{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:58:26Z","timestamp":1783090706219,"version":"3.54.6"},"reference-count":33,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Soonchunhyang University Research Fund and BK21 FOUR","award":["5199990914048"],"award-info":[{"award-number":["5199990914048"]}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Sensors"],"abstract":"<jats:p>(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\u2013Morris Disability Questionnaire (RMDQ); (3) Results: The classifier achieved high discrimination (ROC\u2013AUC = 0.996 \u00b1 0.009, sensitivity = 0.950 \u00b1 0.068, specificity = 0.977 \u00b1 0.049). Pain prediction showed best performance for VAS (R2 = 0.70 \u00b1 0.14; mean absolute error = 1.23 \u00b1 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.<\/jats:p>","DOI":"10.3390\/s25196135","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T15:26:54Z","timestamp":1759505214000},"page":"6135","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable Machine Learning Applied to Bioelectrical Impedance for Low Back Pain: Classification and Pain-Score Prediction"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2721-1011","authenticated-orcid":false,"given":"Seungwan","family":"Jang","sequence":"first","affiliation":[{"name":"Department of Software Convergence, Soonchunhyang University, Asan 31538, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung Mo","family":"Yoo","sequence":"additional","affiliation":[{"name":"Occupational and Environmental Medicine, Yesan Myongji Hospital, Yesan 32423, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9112-2673","authenticated-orcid":false,"given":"Se Dong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Software Convergence, Soonchunhyang University, Asan 31538, Republic of Korea"},{"name":"Department of Medical IT Engineering, Soonchunhyang University, Asan 31538, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changwon","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Software Convergence, Soonchunhyang University, Asan 31538, Republic of Korea"},{"name":"Department of Integrated Healthcare Science, Soonchunhyang University, Asan 31538, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e316","DOI":"10.1016\/S2665-9913(23)00098-X","article-title":"Global, regional, and national burden of low back pain, 1990\u20132020, its attributable risk factors, and projections to 2050: A systematic analysis of the Global Burden of Disease Study 2021","volume":"5","author":"Ferreira","year":"2023","journal-title":"Lancet Rheumatol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"605","DOI":"10.3233\/BMR-200206","article-title":"Are the Roland Morris Disability Questionnaire and Oswestry Disability Index interchangeable in patients after lumbar spinal fusion?","volume":"34","author":"Kersten","year":"2021","journal-title":"J. Back Musculoskelet. Rehabil."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Elabd, O.M., Oakley, P.A., and Elabd, A.M. (2024). Prediction of back disability using clinical, functional, and biomechanical variables in adults with chronic nonspecific low back pain. J. Clin. Med., 13.","DOI":"10.3390\/jcm13133980"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zurek, G., Kasper-J\u0119drzejewska, M., Dobrowolska, I., Mroczek, A., Delaunay, G., Ptaszkowski, K., and Halski, T. (2022). Vibrating Exercise Equipment in Middle-Age and Older Women with Chronic Low Back Pain and Effects on Bioelectrical Activity, Range of Motion and Pain Intensity: A Randomized, Single-Blinded Sham Intervention Study. Biology, 11.","DOI":"10.3390\/biology11020268"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ghita, M., Neckebroek, M., Juchem, J., Copot, D., Muresan, C.I., and Ionescu, C.M. (2020). Bioimpedance sensor and methodology for acute pain monitoring. Sensors, 20.","DOI":"10.3390\/s20236765"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, H., Dai, J., Wang, C., Gao, Z., Liu, Y., Dai, M., Zhao, Z., Yang, L., and Tan, G. (2022). Assessment of low back pain in helicopter pilots using electrical bio-impedance technique: A feasibility study. Front. Neurosci., 16.","DOI":"10.3389\/fnins.2022.883348"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bari, D.S., Aldosky, H.Y.Y., Tronstad, C., Kalv\u00f8y, H., and Martinsen, \u00d8.G. (2018). Electrodermal activity responses for quantitative assessment of felt pain. J. Electr. Bioimpedance, 9.","DOI":"10.2478\/joeb-2018-0010"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Jang, S., Ho, J.G., Jo, A.-R., Yoo, S.M., Lee, H., Lee, H., Kim, Y., and Min, S.D. (2024). Assessing Pain Levels Using Bioelectrical Impedance in Low Back Pain Patients: Clinical Performance Evaluation. Diagnostics, 14.","DOI":"10.3390\/diagnostics14212447"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102530","DOI":"10.1016\/j.nicl.2020.102530","article-title":"Multi-modal biomarkers of low back pain: A machine learning approach","volume":"29","author":"Lamichhane","year":"2021","journal-title":"NeuroImage Clin."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shim, J.-G., Ryu, K.-H., Cho, E.-A., Ahn, J.H., Kim, H.K., Lee, Y.-J., and Lee, S.H. (2021). Machine learning approaches to predict chronic lower back pain in people aged over 50 years. Medicina, 57.","DOI":"10.3390\/medicina57111230"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"10","DOI":"10.29337\/ijdh.34","article-title":"Machine learning applied to low back pain rehabilitation\u2013a systematic review","volume":"1","author":"Amorim","year":"2021","journal-title":"Int. J. Digit. Health"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"104497","DOI":"10.1016\/j.jpain.2024.02.011","article-title":"Machine learning models for low back pain detection and factor identification: Insights from a 6-year nationwide survey","volume":"25","author":"Bhak","year":"2024","journal-title":"J. Pain"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Abdel Hady, D.A., and Abd El-Hafeez, T. (2024). Utilizing machine learning to analyze trunk movement patterns in women with postpartum low back pain. