OEO.V. Eliseev

O.V. Eliseev

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

O.V. Eliseev has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Modern possibilities for the diagnosis of voice disorders using computer acoustic analysis of voice and artificial intelligence

    by D.I. Kurbanova, S.G. Romanenko, O.G. Pavlikhin, E.V. Lesogorova, O.V. Eliseev, E.N. Krasilnikova, E.A. Teplykh, V.A. Zemlyanov, Kh.Z. Khaybulaev

    Objective. To evaluate the effectiveness of different AI models in diagnosing dysphonia based on acoustic voice analysis, and to compare the accuracy and predictive value of algorithms in distinguishing normal condition, functional and organic voice disorders. Material and methods. The study included 1260 patients divided into three groups: those with normal voice function, those with functional and organic pathologies of the vocal folds. All patients underwent acoustic voice analysis using the MDVP program, as well as microlaryngoscopy and videolaryngostroboscopy. Multiple logistic regression, XGBoost, Random Forest, Extra Trees, LightGBM, and neural network algorithms (including the TabFPN architecture) were used to build diagnostic models. The quality of the models was evaluated on a test sample (20% of the total sample) using accuracy, sensitivity, specificity, F1-measure, and ROC-AUC metrics. Statistical data processing was performed using Python. Results. The highest diagnostic accuracy (ROC-AUC >0.935) was demonstrated by models based on boosting algorithms and deep neural networks, especially when using the full set of acoustic parameters (n=34). The XGBoost method and modern neural network architectures provided the best balance between sensitivity and specificity in the classification of three diagnostic categories. Conclusion. Artificial intelligence methods, particularly boosting and neural networks, demonstrate high efficiency in diagnosing dysphonia based on acoustic characteristics of the voice. Their implementation in clinical practice can increase the objectivity of voice disorder diagnostics and accelerate the process of clinical decision-making.

  • A cloud-based system for automatic diagnostics of dysphonia via acoustic parameters using artificial intelligence models

    by D.I. Kurbanova, S.G. Romanenko, O.G. Pavlikhin, E.V. Lesogorova, O.V. Eliseev, E.N. Krasilnikova, V.A. Zemlyanov, E.A. Teplykh, Kh.Z. Khaybulaev

    The diagnosis of voice disorders remains a persistent challenge in otorhinolaryngology, as the analysis of complex data demands specialized clinical expertise. A promising approach involves the implementation of artificial intelligence (AI) and machine learning methods, which can automate the analysis of acoustic voice parameters, objectively differentiating between norm and pathology. The creation of user-friendly, secure and accessible cloud-based platforms utilizing environments like Google Drive and Colaboratory reduces the need for expensive infrastructure. This is a critical prerequisite for the successful integration of AI into clinical practice.

  • Modern possibilities for the diagnosis of voice disorders using computer acoustic analysis of voice and artificial intelligence

    by A.I. Kryukov, S.G. Romanenko, O.G. Pavlikhin, D.I. Kurbanova, E.V. Lesogorova, O.V. Eliseev, Kh.Z. Khaybulaev, E.N. Krasilnikova, T.K. Polyaeva

    Objective. The purpose of the review is to analyze modern approaches to the diagnosis of voice disorders using AI and acoustic analysis, as well as to evaluate their effectiveness and prospects for implementation in clinical practice. Research design. A review of domestic and foreign literature sources on the use of computer acoustic analysis and AI technologies in the diagnosis of diseases of the vocal apparatus is carried out. Material and methods. The material for the analysis was publications in scientific journals, the results of clinical trials, data on the use of specialized software systems (PRAAT, MDVP, LingWaves) and machine learning-based systems (SVM, CNN, RNN and their combinations). Data on diagnostic accuracy, interpretability of results, and applicability in real clinical practice were considered. Results. Acoustic analysis of the voice makes it possible to detect pathological changes in the early stages, before the appearance of pronounced symptoms. The PRAAT and MDVP programs have become the standard in assessing the spectral and temporal characteristics of a voice. The introduction of AI has significantly improved diagnostic accuracy (up to 95–97% in individual studies). Machine learning algorithms and deep neural networks automate diagnostics, allow you to identify hidden patterns and use data obtained even from mobile devices. However, there are still unresolved issues of database standardization, interpretability of models, and ethical and legal aspects of their implementation. Despite the high efficiency of technologies, their use requires the development of uniform standards, ensuring the transparency of algorithms and multidisciplinary interaction of specialists.

  • Features of the laryngeal mucosa microbiota in patients with chronic hyperplastic laryngitis (literature review)

    by D.I. Kurbanova, A.V. Gurov, S.G. Romanenko, O.G. Pavlikhin, E.V. Lesogorova, E.N. Krasilnikova, V.A. Zemlyanov, O.V. Eliseev, E.A. Teplykh, E.A. Safyannikova

    The literature review analyzed the data concerning studies of the microbiome of the laryngeal mucosa in patients with chronic hyperplastic laryngitis. It remains a matter of discussion whether the inflammatory process in the larynx is primary with subsequent dysbiosis and excessive growth of pathogenic microorganisms, or whether changes in the structure of the normal microbial landscape become an inducer of the disease. The article reflects the results of basic research on the role of bacterial, fungal, and viral pathogens detected on the mucous membrane of the larynx in patients with chronic hyperplastic laryngitis, conducted by Russian and foreign scientists using various technological approaches.

