JKJung-Min Kim

Jung-Min Kim

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jung-Min Kim has a total of 10 co-authors. Here are the top co-authors by number of shared publications:

  • Ju Seok Ryu

    Department of Rehabilitation Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea

    5 shared publications
  • Sun-Young Choi

    Department of Rehabilitation Medicine, Seoul National University Bundang Hospital, Seongnam, South Korea

    4 shared publications
  • Jaewon Beom

    Department of Rehabilitation Medicine, Seoul National University Bundang Hospital, Seongnam-si, South Korea

    2 shared publications
  • Min-Seop Kim

    Department of Multimedia Engineering, Dongguk University, Seoul, South Korea

    2 shared publications
  • Sung-Han Rhim

    Department of Mechanical Engineering, Dankook University, Yongin, South Korea

    2 shared publications
  • Eun-Seo Choi

    Department of Rehabilitation Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea

    1 shared publication

Latest Publications

  • Open Access

    Evaluating the Association Between Risk Factors of Obstructive Sleep Apnea with Oral Dysfunction and Lifestyle Behavior in Korean Adults Using Data from the Eighth Cycle of the National Health and Nutrition Examination Survey: A Cross-Sectional Study

    by Won-Jae Jo, Jung-Min Kim, Eun-Seo Choi, Seung-U Lee, Ju Seok Ryu

    Background/Objectives: Research on oral dysfunctions as contributing factors to obstructive sleep apnea (OSA) is needed to prevent and treat OSA. This study aimed to explore the association of OSA with oral dysfunction and examine its impact on nutrient intake, physical activity, and handgrip strength. Methods: This cross-sectional study analyzed data from the Eighth cycle Korea National Health and Nutrition Examination Survey (KNHANES, 2019–2021). The OSA group included diagnosed individuals and those over 40 years with symptoms such as snoring, fatigue, or witnessed breathing pauses during sleep. The non-OSA group included individuals not meeting these criteria. Using 1:1 propensity score matching to control for confounders (sex, age, lifestyle factors), 7636 participants were included. Oral dysfunction was assessed based on chewing problems, complaints of chewing discomfort, and speech difficulties. Nutrient intake, physical activity, and handgrip strength were analyzed using the Rao–Scott χ2 test, complex sample t-test, and complex sample logistic regression. Results: The OSA group demonstrated significantly more oral dysfunction elements than the non-OSA group (p < 0.001). Higher energy intake was observed in the OSA group, with no significant differences in macronutrient intake. Physical activity levels were similar between groups; however, OSA participants without oral problems had higher handgrip strength (p < 0.05). Regression analysis showed increased OSA risk correlated with greater oral dysfunction and lower protein intake. Conclusions: This study revealed a strong association between oral dysfunction and OSA risk. Focusing on the assessment and early intervention of oral dysfunctions that influence OSA risk factors may aid in the early detection and prevention of OSA.


  • Open Access

    Prediction of dysphagia aspiration through machine learning-based analysis of patients’ postprandial voices

    by Jung-Min Kim, Min-Seop Kim, Sun-Young Choi, Ju Seok Ryu

    Background: Conventional diagnostic methods for dysphagia have limitations such as long wait times, radiation risks, and restricted evaluation. Therefore, voice-based diagnostic and monitoring technologies are required to overcome these limitations. Based on our hypothesis regarding the impact of weakened muscle strength and the presence of aspiration on vocal characteristics, this single-center, prospective study aimed to develop a machine-learning algorithm for predicting dysphagia status (normal, and aspiration) by analyzing postprandial voice limiting intake to 3 cc. Methods: Conducted from September 2021 to February 2023 at Seoul National University Bundang Hospital, this single center, prospective cohort study included 198 participants aged 40 or older, with 128 without suspected dysphagia and 70 with dysphagia-aspiration. Voice data from participants were collected and used to develop dysphagia prediction models using the Multi-Layer Perceptron (MLP) with MobileNet V3. Male-only, female-only, and combined models were constructed using 10-fold cross-validation. Through the inference process, we established a model capable of probabilistically categorizing a new patient's voice as either normal or indicating the possibility of aspiration. Results: The pre-trained models (mn40_as and mn30_as) exhibited superior performance compared to the non-pre-trained models (mn4.0 and mn3.0). Overall, the best-performing model, mn30_as, which is a pre-trained model, demonstrated an average AUC across 10 folds as follows: combined model 0.8361 (95% CI 0.7667–0.9056; max 0.9541), male model 0.8010 (95% CI 0.6589–0.9432; max 1.000), and female model 0.7572 (95% CI 0.6578–0.8567; max 0.9779). However, for the female model, a slightly higher result was observed with the mn4.0, which scored 0.7679 (95% CI 0.6426–0.8931; max 0.9722). Additionally, the other models (pre-trained; mn40_as, non-pre-trained; mn4.0 and mn3.0) also achieved performance above 0.7 in most cases, and the highest fold-level performance for most models was approximately around 0.9. The ‘mn’ in model names refers to MobileNet and the following number indicates the ‘width_mult’ parameter. Conclusions: In this study, we used mel-spectrogram analysis and a MobileNetV3 model for predicting dysphagia aspiration. Our research highlights voice analysis potential in dysphagia screening, diagnosis, and monitoring, aiming for non-invasive safer, and more effective interventions. Trial registration: This study was approved by the IRB (No. B-2109-707-303) and registered on clinicaltrials.gov (ID: NCT05149976).


