohort prospectively enrolled between 2013 and 2019 and retrospectively analysed. Seventy-two radiomic features were extracted from baseline 3T MRI (T2-weighted imaging and apparent diffusion coefficient maps), together with three clinical variables (prostate volume, PSA, PSA density). The SGNN pipeline transformed each patient’s feature profile into a weighted graph encoding pairwise feature relationships via logistic regression classifiers trained within each cross-validation fold. GCN and GATv2 architectures were evaluated with multiple sparsification strategies and compared against Gradient Boosting, SVM, Random Forest, and logistic regression using 5-fold stratified cross-validation. Results: Among conventional methods, Gradient Boosting achieved the highest ROC-AUC (0.634 ± 0.080). The SGNN pipeline with GATv2, confidence-based sparsification (p = 0.8), and extended node features incorporating graph centrality measures achieved the best performance (ROC-AUC = 0.699 ± 0.044), an absolute improvement of 0.065 over the best conventional method. The addition of topological node features consistently improved performance by 3–5% across configurations. GATv2 outperformed GCN in matched settings. Conclusions: As a proof of concept, the SGNN framework achieved the highest mean ROC-AUC among the evaluated single-timepoint approaches, though results require confirmation in independent external cohorts. By encoding inter-feature relationships as patient-specific graphs, SGNN offers a complementary modelling paradigm for radiomic data in clinical oncology. Future work should incorporate longitudinal data and graph explainability methods.

Background/Objectives: Gliomas are complex and heterogeneous brain tumors characterized by an unfavorable clinical course and a fatal prognosis, which can be improved by an early determination of tumor kind. Here, we developed explainable machine learning (ML) models for classifying three major glioma subtypes (astrocytoma, oligodendroglioma, and glioblastoma) and predicting survival rates based on RNA-seq data. Methods: We analyzed publicly available datasets and applied feature selection techniques to identify key biomarkers. Using various ML models, we performed classification and survival analysis to develop robust predictive models. The best-performing models were then interpreted using Shapley additive explanations (SHAP). Results: Thirteen key genes (TERT, NOX4, MMP9, TRIM67, ZDHHC18, HDAC1, TUBB6, ADM, NOG, CHEK2, KCNJ11, KCNIP2, and VEGFA) proved to be closely associated with glioma subtypes as well as survival. Support Vector Machine (SVM) turned out to be the optimal classification model with the balanced accuracy of 0.816 and the area under the receiver operating characteristic curve (AUC) of 0.896 for the test datasets. The Case-Control Cox regression model (CoxCC) proved best for predicting survival with the Harrell’s C-index of 0.809 and 0.8 for the test datasets. Using SHAP we revealed the gene expression influence on the outputs of both models, thus enhancing the transparency of the prediction generation process. Conclusions: The results indicated that the developed models could serve as a valuable practical tool for clinicians, assisting them in diagnosing and determining optimal treatment strategies for patients with glioma.

We present EpInflammAge, an explainable deep learning tool that integrates epigenetic and inflammatory markers to create a highly accurate, disease-sensitive biological age predictor. This novel approach bridges two key hallmarks of aging—epigenetic alterations and immunosenescence. First, epigenetic and inflammatory data from the same participants was used for AI models predicting levels of 24 cytokines from blood DNA methylation. Second, open-source epigenetic data (25 thousand samples) was used for generating synthetic inflammatory biomarkers and training an age estimation model. Using state-of-the-art deep neural networks optimized for tabular data analysis, EpInflammAge achieves competitive performance metrics against 34 epigenetic clock models, including an overall mean absolute error of 7 years and a Pearson correlation coefficient of 0.85 in healthy controls, while demonstrating robust sensitivity across multiple disease categories. Explainable AI revealed the contribution of each feature to the age prediction. The sensitivity to multiple diseases due to combining inflammatory and epigenetic profiles is promising for both research and clinical applications. EpInflammAge is released as an easy-to-use web tool that generates the age estimates and levels of inflammatory parameters for methylation data, with the detailed report on the contribution of input variables to the model output for each sample.

Yakutia is one of the coldest permanently inhabited regions in the world, characterized by a subarctic climate with average January temperatures near −40 °C and the minimum below −60 °C. Recently, we demonstrated accelerated epigenetic aging of the Yakutian population in comparison to their Central Russian counterparts, residing in a considerably milder climate. In this paper, we analyzed these cohorts from the inflammaging perspective and addressed two hypotheses: a mismatch in the immunological profiles and accelerated inflammatory aging in Yakuts. We found that the levels of 17 cytokines displayed statistically significant differences in the mean values between the groups (with minimal p-value = 2.06 × 10⁻¹⁹), and 6 of them are among 10 SImAge markers. We demonstrated that five out of these six markers (PDGFB, CD40LG, VEGFA, PDGFA, and CXCL10) had higher mean levels in the Yakutian cohort, and therefore, due to their positive chronological age correlation, might indicate a trend toward accelerated inflammatory aging. At the same time, a statistically significant biological age acceleration difference between the two cohorts according to the inflammatory SImAge clock was not detected because they had similar levels of CXCL9, CCL22, and IL6, the top contributing biomarkers to SImAge. We introduced an explainable deep neural network to separate individual inflammatory profiles between the two groups, resulting in over 95% accuracy. The obtained results allow for hypothesizing the specificity of cytokine and chemokine profiles among people living in extremely cold climates, possibly reflecting the effects of long-term human (dis)adaptation to cold conditions related to inflammaging and the risk of developing a number of pathologies.

On October 28–31, 2024, there took place the international conference, “Longevity Nation 2024— Enhancing Research, Development and Education for Healthy Longevity” in Bar-Ilan University, Ramat Gan, Israel (http://www.longevitynation.org/). This conference explored the challenges that rise from population aging, from interdisciplinary perspectives that reflect new science and technology, and many social, cultural, political, economic and philosophical concerns that aging raises. By bringing together leading Israeli and international voices in the longevity space—researchers, developers, investors, educators, decision makers and public figures—the Longevity Nation conference aimed to contribute to increasing the synergy of science, technology and aging society, and help advance ethical scientific and technological solutions for healthy longevity for the benefit of the entire society. As the conference emphasized, in this period of conflict in Israel and the Middle East, it is especially important to build up international collaboration as a basis for future positive development.

Currently, the method of ultrasound diagnostics (echography) is the leading one among other imaging tools in medicine. The history of the method begins in 1942, but the main developments should be attributed to the 1950-1960s, when owing to the first ultrasound machines created in various countries, the fundamental possibility of visualizing tissue structures of various organs in normal and in various forms of pathology was proved. Since the 1970s, the solution of technical problems has led to the creation of ultrasound systems close to modern types of equipment. In the same years, ultrasound examinations for the first time began to be effectively used in the Research Institute of Pediatrics of the USSR Academy of Medical Sciences, where they took a worthy place among other diagnostic methods. For the first time, ultrasound techniques of various organs were developed, their normal age characteristics were established, the possibilities in the diagnosis of many forms of pathology were proved and the criteria for their differential diagnosis were determined. But at the same time, despite the significant diagnostic potential of ultrasound diagnostics, we must not forget about the sufficient subjectivity of the method, which requires special attention and knowledge when obtaining and interpreting echographic images. The newest ultrasound methods that have appeared in recent years include three- and four-dimensional echography, ultrasound tomography, the possibility of panoramic, contrast and intra-organ studies, pulse inversion harmonics, quantitative assessment of organ parenchyma, elastography, various variants of Doppler (including intravascular) methods.