  • Laryngeal granulomas (literature review)

    by S.G. Romanenko, D.YU. Veltishchev, S.G. Radenska-Lopovok, O.G. Pavlikhin, D.I. Kurbanova, E.V. Lesogorova, O.V. Eliseev, E.N. Krasilnikova, V.A. Zemlyanov, E.A. Teplykh

    Laryngeal granulomas are a benign disease characterized by a high recurrence rate, ranging from 20% to 93%. This article provides an overview of domestic and foreign literature, provides basic information about laryngeal granulomas, and highlights their etiology, pathogenesis, clinic, and treatment methods. The importance of searching for provoking factors of the development of this disease and new ways of its treatment is substantiated.

  • Infiltrative-ulcerative lesion of the larynx in Behcet’s disease

    by S.G. Romanenko, O.G. Pavlikhin, D.I. Kurbanova, E.V. Lesogorova, O.V. Eliseev, E.N. Krasilnikova, E.A. Safyannikova, A.V. Efremenkova

    The article describes a clinical case of differential diagnostic search for the cause of infiltrative ulcerative laryngitis in a young patient. Infectious, systemic, and neoplastic causes are excluded. Behcet’s disease was diagnosed 11 years after the first clinical signs appeared. In this case, the difficulty of diagnosis is due to the absence of typical signs of the disease.

  • Biofeedback therapy in patients with dysphonia and benign laryngeal pathology after endolaryngeal interventions

    by S.G. Romanenko, O.G. Pavlikhin, D.I. Kurbanova, E.V. Lesogorova, O.V. Eliseev, E.A. Safyannikova, E.N. Krasilnikova

    Objective. To increase the effectiveness of voice restoration in patients with benign organic laryngeal pathology and functional dysphonia after endolaryngeal interventions. Material and methods. 360 patients who underwent surgery for benign organic pathology of the vocal folds were examined. The examination was performed using videolaryngoscopy, videolaryngostroboscopy, computer acoustic analysis of the voice, and a subjective assessment of vocal function by a doctor on the N. Yanagihara scale. Results. In 58 patients in the postoperative period, after the relief of inflammatory phenomena, the voice did not recover, due to the pathological type of phonation: nodular, hypotonic or hypertonic. Voice restoration measures were carried out: phonotherapy for patients of the 1st group, phonotherapy and biofeedback therapy sessions for patients of the 2nd group. According to subjective and objective assessments, biofeedback therapy significantly accelerated voice recovery in patients with hypertonic phonation. Biofeedback therapy had no significant effect on the restoration of vocal function in patients with nodular and hypotonic phonation. Conclusion. In cases where the voice does not fully recover after endolaryngeal interventions, additional therapeutic measures are required: phonotherapy and biofeedback therapy.

  • Etiopathogenesis and therapeutic tactics of hemorrhages in the vocal fold in persons of voice-speech professions

    by A.I. Kryukov, S.G. Romanenko, O.G. Pavlikhin, D.I. Kurbanova, E.V. Lesogorova, E.N. Krasilnikova, O.V. Eliseev

    Objective. To increase the effectiveness of treatment of patients with vocal fold hemorrhage based on the analysis of the disease etiology. Material and methods. In order to improve the treatment efficiency of vocal fold hemorrhage in people with voice and speech professions, 112 patients (35 men and 77 women) with vocal fold hemorrhage were examined and treated. Age from 24 to 58 years. Research methods: questionnaires, microlaryngoscopy, videolaryngostroboscopy, acoustic voice analysis (Kay Pentax system). Results. All patients complained of hoarseness. A change in voice that appeared during vocal exertion using a harsh sound attack was noted by 47 (42%) patients, while screaming — 13 (11%), during coughing on the background of acute respiratory viral infection and exacerbation of chronic destructive lung disease — 27 (24%), after fibrolaryngobronchoscopy — 3 (2%), after esophagogastroduodenoscopy — 1, after external neck injury in everyday life — 2 (1%), during the usual volume and intensity of vocal load — 19 (17%). Microlaryngoscopy revealed hemorrhage in the vocal fold in all patients, with 85 (76%) patients experiencing hemorrhage for the first time, 17 (15%) — repeatedly, for 10 (9%) — for the third time or more. A unilateral process was noted in 81 (72%) patients, a bilateral process in 31 (28%). Comprehensive treatment is prescribed to all patients based on an individual approach. The subjective voice score on the visual analog scale averaged 6.4±1.7 points, 1 month after the start of treatment — 9.4±0.4 points. The recovery time was also determined individually, depending on the patient’s profession and the requirements for voice quality. Conclusions. 1. Vocal fold hemorrhage is caused by a disruption of the vascular wall integrity due to a sharp increase in subglottic pressure. 2. Predisposing factors for the development of vocal fold hemorrhage are dystrophic changes in the mucous membrane of the vocal folds and concomitant pathology that contribute to increased vascular permeability. 3. No correlation was found between the volume of vocal fold hemorrhage, its prevalence, and the time of its reduction and restoration of voice function. 4. The duration of treatment is determined individually and depends on the dynamics of the videolaryngostroboscopic picture and the indicators of acoustic voice analysis and the patient’s requirements for voice quality. 5. In case of recurrent hemorrhages, examination of the patient is indicated to exclude coagulopathy; in the presence of concomitant pathology accompanied by microangiopathy (diabetes mellitus, chronic glomerulonephritis, dyshormonal disorders in women, etc.), consultation with specialists is necessary to assess the activity of the concomitant disease, the degree of its impact on the microcirculatory bed and, according to indications, correction of its therapy.

