Denis V. Butnaru
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Denis V. Butnaru has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Aleksandr Zolotarev
Department of Pediatrics and Pediatric Infectious Diseases, Institute of Child’s Health, Sechenov First Moscow State Medical University (Sechenov University), 119991 Moscow, Russia
2 shared publications - Alexey S. Rzhevskiy
Institute of Molecular Theranostics, Sechenov First Moscow State Medical University, 119991 Moscow, Russia
2 shared publications - Alexey Zaikin
Research Center in Artificial Intelligence, Institute of Information Technologies, Mathematics and Mechanics, Lobachevsky State University, Nizhny Novgorod 603022, Russia
2 shared publications - Alina Y. Kapitannikova
Institute of Molecular Theranostics, Sechenov First Moscow State Medical University, 119991 Moscow, Russia
2 shared publications - Anastasia Shikhaleva
Department of Paediatrics and Paediatric Infectious Diseases, Institute of Child’s Health, Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russia
2 shared publications - Andrei Vasilyevich Zvyagin
Scientific Center for Translational Medicine, Sirius University of Science and Technology, 354340 Sirius, Russia
2 shared publications
Latest Publications
- Open Access
- 28 April 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (9) , 3367
Sex-Stratified Machine Learning for the Prediction of Post-COVID Condition: A Longitudinal Cohort Study
Background: Post-COVID-19 condition (PCC) affects many survivors, with evidence of sex-specific differences in prevalence and symptom profiles. However, few prediction studies have examined whether sex-stratified models improve prediction or generalize across sexes. This study aimed primarily to develop and compare sex-stratified machine learning models for PCC prediction using routinely available baseline variables, and secondarily to assess cross-sex generalizability and adversarial robustness. Methods: We analyzed a prospective longitudinal cohort of 1006 adults hospitalized with COVID-19 at Sechenov University Hospital Network (Moscow, Russia). Demographics, smoking status, and pre-existing comorbidities were extracted from medical records, and PCC status was assessed at 6-month follow-up. Machine learning models—including classical algorithms and graph-based neural networks—were trained separately for males and females. Cross-sex validation evaluated generalizability, variable importance aided interpretation, and adversarial perturbations assessed model robustness. Results: PCC prevalence was higher in females (53.9%) than males (39.1%). Overall predictive performance was modest across all models, with AUC values ranging approximately 0.50–0.61. Graph-based models achieved the highest discrimination, with the best AUC reaching approximately 0.61, while classical approaches provided limited predictive value. Cross-sex validation showed minor asymmetry: models trained on male data performed slightly better on female cases than vice versa. Adversarial testing revealed sensitivity of all models to input perturbations. Conclusions: Demographics and comorbidities alone provide insufficient information for reliable PCC prediction. Modest sex-specific differences in model generalizability suggest distinct, sex-associated PCC phenotypes, but richer multimodal data—including clinical biomarkers, wearable-derived measures, and patient-reported outcomes—will be required to develop clinically useful and equitable predictive models. Sex-stratified approaches should be considered in future post-viral syndrome prediction studies.
- 28 April 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (9) , 3367
Open AccessSex-Stratified Machine Learning for the Prediction of Post-COVID Condition: A Longitudinal Cohort Study
Background: Post-COVID-19 condition (PCC) affects many survivors, with evidence of sex-specific differences in prevalence and symptom profiles. However, few prediction studies have examined whether sex-stratified models improve prediction or generalize across sexes. This study aimed primarily to develop and compare sex-stratified machine learning models for PCC prediction using routinely available baseline variables, and secondarily to assess cross-sex generalizability and adversarial robustness. Methods: We analyzed a prospective longitudinal cohort of 1006 adults hospitalized with COVID-19 at Sechenov University Hospital Network (Moscow, Russia). Demographics, smoking status, and pre-existing comorbidities were extracted from medical records, and PCC status was assessed at 6-month follow-up. Machine learning models—including classical algorithms and graph-based neural networks—were trained separately for males and females. Cross-sex validation evaluated generalizability, variable importance aided interpretation, and adversarial perturbations assessed model robustness. Results: PCC prevalence was higher in females (53.9%) than males (39.1%). Overall predictive performance was modest across all models, with AUC values ranging approximately 0.50–0.61. Graph-based models achieved the highest discrimination, with the best AUC reaching approximately 0.61, while classical approaches provided limited predictive value. Cross-sex validation showed minor asymmetry: models trained on male data performed slightly better on female cases than vice versa. Adversarial testing revealed sensitivity of all models to input perturbations. Conclusions: Demographics and comorbidities alone provide insufficient information for reliable PCC prediction. Modest sex-specific differences in model generalizability suggest distinct, sex-associated PCC phenotypes, but richer multimodal data—including clinical biomarkers, wearable-derived measures, and patient-reported outcomes—will be required to develop clinically useful and equitable predictive models. Sex-stratified approaches should be considered in future post-viral syndrome prediction studies.
