Artificial Intelligence for Diagnosis and Treatment of Dysphagia

Introduction

In recent years, technological advances in the use of artificial intelligence (AI) in medicine have demonstrated promising potential in the detection and care of dysphagic patients. Several studies have explored different AI methodologies in the search for diagnostic and therapeutic accuracy for dysphagic patients, while its clinical implementation remains in progress. Improvements in early diagnosis in a scalable manner help public health managers to take more urgent initial measures, always seeking to improve the patient's clinical condition and, mainly, their well-being when it comes to quality of life. Despite promising results in research settings, the transition to widespread clinical use faces important barriers ahead. These include the need for extensive validation in diverse patient populations, integration with existing healthcare systems, and addressing concerns related to data privacy and security. Additionally, there is a need for standardized protocols and guidelines to ensure consistent and reliable use of AI tools in clinical practice. As the field continues to evolve, ongoing collaboration between researchers, clinicians, and technology developers will be crucial to overcoming these challenges and fully realizing the potential of AI in dysphagia management.

In this editorial, we raise the potential use of AI in the diagnosis and treatment of dysphagia. A few selected studies that hold promise for the clinical implementation of AI are discussed, as well as their limitations and further steps. Regarding diagnosis, AI may assist in identifying radiation-free alternatives, remote monitoring, and deep learning methods. Regarding treatment, AI-based treatment is still in its early days with treatment planning.

Publication History

Article published online:
23 January 2025

• References

• 1 Heo S, Uhm KE, Yuk D. et al. Deep learning approach for dysphagia detection by syllable-based speech analysis with daily conversations. Sci Rep 2024; 14 (01) 20270
• 2 Kim JM, Kim MS, Choi SY, Ryu JS. Prediction of dysphagia aspiration through machine learning-based analysis of patients' postprandial voices. J Neuroeng Rehabil 2024; 21 (01) 43
• 3 Jauk S, Kramer D, Veeranki SPK. et al. Evaluation of a Machine Learning-Based Dysphagia Prediction Tool in Clinical Routine: A Prospective Observational Cohort Study. Dysphagia 2023; 38 (04) 1238-1246
• 4 Kim JM, Kim MS, Choi SY, Lee K, Ryu JS. A deep learning approach to dysphagia-aspiration detecting algorithm through pre- and post-swallowing voice changes. Front Bioeng Biotechnol 2024; 12: 1433087
• 5 Khalifa Y, Donohue C, Coyle JL, Sejdic E. Autonomous Swallow Segment Extraction Using Deep Learning in Neck-Sensor Vibratory Signals From Patients With Dysphagia. IEEE J Biomed Health Inform 2023; 27 (02) 956-967
• 6 Weng W, Imaizumi M, Murono S, Zhu X. Expert-level aspiration and penetration detection during flexible endoscopic evaluation of swallowing with artificial intelligence-assisted diagnosis. Sci Rep 2022; 12 (01) 21689
• 7 Jeong CW, Lee CS, Lim DW. et al. The Development of an Artificial Intelligence Video Analysis-Based Web Application to Diagnose Oropharyngeal Dysphagia: A Pilot Study. Brain Sci 2024; 14 (06) 546 [Internet]
• 8 Saab R, Balachandar A, Mahdi H. et al. Machine-learning assisted swallowing assessment: a deep learning-based quality improvement tool to screen for post-stroke dysphagia. Front Neurosci 2023; 17: 1302132
• 9 Gugatschka M, Egger NM, Haspl K. et al. Clinical evaluation of a machine learning-based dysphagia risk prediction tool. Eur Arch Otorhinolaryngol 2024; 281 (08) 4379-4384