ADAndrey A. Dyachenko

Andrey A. Dyachenko

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrey A. Dyachenko has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    COVID-19 vaccination and survival of cancer patients in Northwestern Russia: a historical registry-based cohort study

    by Andrey A. Dyachenko, Maxim A. Bogdanov, Dmitry V. Bogdanov, Anna A. Meldo, Valeria Yu. Chernina, Victor A. Gombolevskiy, M. Grjibovski, Mikhail Yu. Valkov

    Background: Cancer patients face a significantly elevated risk of severe COVID-19 outcomes. Although vaccination is a cornerstone of prevention, data on vaccination coverage and association with survival among Russian cancer patients remain scarce. We assessed COVID-19 vaccination coverage and its association with overall survival in a population-based cohort of cancer patients in Northwest Russia. Methods: This retrospective registry-based cohort study integrated data from the Population-Based Cancer Registry (PBCR) of the Arkhangelsk Region and the Nenets Autonomous Okrug, regional vaccination records, and an artificial intelligence (AI)-based analysis of chest computed tomography (CT) scans. The cohort consisted of 1,144 cancer patients who underwent CT between August 2020 and April 2021. Vaccination status was ascertained via data linkage. Overall survival (OS) was compared between vaccinated and unvaccinated patients using Kaplan–Meier analysis and multivariable Cox proportional hazards regression, adjusted for demographic, clinical, and AI-derived CT biomarkers. To mitigate immortal time bias, the primary analysis used a landmark approach restricted to patients alive on March 1, 2021 (N = 1,136). A sensitivity analysis used a November 1, 2021 landmark (N = 894). Vaccination status was defined as receipt of at least one dose before the landmark date. Results: Only 6.6% (n=76) of patients received at least one dose of a COVID-19 vaccine (Sputnik V or Sputnik Light). Vaccinated patients were more likely to have earlier-stage cancer and were less likely to be receiving active treatment. In the primary landmark analysis, vaccination was associated with a significantly higher 3-year OS (80.3% vs. 45.7%, p < 0.001). In multivariable analysis, vaccination was independently associated with a 60% lower hazard of all-cause mortality (adjusted HR 0.40, 95% CI 0.25–0.64). AI-detected COVID-19 pneumonia on baseline CT was also an independent predictor of poorer survival (adjusted HR 1.32, 95% CI 1.09–1.59). In the sensitivity analysis (November 1, 2021 landmark), the adjusted HR for vaccination was 0.56 (95% CI 0.34–0.92), showing a consistent but attenuated association. Conclusion: This study reveals critically low COVID-19 vaccination coverage among cancer patients in Northwest Russia. Nevertheless, vaccination was strongly associated with a substantial survival benefit, underscoring its importance as a potentially lifesaving intervention for this vulnerable population.

  • Open Access

    Prognostic role of COVID-19 pneumonia signs and other CT-biomarkers for survival in patients with malignant neoplasms: the ARILUS project

    by A.A. Dyachenko, M.A. Bogdanov, Dmitriy V Bogdanov, Andrej M Grjibovski, A.A. Markov, E.A. Nazarova, Valeria Yu. Chernina, M.G. Belyaev, V.A. Gombolevskiy, Mikhail Yu Valkov