- Open Access
Post-COVID-19 Condition Prediction in Hospitalised Cancer Patients: A Machine Learning-Based Approach
Background: The COVID-19 pandemic has led to widespread long-term complications, known as post-COVID conditions (PCC), particularly affecting vulnerable populations such as cancer patients. This study aims to predict the incidence of PCC in hospitalised cancer patients using the data from a longitudinal cohort study conducted in four major university hospitals in Moscow, Russia. Methods: Clinical data have been collected during the acute phase and follow-ups at 6 and 12 months post-discharge. A total of 49 clinical features were evaluated, and machine learning classifiers including logistic regression, random forest, support vector machine (SVM), k-nearest neighbours (KNN), and neural network were applied to predict PCC. Results: Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. KNN demonstrated the highest predictive performance, with an AUC of 0.80, sensitivity of 0.73, and specificity of 0.69. Severe COVID-19 and pre-existing comorbidities were significant predictors of PCC. Conclusions: Machine learning models, particularly KNN, showed some promise in predicting PCC in cancer patients, offering the potential for early intervention and personalised care. These findings emphasise the importance of long-term monitoring for cancer patients recovering from COVID-19 to mitigate PCC impact.
Open AccessPost-COVID-19 Condition Prediction in Hospitalised Cancer Patients: A Machine Learning-Based Approach
Background: The COVID-19 pandemic has led to widespread long-term complications, known as post-COVID conditions (PCC), particularly affecting vulnerable populations such as cancer patients. This study aims to predict the incidence of PCC in hospitalised cancer patients using the data from a longitudinal cohort study conducted in four major university hospitals in Moscow, Russia. Methods: Clinical data have been collected during the acute phase and follow-ups at 6 and 12 months post-discharge. A total of 49 clinical features were evaluated, and machine learning classifiers including logistic regression, random forest, support vector machine (SVM), k-nearest neighbours (KNN), and neural network were applied to predict PCC. Results: Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. KNN demonstrated the highest predictive performance, with an AUC of 0.80, sensitivity of 0.73, and specificity of 0.69. Severe COVID-19 and pre-existing comorbidities were significant predictors of PCC. Conclusions: Machine learning models, particularly KNN, showed some promise in predicting PCC in cancer patients, offering the potential for early intervention and personalised care. These findings emphasise the importance of long-term monitoring for cancer patients recovering from COVID-19 to mitigate PCC impact.
- Open Access
- 2 December 2022
- Published by MDPI AG in Biomedicines
- Vol. 10 (12) , 3115
Liquid Biopsy in Diagnosis and Prognosis of Non-Metastatic Prostate Cancer
Currently, sensitive and specific methods for the detection and prognosis of early stage PCa are lacking. To establish the diagnosis and further identify an appropriate treatment strategy, prostate specific antigen (PSA) blood test followed by tissue biopsy have to be performed. The combination of tests is justified by the lack of a highly sensitive, specific, and safe single test. Tissue biopsy is specific but invasive and may have severe side effects, and therefore is inappropriate for screening of the disease. At the same time, the PSA blood test, which is conventionally used for PCa screening, has low specificity and may be elevated in the case of noncancerous prostate tumors and inflammatory conditions, including benign prostatic hyperplasia and prostatitis. Thus, diverse techniques of liquid biopsy have been investigated to supplement or replace the existing tests of prostate cancer early diagnosis and prognostics. Here, we provide a review on the advances in diagnosis and prognostics of non-metastatic prostate cancer by means of various biomarkers extracted via liquid biopsy, including circulating tumor cells, exosomal miRNAs, and circulating DNAs.
