Russian Bulletin of Otorhinolaryngology · 18 Nov 2026
Modern possibilities for the diagnosis of voice disorders using computer acoustic analysis of voice and artificial intelligence
D.I. Kurbanovah-index 1, S.G. Romanenko, O.G. Pavlikhin, E.V. Lesogorova, O.V. Eliseev, E.N. Krasilnikova, E.A. Teplykh, V.A. Zemlyanov, Kh.Z. Khaybulaevh-index 0
Citations by database
Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.
- OpenCitations0
- Crossref0
- Europe PMC0
Citations per year
The current year is still counting.
- 2026 so far0
Abstract
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.
What the data shows
- No database records a citation yet, as is usual for a paper this new.
- D.I. Kurbanova has the highest h-index among the authors (1).
Graph
This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.
Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.
Start with
Cited by 0 papers
Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.
References (7)
What it cites, from open citation data, with Crossref's record of each.