    Background: Clinically manifested pneumonia associated with COVID-19 infection in cancer patients has been associated with worse prognosis. The prognostic significance of subclinical manifestations of pulmonary infiltration is poorly understood. Aims: To estimate the survival of cancer patients with signs of asymptomatic pneumonia detected by a multitarget artificial intelligence (AI) algorithm on chest computed tomography (CT) during the COVID-19 pandemic, and to evaluate factors associated with the risk of death in this population. Materials and methods: This population-based cohort study, conducted within the ARILUS project, included 1,147 examinations of cancer patients performed between August 2020 and May 2021. Signs of pneumonia on CT were detected by the AI algorithm in 556 (48.4%) patients with malignant neoplasms (MN) who had no clinical manifestations of infection at the time of the examination. Overall survival (OS) was assessed using the life table and Kaplan-Meier methods. Multivariate Cox proportional hazards regression analysis was used to identify independent predictors of death and to assess the influence of potential confounding factors. Results: During the follow-up period, 680 deaths were recorded among cancer patients, of which 575 deaths were due to MN progression. Three-year OS differed significantly between the groups: in patients without signs of pulmonary infiltration on CT, it was 60.7% (95% CI 56.6%– 64.7%), whereas in patients with AI-detected signs of pneumonia, it was 45.6% (95% CI 41.3%– 49.8%) (p<0.001). In the multivariable regression analysis, independent factors associated with an unfavorable prognosis (death) were: presence of pulmonary infiltration (adjusted hazard ratio (HR) 1.31; 95% CI 1.09–1.58), male sex (HR 1.25; 95% CI 1.00–1.57), and MN stage (HR 1.78 for stage II, HR 2.93 for stage III, and HR 4.74 for stage IV compared to stage I). Signs of pulmonary emphysema (HR 1.84), aortic aneurysm (HR 1.75), and coronary artery calcification (HR 1.22-1.34), which were significantly associated with the risk of death in the univariable analysis, lost their prognostic significance in the multivariable model after adjustment for other variables. Conclusions: Asymptomatic COVID-19 pneumonia detected by AI on CT is an independent predictor of reduced overall survival in MN patients. Automated AI screening for such changes may be recommended in routine practice.


  • Open Access

    Prevalence of COVID-19-associated pneumonia signs on chest computed tomography in cancer patients: the ARILUS study

    by A. A. Dyachenko, A. M. Grjibovski, M. A. Bogdanov, D. V. Bogdanov, E. A. Nazarova, A. A. Meldo, V. Yu. Chernina, M. G. Belyaev, V. A. Gombolevsky, M. Yu. Valkov

    Aim. To study the prevalence of pneumonia features associated with 2019 coronavirus disease (COVID-19) in cancer patients based on chest computed tomography (CT) data using an artificial intelligence (AI) algorithm.Materials and methods. A cross-sectional study was conducted as part of the ARILUS project. Using multitarget AI, CT images of 1148 patients examined at the Arkhangelsk Clinical Oncology Dispensary from 01.04.2020 to 31.12.2021 were analyzed. Patients were divided into groups: without signs of pneumonia (n = 592, 51.6%) and with signs of pneumonia (n = 556, 48.4%). In 95.3% of patients with pneumonia, the lesion volume was less than 25% (CT-1). Using multivariate Poisson regression, adjusted prevalence ratios (aPR) with 95% confidence intervals (CI) were calculated.Results. For demographic characteristics such as gender, age, place of residence, no relationship with the presence of signs of COVID-19 pneumonia was established. Topography of neoplasm is associated with the presence of signs of COVID-19 pneumonia (reference group – cancers of the female genital organs): lung cancer – aPR 1.87; 95% CI: 1.40–2.49; head and neck cancers – aPR 1.85; 95% CI: 1.32–2.58; upper gastrointestinal tract – aPR 1.51; 95% CI: 1.12–2.04; breast cancer – aPR: 1.38; 95% CI: 1.00–1.90; p < 0.01. The presence of pulmonary emphysema is associated with signs of COVID-19 pneumonia: aPR 1.25; 95% CI: 1.09–1.45, p = 0.002. With an increase in the Agatston score (AS) reflecting coronary artery calcification (reference group absence of calcification), the association with the presence of signs of COVID-19 pneumonia increased – for AS 1–99: aPR 1.24; 95% CI: 1.05–1.47; AS 100– 299: aPR 1.58; 95% CI: 1.33–1.87; AS 300 and above: aPR 1.61; 95% CI: 1.36–1.90; p < 0.001 for a linear trend.Conclusion. Factors associated with the detection of COVID-19 pneumonia among cancer patients include the localization of neoplasms in the lungs, head and neck organs, upper gastrointestinal tract, breast, and as well as the presence of signs of emphysema and coronary calcification according to CT data

  • Open Access

    Survival of patients with malignant neoplasms to be screened as part of the adult medical examination during the COVID-19 pandemic

    by A. A. Dyachenko, Л. Е. Валькова, M. L. Levit, Yu. A. Voroshilov, M. Yu. Valkov

