G. A. Bledzhyants

G. A. Bledzhyants

Auto-generated profile, based on publicly available information

G. A. Bledzhyants

A.N. Bakulev National Medical Research Center of Cardiovascular Surgery

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2022 in Medical alphabet
Verified
Journal Article
Closed access
PDF file
EME. G. Margaryan
E. G. Margaryan
AKA. G. Kadzhoian
A. G. Kadzhoian
NNNina Novozhilova
Nina Novozhilova
AAArthur Atanesyan
Arthur Atanesyan
VKV. E. Komogortseva
V. E. Komogortseva
GBG. A. Bledzhyants
G. A. Bledzhyants
Aim. To substantiate the need for the use of digital systems to support medical decision-making in the diagnosis of diseases of the oral mucosa.Materials and Methods. The study was conducted by the method of anonymous questionnaires, dedicated to the evaluation of the use of digital systems to support medical decision-making in the diagnosis of diseases of the oral mucosa, on the basis of the Institute of Dentistry I.M. Sechenov First Moscow State Medical University (Sechenov University). The study analyzed 200 questionnaires of doctors aged 20 to 70 years. The main methods used in the study: statistical method using the Kruskal-Wallis test, followed by pairwise comparison using the Mann-Whitney-Wilcoxon test (with Benjamin-Hochberg correction for multiple comparisons), questionnaire.Results. It was revealed that dentists with a long experience of medical practice from 15 to 20 years (77,8%) more often detect manifestations of diseases of the oral mucosa at a medical appointment. When analyzing the diagnosis of oral mucosa diseases, depending on the specialization of the dentist, it was found that this group of pathologies is more often determined by orthodontists(68,8%). At the same time, for the majority of specialists (59%), the diagnosis of diseases of the oral mucosa is difficult. Dentists of various specializations in most cases noted difficulties in determining a presumptive diagnosis (59.5%). At the same time, most specialists associated this with a lack of knowledge and experience in working with patients with diseases of the oral mucosa (66.5%) and with a large variety forms of diseases of the oral mucosa (54%) and resorted to the use of additional sources of information from textbooks, manuals, information articles, as well as the help of colleagues (64.5%). However, at clinical appointments, many doctors faced a lack of time to use reference literature (48.5%). As a result of the survey, it was also revealed that the majority of respondents (64,5%) would like to use the medical decision support system integrated into the medical information system of a medical institution.

2 November 2024 in Medical alphabet
Verified
Journal Article
Closed access
PDF file
EME. G. Margaryan
E. G. Margaryan
YKYu. S. Kurenkova
Yu. S. Kurenkova
KLK. V. Lalayan
K. V. Lalayan
МАМ. Т. Абдельрахим
М. Т. Абдельрахим
AKA. G. Kadzhoian
A. G. Kadzhoian
КЛК. B. Лалаян
К. B. Лалаян
Aim: to justify the necessity of machine learning technology in treatment and diagnostics in dentistry.Material and methods: the research was taken using the method of anonymous questionnaire to estimate the demand and necessity of machine learning technology in diagnostics and treatment in dentistry on the basis of the E.V Borovsky Institute of Dentistry I.M Sechenov First Moscow State Medical University (Sechenov University). 100 participants from different dental specialities aged 20 to 54 took part in the questionnaire. Wilson score interval and Student’s T Critical Values were used for the statistical analysis of the Results.Results: during the study, it was found that the majority of dentists who participated in the questionnaire (54%) have challenges in diagnosing oral mucosal diseases. Herewith dentists with work experience more than 5 years diagnose this kind of disease more frequently than specialists with less work experience (p<0.05). Surgical dentists (46,6%) and prosthetic specialists (50%) diagnose this pathology most often. Clinicians attribute diagnostic challenges to the lack of experience (85%) and low occurrence of patients with this group of diseases. During treatment and diagnostics 84% of residents mentioned that they compare their patients’ clinical cases with clinical cases from the Internet and other resources, 78% of residents believe that machine learning will help to increase the efficiency of diagnosing oral mucosal diseases in clinical work. During the held research, it was found that 85% of participating dentists would definitely use digital programs with machine learning in their clinical work for treatment and diagnostics.Conclusions: the presence of problems in treatment and diagnostics of oral mucosal diseases was confirmed, and to solve it, the demand and the need to develop and implement digital systems based on artificial intelligence using machine learning technology were substantiated. 