- 2 December 2022
- Published by MDPI AG in Biomedicines
- Vol. 10 (12) , 3115
Open AccessLiquid Biopsy in Diagnosis and Prognosis of Non-Metastatic Prostate Cancer
Currently, sensitive and specific methods for the detection and prognosis of early stage PCa are lacking. To establish the diagnosis and further identify an appropriate treatment strategy, prostate specific antigen (PSA) blood test followed by tissue biopsy have to be performed. The combination of tests is justified by the lack of a highly sensitive, specific, and safe single test. Tissue biopsy is specific but invasive and may have severe side effects, and therefore is inappropriate for screening of the disease. At the same time, the PSA blood test, which is conventionally used for PCa screening, has low specificity and may be elevated in the case of noncancerous prostate tumors and inflammatory conditions, including benign prostatic hyperplasia and prostatitis. Thus, diverse techniques of liquid biopsy have been investigated to supplement or replace the existing tests of prostate cancer early diagnosis and prognostics. Here, we provide a review on the advances in diagnosis and prognostics of non-metastatic prostate cancer by means of various biomarkers extracted via liquid biopsy, including circulating tumor cells, exosomal miRNAs, and circulating DNAs.
- Open Access
Isolation of Circulating Tumor Cells from Seminal Fluid of Patients with Prostate Cancer Using Inertial Microfluidics
Prostate cancer (PCa) diagnosis is primarily based on prostate-specific antigen (PSA) testing and prostate tissue biopsies. However, PSA testing has relatively low specificity, while tissue biopsies are highly invasive and have relatively low sensitivity at early stages of PCa. As an alternative, we developed a technique of liquid biopsy, based on isolation of circulating tumor cells (CTCs) from seminal fluid (SF). The recovery of PCa cells from SF was demonstrated using PCa cell lines, achieving an efficiency and throughput as high as 89% (±3.8%) and 1.7 mL min−1, respectively, while 99% (±0.7%) of sperm cells were disposed of. The introduced approach was further tested in a clinical setting by collecting and processing SF samples of PCa patients. The yield of isolated CTCs measured as high as 613 cells per SF sample in comparison with that of 6 cells from SF of healthy donors, holding significant promise for PCa diagnosis. The correlation analysis of the isolated CTC numbers with the standard prognostic parameters such as Gleason score and PSA serum level showed correlation coefficient values at 0.40 and 0.73, respectively. Taken together, our results show promise in the developed liquid biopsy technique to augment the existing diagnosis and prognosis of PCa.
Open AccessIsolation of Circulating Tumor Cells from Seminal Fluid of Patients with Prostate Cancer Using Inertial Microfluidics
Prostate cancer (PCa) diagnosis is primarily based on prostate-specific antigen (PSA) testing and prostate tissue biopsies. However, PSA testing has relatively low specificity, while tissue biopsies are highly invasive and have relatively low sensitivity at early stages of PCa. As an alternative, we developed a technique of liquid biopsy, based on isolation of circulating tumor cells (CTCs) from seminal fluid (SF). The recovery of PCa cells from SF was demonstrated using PCa cell lines, achieving an efficiency and throughput as high as 89% (±3.8%) and 1.7 mL min−1, respectively, while 99% (±0.7%) of sperm cells were disposed of. The introduced approach was further tested in a clinical setting by collecting and processing SF samples of PCa patients. The yield of isolated CTCs measured as high as 613 cells per SF sample in comparison with that of 6 cells from SF of healthy donors, holding significant promise for PCa diagnosis. The correlation analysis of the isolated CTC numbers with the standard prognostic parameters such as Gleason score and PSA serum level showed correlation coefficient values at 0.40 and 0.73, respectively. Taken together, our results show promise in the developed liquid biopsy technique to augment the existing diagnosis and prognosis of PCa.