  • Clinical features of ulcerative laryngitis

    by S.G. Romanenko, E.A. Kirasirova, O.G. Pavlikhin, O.V. Eliseev, D.I. Kurbanova, E.V. Lesogorova, E.N. Krasilnikova

    Ulcerative laryngitis refers to rare diseases, it is also called prolonged ulcerative laryngitis, idiopathic ulcerative laryngitis and acute ulcerative laryngitis. Objective. To increase the effectiveness of treatment of patients with ulcerative laryngitis based on the study of the clinical features of the disease and evaluation of treatment results. Material and methods. The results of the examination (collection of complaints and anamnesis, general otorhinolaryngological examination, indirect microlaryngoscopy, videolaryngostroboscopy, microbiological studies, subjective assessment of vocal function) and treatment of 20 patients with ulcerative laryngitis who applied to the phoniatric unit of the Sverzhevsky Research Clinical Institute of Otorhinolaryngology (Moscow, Russia) are presented. Results. The study group consisted of 16 women and 4 men aged 19 to 73 years (median 47.5 years). In all patients, the disease is associated with a prolonged or subacute cough. The duration of dysphonia ranged from 1 to 10 months (2.6 months on average). A history of smoking was detected in 7 patients, increased vocal load in 5. The clinical picture in all patients was similar: dysphonia and cough. Video laryngoscopy revealed hyperemia and infiltration of the vocal folds with the presence of erosions or ulcers covered with fibrin, located symmetrically in the middle third of the vocal folds along the free edge with a transition to the upper surface. Video pharyngostroboscopy revealed a decrease in the amplitude and irregularity of vibrations in the erosion zone, and the preservation of the mucous wave in the remaining parts of the vocal folds. Microbiological examination revealed fungal flora in 4 patients and bacterial flora in 4 patients. The duration of treatment averaged 9.6 weeks, while the healing of ulcerative defects of the vocal folds occurred 2-4 weeks after the cessation of coughing. Phonopedic classes were needed by 2 patients. In 1 case, surgical treatment was required. Laryngeal contact granuloma was detected in 2 patients with ulcerative laryngitis. Granuloma regression is achieved with the help of conservative therapy. The restoration of voice as a result of the treatment was achieved in all patients. Conclusion. Ulcerative laryngitis is a rare disease associated with vocal injury, characterized by dysphonia, bilateral and symmetrical ulcerative defects in the middle third of the vocal folds, and prolonged healing. It is necessary to conduct a microbiological examination at the first treatment of a patient with this pathology. Treatment should be individual and comprehensive. Surgical treatment is indicated in exceptional cases for the differential diagnosis of laryngeal cancer. Phonopedia may be required. Long-term monitoring of the patient is necessary until full recovery and restoration of voice function.

  • Epidemiological features of laryngeal papillomatosis in adults in Moscow

    by A.I. Kryukov, S.G. Romanenko, A.B. Oteyami, N.H. Amegan, O.G. Pavlikhin, O.V. Eliseev, D.I. Kurbanova, E.V. Lesogorova

    Objective. To evaluate the incidence of laryngeal papillomatosis (LP) and LP recurrence in adults and to determine the risk factors for the development of LP recurrence in adults in Moscow. To solve the tasks set, a survey of patients carried out, including the collection of complaints and anamnesis, a standard examination of the ENT organs, an assessment of the condition of the larynx, and a histological examination. Material and methods. We conducted a retrospective analysis of the case histories of 299 patients with LP observed and treated at the Sverzhevsky Research and Clinical Institute of Otorhinolaryngology in the period 2010-2020. Results. On average, over the entire study period, the prevalence of PG was 17.80%. It was found that out of 299 patients, 69.6% (n=208) had a relapse of LP. Papilloma of the larynx were more often localized in the glottis. 275 (92%) patients had a widespread form of LP. LP recurrences were significantly more common in women and in patients with an existing cicatricle process in the larynx. The relapse rate was higher in non-smokers (73.5% vs 47.8%; p<0.001). Although the recurrence rate was higher in patients with non-voice occupations (70.6% vs. 52.9%), there was no statistically significant association between relapses and the vocal professions (p=0.125). Conclusion. As a result of the study, a number of risk factors for laryngeal papillomatosis recurrent have been identified, and their study should be continued.