Alexander V. Plastun
Research Subjects
Research Interests
Alexander V. Plastun has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Andrey V. Budnevskiy
Voronezh State Medical University named after N.N. Burdenko
2 shared publications - Evgeniy S. Ovsyannikov
Voronezh State Medical University named after N.N. Burdenko
2 shared publications - Sergey Nikolaevich Avdeev
Sechenov First Moscow State Medical University, Moscow, Russia
2 shared publications - Vladimir Bondarev
Sevastopol State University
2 shared publications - Lidiya Ur'EVna Nikitina
I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University)
1 shared publication S.N. Feigelman
Voronezh State Medical University named after N.N. Burdenko
1 shared publication
Latest Publications
- Open Access
- 18 August 2026
- Published by Consilium Medicum in Terapevticheskii arkhiv
- Vol. 98 (8) , 478-485
Advanced diagnostic capabilities for cough assessment utilizing the neural network model «CoughScan»: findings from a prospective, comparative observational study
Background. Identifying the character, frequency, and intensity of cough is crucial in clinical practice, aiding in differential diagnosis, influencing treatment choices. «CoughScan» is a software with an embedded neural network model designed to assess cough frequency in real-time for diagnostic and monitoring purposes. Aim. To obtain additional data on the efficacy and safety of Rengalin® in the treatment of cough in adults with acute respiratory viral infections (ARVI) using both traditional and new intelligent technologies. Materials and methods. An observational study was conducted involving 60 patients with ARVI, receiving Rengalin® for cough management. Outpatient patients were divided into 2 groups: the main group (n=40) received Rengalin® for 7 days, while the control group (n=20) received no cough medication. The severity of symptoms of ARVI and cough was assessed with Cough severity scale (CSS), «CoughScan», Bronchitis Severity Scale (BSS). Results. The cough severity score on CSS decreased by 2.9 points in the Rengalin® group and by 1.5 points in the control group (p=0.0004). The average BSS score reduced by 1.3 units with Rengalin® and by 0.2 units in controls (p=0.0001). The mean duration of cough during treatment was 5.7±0.2 days versus 7.2±0.4 days without treatment (p=0.0178). Monitoring of daily cough intensity with «CoughScan» also showed a statistically significant advantage in the Rengalin® group (p0.0001). A non-inferiority test based on the area under the curve (AUC) over 7 days indicated comparable results between «CoughScan» and the CSS, with differences within 10%. Conclusion. «CoughScan» is a convenient and reliable tool for assessing cough dynamics in outpatient settings. Its data are comparable to the Cough severity scale regarding treatment efficacy, with antitussive activity of Rengalin® evident from the early days of therapy.
- 18 August 2026
- Published by Consilium Medicum in Terapevticheskii arkhiv
- Vol. 98 (8) , 478-485
Open AccessAdvanced diagnostic capabilities for cough assessment utilizing the neural network model «CoughScan»: findings from a prospective, comparative observational study
Background. Identifying the character, frequency, and intensity of cough is crucial in clinical practice, aiding in differential diagnosis, influencing treatment choices. «CoughScan» is a software with an embedded neural network model designed to assess cough frequency in real-time for diagnostic and monitoring purposes. Aim. To obtain additional data on the efficacy and safety of Rengalin® in the treatment of cough in adults with acute respiratory viral infections (ARVI) using both traditional and new intelligent technologies. Materials and methods. An observational study was conducted involving 60 patients with ARVI, receiving Rengalin® for cough management. Outpatient patients were divided into 2 groups: the main group (n=40) received Rengalin® for 7 days, while the control group (n=20) received no cough medication. The severity of symptoms of ARVI and cough was assessed with Cough severity scale (CSS), «CoughScan», Bronchitis Severity Scale (BSS). Results. The cough severity score on CSS decreased by 2.9 points in the Rengalin® group and by 1.5 points in the control group (p=0.0004). The average BSS score reduced by 1.3 units with Rengalin® and by 0.2 units in controls (p=0.0001). The mean duration of cough during treatment was 5.7±0.2 days versus 7.2±0.4 days without treatment (p=0.0178). Monitoring of daily cough intensity with «CoughScan» also showed a statistically significant advantage in the Rengalin® group (p0.0001). A non-inferiority test based on the area under the curve (AUC) over 7 days indicated comparable results between «CoughScan» and the CSS, with differences within 10%. Conclusion. «CoughScan» is a convenient and reliable tool for assessing cough dynamics in outpatient settings. Its data are comparable to the Cough severity scale regarding treatment efficacy, with antitussive activity of Rengalin® evident from the early days of therapy.
- 2 July 2026
- Published by Media Sphere Publishing Group in Journal of Respiratory Medicine
- Vol. 2 (2)
Artificial intelligence in respiratory medicine
Artificial intelligence (AI) is increasingly being implemented in all spheres of life, occupying a special place in modern medicine. The main advantage of AI in comparison with the work of specialist doctors is the rapid processing of large amounts of data with the detection of microscopic changes inaccessible to human senses. Nevertheless, there are significant drawbacks in the work of AI that limit its use in routine medical practice, for example, the high dependence of accuracy on the quality of the training sample and the principles of identifying patterns that are not fully known, as well as the lack of strict standardization regulations.
- 2 July 2026
- Published by Media Sphere Publishing Group in Journal of Respiratory Medicine
- Vol. 2 (2)
Artificial intelligence in respiratory medicine
Artificial intelligence (AI) is increasingly being implemented in all spheres of life, occupying a special place in modern medicine. The main advantage of AI in comparison with the work of specialist doctors is the rapid processing of large amounts of data with the detection of microscopic changes inaccessible to human senses. Nevertheless, there are significant drawbacks in the work of AI that limit its use in routine medical practice, for example, the high dependence of accuracy on the quality of the training sample and the principles of identifying patterns that are not fully known, as well as the lack of strict standardization regulations.