Seungwan Jang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Seungwan Jang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Se Dong Min
Department of Software Convergence, Soonchunhyang University, Asan 31538, Republic of Korea
2 shared publications - Seung Mo Yoo
Occupational and Environmental Medicine, Yesan Myongji Hospital, Yesan 32423, Republic of Korea
2 shared publications - A-Ram Jo
Department of Business Administration, Kyung Hee University, Seoul 02453, Republic of Korea
1 shared publication - Changwon Wang
Department of Integrated Healthcare Science, Soonchunhyang University, Asan 31538, Republic of Korea
1 shared publication - Hoonyoung Lee
Department of Business Administration, Kyung Hee University, Seoul 02453, Republic of Korea
1 shared publication - Hyunyoung Lee
Department of Software Convergence, Soonchunhyang University, Asan 31538, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Explainable Machine Learning Applied to Bioelectrical Impedance for Low Back Pain: Classification and Pain-Score Prediction
(1) Background: Low back pain (LBP) is the most prevalent cause of disability worldwide, yet current assessment relies mainly on subjective questionnaires, underscoring the need for objective and interpretable biomarkers. Bioelectrical impedance parameter (BIP), quantified by resistance (R), impedance magnitude (Z), and phase angle (PA), reflects tissue hydration and cellular integrity and may provide physiological correlates of pain; (2) Methods: This cross-sectional study used lumbar BIP and demographic characteristics from 83 participants (38 with lumbar BIP and 45 normal controls). We applied Extreme Gradient Boosting (XGBoost), a regularized tree-based machine learning (ML) algorithm, with stratified five-fold cross-validation. Model interpretability was ensured using SHapley Additive exPlanations (SHAP), which provide global importance rankings and local feature attributions. Outcomes included classification of LBP versus healthy status and regression-based prediction of pain scales: the Visual Analog Scale (VAS), Oswestry Disability Index (ODI), and Roland–Morris Disability Questionnaire (RMDQ); (3) Results: The classifier achieved high discrimination (ROC–AUC = 0.996 ± 0.009, sensitivity = 0.950 ± 0.068, specificity = 0.977 ± 0.049). Pain prediction showed best performance for VAS (R2 = 0.70 ± 0.14; mean absolute error = 1.23 ± 0.27), with weaker performance for ODI and RMDQ; (4) Conclusions: These findings suggest that explainable ML models applied to BIP could discriminate between LBP and healthy groups and could estimate pain intensity, providing an objective complement to subjective assessments.
Open AccessExplainable Machine Learning Applied to Bioelectrical Impedance for Low Back Pain: Classification and Pain-Score Prediction
(1) Background: Low back pain (LBP) is the most prevalent cause of disability worldwide, yet current assessment relies mainly on subjective questionnaires, underscoring the need for objective and interpretable biomarkers. Bioelectrical impedance parameter (BIP), quantified by resistance (R), impedance magnitude (Z), and phase angle (PA), reflects tissue hydration and cellular integrity and may provide physiological correlates of pain; (2) Methods: This cross-sectional study used lumbar BIP and demographic characteristics from 83 participants (38 with lumbar BIP and 45 normal controls). We applied Extreme Gradient Boosting (XGBoost), a regularized tree-based machine learning (ML) algorithm, with stratified five-fold cross-validation. Model interpretability was ensured using SHapley Additive exPlanations (SHAP), which provide global importance rankings and local feature attributions. Outcomes included classification of LBP versus healthy status and regression-based prediction of pain scales: the Visual Analog Scale (VAS), Oswestry Disability Index (ODI), and Roland–Morris Disability Questionnaire (RMDQ); (3) Results: The classifier achieved high discrimination (ROC–AUC = 0.996 ± 0.009, sensitivity = 0.950 ± 0.068, specificity = 0.977 ± 0.049). Pain prediction showed best performance for VAS (R2 = 0.70 ± 0.14; mean absolute error = 1.23 ± 0.27), with weaker performance for ODI and RMDQ; (4) Conclusions: These findings suggest that explainable ML models applied to BIP could discriminate between LBP and healthy groups and could estimate pain intensity, providing an objective complement to subjective assessments.
- Open Access
- 31 October 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (21) , 2447
Assessing Pain Levels Using Bioelectrical Impedance in Low Back Pain Patients: Clinical Performance Evaluation
Background/Objectives: Musculoskeletal pain is one of the leading causes of years lived with disability worldwide and has a negative impact on daily life and quality of life. Methods: The purpose of this study was to analyze the electrical characteristics of back pain by measuring and calculating bioelectrical impedance variables (R, Z, PA) in 85 subjects (45 in the Healthy group and 40 in the LBP group). Additionally, impedance measurements were conducted on 20 subjects (10 in the Young group and 10 in the Older group) to assess the impact of aging. Results: Bioelectrical impedance parameter values were higher in cases of back pain, and correlation analysis showed that there was a statistically significant difference between the Healthy and LBP groups (p < 0.05). A positive correlation was found between impedance parameters and pain related indices (ODI, RMDQ, VAS) (mean R, Z, PA: 0.68, 0.54, 0.75), with BMI positively correlating only with PA (0.493). Diagnostic accuracy for detecting back pain exceeded 95% (R, Z, PA: 0.984, 0.984, 0.963). Conclusions: Results indicated that aging did not significantly affect impedance values. The bioelectrical impedance measurement device used in this study, with its simultaneous diagnostic and therapeutic capabilities, proved useful for real-time pain diagnosis and treatment monitoring, highlighting its potential clinical utility.
- 31 October 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (21) , 2447
Open AccessAssessing Pain Levels Using Bioelectrical Impedance in Low Back Pain Patients: Clinical Performance Evaluation
Background/Objectives: Musculoskeletal pain is one of the leading causes of years lived with disability worldwide and has a negative impact on daily life and quality of life. Methods: The purpose of this study was to analyze the electrical characteristics of back pain by measuring and calculating bioelectrical impedance variables (R, Z, PA) in 85 subjects (45 in the Healthy group and 40 in the LBP group). Additionally, impedance measurements were conducted on 20 subjects (10 in the Young group and 10 in the Older group) to assess the impact of aging. Results: Bioelectrical impedance parameter values were higher in cases of back pain, and correlation analysis showed that there was a statistically significant difference between the Healthy and LBP groups (p < 0.05). A positive correlation was found between impedance parameters and pain related indices (ODI, RMDQ, VAS) (mean R, Z, PA: 0.68, 0.54, 0.75), with BMI positively correlating only with PA (0.493). Diagnostic accuracy for detecting back pain exceeded 95% (R, Z, PA: 0.984, 0.984, 0.963). Conclusions: Results indicated that aging did not significantly affect impedance values. The bioelectrical impedance measurement device used in this study, with its simultaneous diagnostic and therapeutic capabilities, proved useful for real-time pain diagnosis and treatment monitoring, highlighting its potential clinical utility.