Artificial intelligence for dysphagia screening: A machine learning approach
Künstliche Intelligenz für das Dysphagie-Screening: ein Machine-Learning-Ansatz
PLOS Digital Health · 29.09.2026 · 5 (9) · e0001755
DOI: 10.1371/journal.pdig.0001755 ↗Auf einen Blick
Eine explorative diagnostische Querschnittsstudie prüfte Machine-Learning-Modelle zum Screening auf oropharyngeale Dysphagie. Mehrere Modelle erreichten eine ausreichende diagnostische Genauigkeit.
Fragestellung
Kann ein Machine-Learning-Modell das Risiko für bestätigte Dysphagie anhand der diagnostischen Genauigkeit vorhersagen?
Methode
Explorative diagnostische Querschnittsstudie bei Erwachsenen und älteren Erwachsenen; 8 Algorithmen wurden getestet und mit Videofluoroskopie bestätigt.
Ergebnisse
465 Teilnehmende, davon 153 mit Dysphagie. Beste Modelle: Naive Bayes, Logistic Regression, Support Vector Machine und Convolutional Neural Network mit Accuracy 0,76–0,79 und Sensitivität 0,74–0,84.
Einschränkungen
Externes Validieren der vorgeschlagenen Screeningsmodelle ist erforderlich.
Schlussfolgerung der Autor:innen
Der Einsatz künstlicher Intelligenz auf Basis verschiedener Machine-Learning-Ansätze ist für das Dysphagie-Screening vielversprechend und zeigte eine ausreichende diagnostische Genauigkeit.
Kernaussagen
- 465 Teilnehmende, 153 mit Dysphagie
- Beste Modelle: Accuracy 0,76–0,79
- 15-Item-Screening zu persönlichen, Gesundheits- und Mundgesundheitsmerkmalen
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 29.09.2026. Verfasst von Rafaela Soares Rech und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in Dentistry, Faculty of Dentistry, Federal University of Rio Grande do Sul, Porto Alegre, Rio Grande do Sul, Brazil. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul, Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Early and reliable screening for oropharyngeal dysphagia symptoms in at-risk populations is a crucial first stage in effective management. This study aims to propose a machine learning model that can predict whether individuals are at risk of having confirmed dysphagia based on diagnostic accuracy. This was an exploratory cross-sectional diagnostic accuracy study. Adults and older adults were screened and assessed, and a videofluoroscopy swallowing study was performed to confirm dysphagia in participants with complaints about swallowing and signs or symptoms identified in the clinical assessment by a speech therapist. Eight algorithms were tested based on a theoretical model to evaluate their diagnostic accuracy: Naive Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Multilayer Perceptron, and Convolutional Neural Networks. The Pandas library in Python was used for data visualization and manipulation. In total, 465 participants were included, of whom 153 had dysphagia. A screening with 15 items related to personal, health, and oral health characteristics is proposed. The final four best-performing models were Naive Bayes (accuracy 0.76, sensitivity 0.84), Logistic Regression (accuracy 0.79, sensitivity 0.82), Support Vector Machine (accuracy 0.78, sensitivity 0.79), and Convolutional Neural Network (accuracy 0.78, sensitivity 0.74). The use of artificial intelligence based on different machine-learning approaches is promising for dysphagia screening, demonstrating adequate diagnostic accuracy. Future studies should be conducted to externally validate the proposed screening models.
Autor:innen und Institutionen
- Graduate Program in Dentistry, Faculty of Dentistry, Federal University of Rio Grande do Sul, Porto Alegre, Rio Grande do Sul, Brazil.
- Graduate Program in Information Technology and Healthcare Management, Federal University of Health Sciences of Porto Alegre, Porto Alegre, Rio Grande do Sul, Brazil.
- Department of Speech-Language Pathology, Federal University of Health Sciences of Porto Alegre, Porto Alegre, Rio Grande do Sul, Brazil.
- Department of Exact and Applied Social Sciences, Federal University of Health Sciences of Porto Alegre, Porto Alegre, Rio Grande do Sul, Brazil.
- Department of Preventive and Social Dentistry, Faculty of Dentistry, Federal University of Rio Grande do Sul, Porto Alegre, Rio Grande do Sul, Brazil.
- Department of Epidemiology and Health Promotion, College of Dentistry, New York University, New York, New York, United States of America.
ORCID-Profile: Rafaela Soares Rech, Dieine Estela Bernieri Schiavon, Danielli Pires Vieira, Fernando Neves Hugo
Förderung
- Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
Rech, R. S., Lopes Becker, C. D., Bernieri Schiavon, D. E., Vieira, D. P., Hilgert, J. B., & Hugo, F. N. (2026). Artificial intelligence for dysphagia screening: A machine learning approach. PLOS Digital Health, 5(9), e0001755. https://doi.org/10.1371/journal.pdig.0001755
Vancouver
Rech RS, Lopes Becker CD, Bernieri Schiavon DE, Vieira DP, Hilgert JB, Hugo FN. Artificial intelligence for dysphagia screening: A machine learning approach. PLOS Digital Health. 2026;5(9):e0001755. doi:10.1371/journal.pdig.0001755
BibTeX
@article{Rech2026,
author = {Rech, Rafaela Soares and Lopes Becker, Carla Diniz and Bernieri Schiavon, Dieine Estela and Vieira, Danielli Pires and Hilgert, Juliana Balbinot and Hugo, Fernando Neves},
title = {Artificial intelligence for dysphagia screening: A machine learning approach},
journal = {PLOS Digital Health},
year = {2026},
volume = {5},
number = {9},
pages = {e0001755},
doi = {10.1371/journal.pdig.0001755}
}
EUVIMED