Jung-Min Kim ^1,2 Min-Seop Kim ³ Sun-Young Choi ² Kyogu Lee ⁴ Ju Seok Ryu ^2,5*

• ¹ Department of Health Science and Technology, Graduate School of Convergence Science of Technology, Seoul National University, Suwon, Gyeonggi, Republic of Korea
• ² Seoul National University Bundang Hospital, Seongnam-si, Gyeonggi, Republic of Korea
• ³ Department of Multimedia Engineering, Dongguk University, Seoul, Republic of Korea
• ⁴ Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Seoul, Republic of Korea
• ⁵ College of Medicine, Seoul National University, Seoul, Seoul, Republic of Korea

Introduction: This study aimed to identify differences in voice characteristics and changes between patients with dysphagia-aspiration and healthy individuals using a deep learning model, with a focus on under-researched areas of pre- and post-swallowing voice changes in patients with dysphagia. We hypothesized that these variations may be due to weakened muscles and blocked airways in patients with dysphagia. Methods: A prospective cohort study was conducted on 198 participants aged >40 years at the Seoul National University Bundang Hospital from October 2021 to February 2023. Pre- and post-swallowing voice data of the participants were converted to a 64-kbps mp3 format, and all voice data were trimmed to a length of 2 seconds. The data were divided for 10-fold cross-validation and stored in HDF5 format with anonymized IDs and labels for the normal and aspiration groups. During preprocessing, the data were converted to Mel spectrograms, and the EfficientAT model was modified using the final layer of MobileNetV3 to effectively detect voice changes and analyze pre- and post-swallowing voices. This enabled the model to probabilistically categorize new patient voices as normal or aspirated. Results: In a study of the machine-learning model for aspiration detection, area under the ROC curve (AUC) values were analyzed across sexes under different configurations. The average AUC values for males ranged from 0.8117 to 0.8319, with the best performance achieved at a learning rate of 3.00e-5 and a batch size of 16. The average AUC values for females improved from 0.6975 to 0.7331, with the best performance observed at a learning rate of 5.00e-5 and a batch size of 32. As there were fewer female participants, a combined model was developed to maintain the sex balance. In the combined model, the average AUC values ranged from 0.7746 to 0.7997, and optimal performance was achieved at a learning rate of 3.00e-5 and a batch size of 16. Conclusions: This study evaluated a voice analysis-based program to detect pre- and post-swallowing changes in patients with dysphagia, potentially aiding in real-time monitoring. Such a system can provide healthcare professionals with daily insights into the conditions of patients, allowing for personalized interventions.