  • Open Access

    Application of 3D scanner to measure physical size and improvement of hip brace manufacturing technology in severe cerebral palsy patients

    by Jung-Min Kim, Jiwoon Lim, Sun-Young Choi, Sung-Han Rhim, Jaewon Beom, Ju Seok Ryu

    This prospective pilot study aimed to develop a personalized hip brace for treating hip subluxation in children with cerebral palsy. Nineteen children, aged 1–15, with severe cerebral palsy participated in the study. Customized hip braces were created based on 3D scanner measurements and worn for 7 days. The primary outcome, Hip Migration Index (MI), and secondary outcomes, including range of motion (ROM) in the hip and knee joints, pain intensity, satisfaction, discomfort scores, CPCHILD, and wearability test, were assessed. The MI and ROM were assessed at screening and at Visit 1 (when the new hip brace was first worn), while other indicators were evaluated at screening, Visit 1, and Visit 2 (7 days after wearing the new hip brace). The study demonstrated significant improvements in the MI for the right hip, left hip, and both sides. However, there were no statistically significant differences in hip and knee joint ROM. Other indicators showed significant changes between screening, Visit 1, and Visit 2. The study suggests that customized hip braces effectively achieved immediate correction, positively impacting the quality of life and satisfaction in children with cerebral palsy. Furthermore, the hip braces have the potential to enhance compliance and prevent hip subluxation.Clinical Trial Registration number: NCT05388422


  • Open Access

    Prediction of dysphagia aspiration through machine learning-based analysis of patients’ postprandial voices

    by Jung-Min Kim, Min-Seop Kim, Sun-Young Choi, Ju Seok Ryu

    Background: Conventional diagnostic methods for dysphagia have limitations such as long wait times, radiation risks, and restricted evaluation. Therefore, voice-based diagnostic and monitoring technologies are required to overcome these limitations. Based on our hypothesis regarding the impact of weakened muscle strength and the presence of aspiration on vocal characteristics, this single-center, prospective study aimed to develop a machine-learning algorithm for predicting dysphagia status (normal, and aspiration) by analyzing postprandial voice limiting intake to 3cc. Methods: This study was a single-center, prospective cohort study, conducted from September 2021 to February 2023, at the Seoul National University Bundang Hospital. A total of 204 participants were included, aged 40 or older, comprising 133 without suspected dysphagia and 71 with dysphagia-aspiration.Voice data from participants were collected and used to develop dysphagia prediction models using the Audio Spectrogram Transformer process with MobileNet V3. Male-only, female-only, and combined models were constructed using 10-fold cross-validation. Through the inference process, we established a model capable of probabilistically categorizing a new patient's voice as either normal or indicating the possibility of aspiration. Results: The pre-trained models (mn40_as and mn30_as) exhibited superior performance compared to the non-pre-trained models (mn4.0 and mn3.0). The best-performing model, mn30_as, which is a pre-trained model, demonstrated an average AUC across 10 folds as follows: combined model 0.7879 (95% CI 0.7355-0.8403; max 0.9531), male model 0.7787 (95% CI 0.6768-0.8806; max 1.000), and female model 0.7586 (95% CI 0.6769-0.8402; max 0.9132). Additionally, the other models (pre-trained; mn40_as, non-pre-trained; mn4.0 and mn3.0) also achieved performance above 0.7 in most cases, and the highest fold-level performance for most models was approximately around 0.9. Conclusions: This study suggests the potential of using simple voice analysis as a supplementary tool for screening, diagnosing, and monitoring dysphagia aspiration. By directly analyzing the voice itself, this method enables simpler and more remarkable analysis in contrast to conventional clinical evaluations. The postprandial voice-based prediction model holds implications for improving patient quality of life and advancing the development of non-invasive, safer, and more effective intervention methods. Trial registration: This study was approved by the IRB (No. B-2109-707-303) and registered on clinicaltrials.gov (ID: NCT05149976).


  • Open Access

    Application of 3D scanner to measure physical size and improvement of hip brace manufacturing technology in severe cerebral palsy patients

    by Jung-Min Kim, Ji-Woon Lim, Sun-Young Choi, Sung-Han Rhim, Jaewon Beom, Ju-Seok Ryu

    This prospective pilot study aimed to develop a personalized hip brace for treating hip subluxation in children with cerebral palsy. Nineteen children, aged 1 to 15, with severe cerebral palsy participated in the study. Customized hip braces were created based on 3D scanner measurements and worn for seven days. The primary outcome, Hip Migration Index (MI), and secondary outcomes, including range of motion (ROM) in the hip and knee joints, pain intensity, satisfaction, discomfort scores, CPCHILD, and wearability test, were assessed. The MI and ROM were assessed at screening and at Visit 1 (when the new hip brace was first worn), while other indicators were evaluated at screening, Visit 1, and Visit 2 (seven days after wearing the new hip brace). The study demonstrated significant improvements in the MI for the right hip, left hip, and both sides. However, there were no statistically significant differences in hip and knee joint ROM. Other indicators showed significant changes between screening, Visit 1, and Visit 2. The study suggests that customized hip braces effectively achieved immediate correction, positively impacting the quality of life and satisfaction in children with cerebral palsy. Furthermore, the braces have the potential to enhance compliance and prevent hip subluxation.