24 September 2025 in Medical alphabet
Verified
Journal Article
Open access
PDF file
EME. G. Margaryan
E. G. Margaryan
GBG. A. Bledzhyants
G. A. Bledzhyants
AKA. G. Kadzhoian
A. G. Kadzhoian
YKYu. S. Kurenkova
Yu. S. Kurenkova
MAM. T. Abdelrakhim
M. T. Abdelrakhim
АТА. Тёрнер
А. Тёрнер
Oral mucosal diseases pose a significant diagnostic challenge due to the similarity of clinical presentations across different pathologies. The integration of Clinical Decision Support Systems (CDSS) represents a promising approach in dentistry to improve diagnostic accuracy.Objective. This study aimed to evaluate the effectiveness of diagnosing oral mucosal diseases with and without the use of a CDSS.Materials and Methods. The study utilized:UMKB (United Medical Knowledge Base) – a unified medical knowledge base, CDSS (Clinical Decision Support System) and an electronic physician assistant,patients and expert dentists. A comparative prospective study was conducted involving 102 patients with oral mucosal diseases. Diagnostic accuracy was assessed with and without CDSS assistance. Patient satisfaction with the diagnostic process was evaluated via digital questionnaires (Google Forms).Results. The use of CDSS by dentists: increased the frequency of preliminary diagnoses (92% with CDSS vs. 78.8% without),iImproved diagnostic correctness (86.5% with CDSS vs. 51.9% without), enhanced final diagnosis completeness (90% with CDSS), increased preventive care recommendations (94% with CDSS vs. 73% without).Conclusions. The CDSS significantly improved: diagnostic accuracy (p = 0.002), data completeness (p < 0.001 for general and oral mucosal examinations), reduced the need for external consultations (p = 0.003), expanded preventive care coverage (p = 0.004). Patient satisfaction was higher with CDSS use (p = 0.003), though this correlation weakened with age (p = 0.047).

21 May 2025 in Medical alphabet
Verified
Journal Article
Closed access
PDF file
EME. G. Margaryan
E. G. Margaryan
GBG. A. Bledzhyants
G. A. Bledzhyants
AKA. G. Kadzhoian
A. G. Kadzhoian
ASA. K. Salpakova
A. K. Salpakova
YKYu. S. Kurenkova
Yu. S. Kurenkova
ТХТань Хуэйпин
Тань Хуэйпин
As part of this research, an intelligent clinical decision support system was developed to enhance the diagnostic efficiency of oral mucosal diseases. Following manual modeling of graph-based representations of oral mucosal diseases and development of disease prediction and diagnostic modules using algorithmic methods, the intelligent clinical decision support system underwent testing. For clinical validation, the CDSS was integrated into healthcare information systems of medical institutions and made accessible via smartphone and computer screens. The study involved evaluation of clinical, laboratory, and instrumental patient data.Objective. Clinical validation of a Clinical Decision Support System integrated with a Medical Information System in a therapeutic dentistry clinic.Materials and methods. Retrospective analysis of medical records of patients with oral mucosal diseases, prospective study of patients with oral mucosal conditions, Clinical Decision Support System.Results. Clinical validation of the Clinical Decision Support System was successfully conducted in a therapeutic dentistry clinic.Conclusions: The clinical validation demonstrated the CDSS’s capability to: extract symptoms with 91.8% accuracy, establish preliminary diagnosis with 84.7% accuracy, determine final diagnosis based on analysis of additional diagnostic methods with 94.6% accuracy.

2 May 2026 in Medical alphabet
Verified
Journal Article
Open access
PDF file
EME. G. Margaryan
E. G. Margaryan
GBG. A. Bledzhyants
G. A. Bledzhyants
YKYu. S. Kurenkova
Yu. S. Kurenkova
МАМ. Т. Абдельрахим
М. Т. Абдельрахим
KDK. D. Devletova
K. D. Devletova
AHArooj Ul Hassan
Arooj Ul Hassan
Oral mucosa pathologies (OMP) represent one of the most challenging groups of diseases to diagnose, characterized by polymorphic manifestations. The development and implementation of a digital machine vision algorithm for diagnosing oral mucosa diseases is a relevant direction for improving the quality and efficiency of diagnostics in modern dentistry.    Aim:  to conduct a prospective collection and structuring of images with annotation of oral mucosa pathological lesions, integrate the dataset into a digital machine vision model, and train a clinical decision support system.    Material and methods: the study used: the United Medical Knowledge Base (UMKB), a Clinical Decision Support System (CDSS), patients with and without oral mucosa diseases, photography equipment, prospective images of pathological conditions and normal states, annotation of pathological lesions.    Results: the conducted work demonstrated the system’s effectiveness in identifying pathological lesions from oral mucosa images at 84 %, and the accuracy of nosology identification based on the list of pathological signs ranged from 90 to 95 %. This confirms the potential to improve the diagnostic efficiency of oral mucosa diseases using an intelligent CDSS in clinical practice.   Conclusions:  a prospective collection and structuring of images was carried out, with annotation of files across 15 categories of oral mucosa lesions into a digital machine vision model. This was followed by the additional training of a CDSS, achieving an efficiency of 84 % and a testing accuracy for determining nosology of 90–95 %.