    Purpose of the study. To assess the variations of survival in malignant neoplasms subject to screening as part of the regular adult population check-up (index MN, iMN) during the COVID-19 pandemic according to the data of the Arkhangelsk Regional Cancer Registry (ARCR).Materials and methods. Data on nine iMN in the Arkhangelsk region were extracted from the ARCR database. Using the actuarial method, 1-year cancer-specific (CSS) and overall (OS) survival were estimated during the COVID-19 pandemic in 2020–2021. This period was compared with the 2018–2019 period before the pandemic. Differences between the periods were assessed using the log-rank method. Cox regression analysis was used to identify possible causes of differences in survival between the periods.Results. A total of 12,354 records of nine iMNs were selected to analyze the survival during the COVID-19 pandemic. For all malignant neoplasms, there was a decrease in the one-year OSR rates, which was statistically significant for lung cancer (from 42.4 % to 32.8 %, p = 0.0001) and cervical cancer (from 90.3 % to 80.8 %, p = 0.02), and OS (by 2.6 %–11.0 %, significant for seven of the nine iMNs). Compared with the pre-COVID period, during the pandemic, the proportion of deaths of patients with iMNs from respiratory diseases increased by 1.5 times and the proportion of deaths from external causes increased from 3 % to 9 %, chi-square (4) = 41.8, p = 0.00001. In the regression models of CSS and OS, after adjusting for stage, the hazard ratio decreased from 1.15 (95 % confidence interval (CI) 1.07–1.24) to 1.10 (95 % CI 1.03–1.19) and from 1.22 (95 % CI 1.14–1.31) to 1.18 (95 % CI 1.10–1.26). In multivariable regression, the risk of cancer-specific and all-cause death in patients with malignant neoplasms during the pandemic remained higher by 16 % and 24 %.Conclusion. The 15–33 % higher risk of cancer-specific and all-cause death during the COVID-19 pandemic is explained by an increase in the proportion of advanced stages due to limited access to screening. Longer-term survival analysis is required.


  • Open Access

    Using artificial intelligence to predict and prevent non-cancer mortality in patients with cancer: ARILIS study protocol

    by Mikhail Yu. Valkov, Andrej М. Grjibovski, Alexander V. Kudryavtsev, Maxim A. Bogdanov, Dmitriy V. Bogdanov, Andrey A. Dyachenko, Valeria Yu. Chernina, Mikhail G. Belyaev, Farukh R. Yaushev, Elena V. Panina, et al.

    Aim: To present the ARILIS study aimed at assessing the use of artificial intelligence to analyze chest computed tomography (CT) data to predict and prevent non-cancer mortality in patients with cancer. Material and methods: This cohort study will include patients with cancer diagnosed in the Arkhangelsk region (AR) within the 2019–2023 period. The COVID-19 patients with pneumonia, patients with general medical conditions, and the population of the Know Your Heart Study are planned to be enrolled as control groups. To detect and quantify the CT signs of the cardiovascular, pulmonary, and bone disorders, the thoracic СT scans of all the subjects will be processed using the multi-targeted AI algorithm provided by the IRA Labs company. From the date of processing of the thoracic CT scans using the multi-targeted AI algorithm, the study subjects will be followed for new clinical diagnoses and all-cause mortality. Expected results: T he study will determine the prevalence of CT signs of the cardiovascular, pulmonary, and bone disorders in patients with cancer compared with the Know Your Heart Study population sample. It will also assess the incidence of cardiovascular, pulmonary, and bone events and all-cause mortality in patients with cancer compared with control groups, explore the potential of the IRA Labs’ multi-targeted AI algorithm in the assessment and reclassification of assessed risks in patients with cancer, and provide a software product for using mtIA in healthcare practice.