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-68798-6"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s41666-020-00077-1","article-title":"Predicting missing values in medical data via XGBoost regression","volume":"4","author":"Zhang","year":"2020","journal-title":"J. Healthc. Inform. Res."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yi, F., Yang, H., Chen, D., Qin, Y., Han, H., Cui, J., Bai, W., Ma, Y., Zhang, R., and Yu, H. (2023). XGBoost-SHAP-based interpretable diagnostic framework for alzheimer\u2019s disease. BMC Med. Inform. Decis. Mak., 23.","DOI":"10.1186\/s12911-023-02238-9"},{"key":"ref_16","unstructured":"Cheong, L.L., Meharizghi, T., Black, W., Guang, Y., and Meng, W. (2022). Explainability of Traditional and Deep Learning Models on Longitudinal Healthcare Records. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tong, M.W., Ziegeler, K., Kreutzinger, V., and Majumdar, S. (2025). Explainable AI reveals tissue pathology and psychosocial drivers of opioid prescription for non-specific chronic low back pain. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-13619-7"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Gabriel, S., Lau, R., and Gabriel, C. (1996). The dielectric properties of biological tissues: II. Measurements in the frequency range 10 Hz to 20 GHz. Phys. Med. Biol., 41.","DOI":"10.1088\/0031-9155\/41\/11\/002"},{"key":"ref_19","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume":"35","author":"Grinsztajn","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1136\/medethics-2020-107102","article-title":"Machine learning in medicine: Should the pursuit of enhanced interpretability be abandoned?","volume":"48","author":"Yoon","year":"2022","journal-title":"J. Med. Ethics"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1016\/S0140-6736(18)30489-6","article-title":"Prevention and treatment of low back pain: Evidence, challenges, and promising directions","volume":"391","author":"Foster","year":"2018","journal-title":"Lancet"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"112064","DOI":"10.1016\/j.nut.2023.112064","article-title":"Phase angle of bioimpedance as a marker of inflammation in cardiovascular diseases: A systematic review","volume":"112","author":"Ceolin","year":"2023","journal-title":"Nutrition"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yamada, Y., Yoshida, T., Murakami, H., Kawakami, R., Gando, Y., Ohno, H., Tanisawa, K., Konishi, K., Julien, T., and Kondo, E. (2022). Phase angle obtained via bioelectrical impedance analysis and objectively measured physical activity or exercise habits. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-21095-6"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s11154-022-09775-0","article-title":"Phase angle and cellular health: Inflammation and oxidative damage","volume":"24","author":"Orsso","year":"2023","journal-title":"Rev. Endocr. Metab. Disord."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rezazadegan, M., Shirani, M., Samadanian, F., Akbari, M., and Shirani, F. (2024). Association between dietary inflammatory index and phase angle in university employees: A cross-sectional study. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-71855-9"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1021\/acsmeasuresciau.2c00033","article-title":"Bioelectrical impedance spectroscopy for monitoring mammalian cells and tissues under different frequency domains: A review","volume":"2","author":"Abasi","year":"2022","journal-title":"ACS Meas. Sci. Au"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Cooley, J.R., Kjaer, P., Jensen, T.S., Jacques, A., Theroux, J., and Hebert, J.J. (2023). Lumbar multifidus muscle morphology is associated with low back-related pain duration, disability, and leg pain: A cross-sectional study in secondary care. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0285993"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Cooley, J.R., Jensen, T.S., Kjaer, P., Jacques, A., Theroux, J., and Hebert, J.J. (2024). Spinal degeneration and lumbar multifidus muscle quality may independently affect clinical outcomes in patients conservatively managed for low back or leg pain. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-60570-0"},{"key":"ref_31","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2940","DOI":"10.1097\/00007632-200011150-00017","article-title":"The Oswestry Disability Index","volume":"25","author":"Fairbank","year":"2000","journal-title":"Spine (1976)"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1097\/00007632-198303000-00004","article-title":"A study of the natural history of back pain: Part I: Development of a reliable and sensitive measure of disability in low-back pain","volume":"8","author":"Roland","year":"1983","journal-title":"Spine"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6135\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T15:27:55Z","timestamp":1759505275000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":33,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["s25196135"],"URL":"https:\/\/doi.org\/10.3390\/s25196135","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]}}}