  • Open Access

    Impact of surrogate molecular biological subtype on breast cancer survival: in-depth epidemiological analysis based on the Archangelsk regional cancer registry data

    by Анна Агаева, Дмитрий Громов, Ольга Чемакина, Анастасия Светлакова, Людмила Валькова, Андрей Дяченко, Дмитрий Богданов, Михаил Вальков


  • Open Access

    Epidemiological survival predictors of cancer of the corpus uteri: a population-based analysis

    by A. V. Svetlakova, D. D. Gromov, O. V. Chemakina, A. V. Agayeva, Л. Е. Валькова, A. A. Dyachenko, D. V. Bogdanov, M. Yu. Valkov

    Cancer of the corpus uteri (CCU) is one of the most common gynecological malignancies in high- and middleincome countries. The objective of the study was to evaluate the factors predicting survival in CCU patients over the period 2000-2021 using the data of population-based cancer registry of the Arkhangelsk region. Material and Methods. Cancer-specific survival (CSS) of patients with CCU for the period 2000-21 was evaluated using life tables and Kaplan-Mayer methods with a log-rank test. The Cox proportional hazards regression model was used to assess the effect of prognostic factors on survival time. Results. A total of 3272 cases were selected for the analysis. The 5-year survival rates improved from 70.6 % in 2000-04 to 75.6 % in 2015-19. In stage I, II, III, and IV CUN, the 5-year survival rates were 90.8 % (95 % CI 89.3-92.0 %), 71.1 (95 % CI 66.3-75.4 %), 46.7 (95 % CI 41.4-51.8 %), and 3.9 (95 % CI 1.5-7.5 %), respectively; pConclusion. In this population-based study, we have found that the survival of patients with CCU is significantly affected by age and place of residence, which may indicate a limited access of some patients to effective treatment and requires further analysis. No increased risk of death from CCU during the COVID-19 pandemic was found.


  • Open Access

    Population factors predicting survival in breast cancer: analysis according to the data of the Arkhangelsk Regional Cancer Registry in 2000–2020

    by A. V. Agaeva, A. V. Svetlakova, D. D. Gromov, O. V. Chemakina, Л. Е. Валькова, A. A. Dyachenko, D. V. Bogdanov, M. Yu. Valkov

    Background. Breast cancer (BC) is the leading cancer in the world and in Russia. Epidemiological factors predicting breast cancer survival in Russia have not been studied enough. Aim. To evaluate the factors predicting survival in BC by the data of the Arkhangelsk Regional Cancer Registry in 2000–2020 and the survival during the COVID-19 pandemic Materials and methods. Data on all cases of Вс for 2000–2020 retrieved from the Arkhangelsk Regional Cancer Registry database. Cancer-specific survival was estimated using the Kaplan–Meier and the life tables method. The prognostic value of variables available in Arkhangelsk Regional Cancer Registry was assessed in Cox regression. Results. The final analysis included 9,089 cases of breast cancer. During the observation period, 2723 deaths from breast cancer were registered. The one-, five- and ten-year survival rates in the entire population were 91.6 %, 73.0 % and 64.0 %, respectively. In a multivariate analysis, the risk of death from BC increased by 2.9, 8.2, 21.3 and 6.8 at 2, 3, 4 and unknown stages; 2.1 times with the localization of the tumor in the area of the nipple and areola; by 33 % in ductal cancer compared with lobular cancer, by 1.8 and 2.6 times in those who received palliative treatment and did not receive treatment; by 33 % in women aged 80 years and older; by 22 % for those living in rural areas. In the period 2013–2019, the 5-year cancer-specific survival reached 79.1 %, which is 14 % and 6 % higher than in the periods 2000–2006 and 2007–2012. Survival rates have not declined during the COVID-19 pandemic. Conclusion. The risk of death from BC is increased in advanced stages, ductal morphology, localization in the nipple-areolar region, age over 80 years, and living in rural areas. During the COVID-19 pandemic BC survival did not worsen, but this requires further study.


  • Open Access

    Impact of the СOVID-19 pandemic on cancer incidence in patients undergoing cancer screening during annual health checkup (population-based study)

    by Л. Е. Валькова, A. A. Dyachenko, V. M. Merabishvili, D. V. Bogdanov, A. V. Berezin, E. F. Potekhina, M. Yu. Valkov

    Background. During the COVID-19 pandemic, annual adult check-ups have been postponed, resulting in cancer screening disruption.The aim of the study was to evaluate changes in the incidence and stage distribution of malignancies included in the screening program during the COVID-19 pandemic using the Arkhangelsk Regional Cancer Registry (ARRC).Material and Methods. We assessed the changes of the incidence rates and stage distribution for the colon, rectum, lung, breast, cervix, uterine body, ovary, prostate and kidney cancers over the periods 2018–19 and 2020–21. Results. A total of 12354 cases with 9 cancers were selected: 6680 for the period 2018–19 and 5674 (-15.1 %) for the period 2020-21. The most significant decrease in crude and age-standardized incidence rates was registered in patients with lung (-18.0–18.1 %), rectum (-25.1–25.9 %) and cervix (-33.6–36.9 %) cancers, p˂0.001. The decrease was not significant in patients with breast, uterine body, and kidney cancers. The proportion of patients with stage I decreased in lung cancer (-20.0 %, from 14.8 % to 11.8 %), rectum (-20.2 %, from 20.9 % to 16.7 %), and uterine cervix (-37.1 %, from 53.2 % to 33.5 %). In prostate and kidney cancers, the proportion of patients with stage I increased by 30 % (from 19.5 % to 25.4 %) and 17.6 % (from 45.9 % to 54.0 %), respectively. A significant reduction in the proportion of early stages during the COVID-19 pandemic was observed in lung and cervical cancer.Conclusion. Postponed health checkups due to COVID-19 pandemic disruptions have led to substantial reductions in new cancers being diagnosed, mainly for cervical, lung, colon and rectal cancers. No significant changes were observed for other cancers. Further analysis of mortality and survival of cancer patients is required.


  • Increment of the incidence of glioblastoma following decrease in the incidence of brain tumors in 2000-2020: a population-based registry study

    by K. Kalyango, A.A. Dyachenko, D.V. Bogdanov, E.F. Potekhina, V.M. Merabishvili, M.YU. Valkov

    Распространенность и динамика отдельных морфологических вариантов нейроглиальных злокачественных новообразований головного мозга (ЗНО ГМ) (код С71 по МКБ-10) для популяции Российской Федерации неизвестна. ЦЕЛЬ ИССЛЕДОВАНИЯ Оценить динамику заболеваемости ЗНО ГМ в 2000—2020 гг. на основе индивидуальных записей морфологически верифицированных случаев в канцер-регистре Архангельской области. МАТЕРИАЛ И МЕТОДЫ Рассчитаны «грубые» и стандартизованные по возрасту (СПВ) (стандарт ВОЗ 2000 г.) показатели заболеваемости ЗНО ГМ в период с 2000 по 2020 г. в целом по группе С70—С71 и с учетом морфологических подтипов опухоли. Заболеваемость морфологически верифицированной глиобластомой (ГБ) детально оценена с учетом пола, возраста, места проживания. Для оценки динамики и значимости линейных трендов использовали сегментированный регрессионный анализ. РЕЗУЛЬТАТЫ Всего за период с 2000 по 2020 г. выявлено 1699 случаев ЗНО ГМ, морфологическая верификация получена у 1289 (76%) больных, из них у 467 (27%), 92 (5%) и 307 (18%) выявлены ГБ, анапластические глиомы G3 и глиомы G2 соответственно. Доля ГБ и анапластических глиом возросла с 23,4% и 3,9% в 2000 г. до 55,3% и 9,2% в 2020 г. соответственно. На фоне снижения СПВ показателей для всей группы С71 после 2015 г. с 5,2 до 3,2 случая на 100 тыс. населения (ежегодная убыль 7,1%) заболеваемость ГБ монотонно возрастала — с 1,0 до 2,1 случая на 100 тыс. населения (ежегодный прирост 6,2%). Не выявлены различия в заболеваемости между мужчинами и женщинами. Уровни СПВ показателей заболеваемости были на 50—70% выше среди сельского населения. ЗАКЛЮЧЕНИЕ Выявлен статистически значимый рост заболеваемости глиобластомой — более чем в 2 раза за последние 20 лет, связанный, вероятно, с улучшением диагностики и регистрации этого заболевания. Требуется углубленный анализ заболеваемости и выживаемости при редких опухолях нейроглии.