{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T05:30:49Z","timestamp":1767072649202,"version":"3.48.0"},"reference-count":28,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T00:00:00Z","timestamp":1766620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Background\/Objectives: Transforaminal epidural steroid injection (TFESI) is widely used to treat lumbosacral radicular pain caused by a herniated lumbar disc (HLD). However, therapeutic response varies substantially, and reliable outcome prediction remains challenging because of the multifactorial interplay of clinical and morphological factors. Machine learning (ML) approaches may address this limitation by modeling nonlinear interactions among patient-specific variables. Methods: This retrospective cohort study analyzed 242 patients with HLD-related radiculopathy who underwent single-level lumbar TFESI. Eight variables\u2014age, sex, injection side, injection level, pain duration, pretreatment numeric rating scale (NRS) score, HLD location, and HLD subtype\u2014were used as input features. Therapeutic outcome was defined as a \u226550% reduction in NRS score at 1 month after TFESI. Three predictive models, namely deep neural network (DNN), random forest (RF), and XGBoost, were developed and evaluated using a validation cohort of 49 patients. Results: The DNN model demonstrated the best validation performance, achieving an area under the curve (AUC) of 0.821 (95% confidence interval [CI], 0.690\u20130.929). The performance of the RF (AUC, 0.711; 95% CI, 0.535\u20130.865) and XGBoost (AUC, 0.674; 95% CI, 0.498\u20130.831) models was inferior to that of the DNN. In addition, the DNN produced fewer false-positive predictions and showed more robust discrimination between favorable and poor outcomes than the other ML models. Conclusions: A deep learning\u2013based predictive model demonstrated superior performance in predicting therapeutic outcomes after lumbar TFESI in patients with HLD-related radiculopathy. Integration of routine clinical and magnetic resonance imaging (MRI)-derived features into ML algorithms may enhance individualized prognostication and assist clinicians in optimizing patient selection for interventional procedures. To the best of our knowledge, this is the first study to develop an ML-based model integrating routine clinical variables with MRI findings for the prediction of TFESI outcomes in HLD-related radiculopathy. Nevertheless, the study is limited by its single-center retrospective design, lack of external validation, and reliance on MRI assessments performed by a single rater. Future multicenter studies are warranted to improve generalizability and confirm clinical utility.<\/jats:p>","DOI":"10.3390\/bioengineering13010018","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T23:52:27Z","timestamp":1766706747000},"page":"18","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Prediction of Therapeutic Outcome After Transforaminal Epidural Steroid Injection for Radiculopathy from Herniated Lumbar Disc"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2333-4612","authenticated-orcid":false,"given":"Jeoung Kun","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Business Administration, School of Business, Yeungnam University, Gyeongsan-si 38541, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7629-7213","authenticated-orcid":false,"given":"Min Cheol","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine & Rehabilitation, College of Medicine, Yeungnam University, Daegu 42415, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"113","DOI":"10.36076\/ppj.2023.26.113","article-title":"Effectiveness of transforaminal, interlaminar, and caudal epidural injections in lumbosacral disc herniation: A systematic review and network meta-analysis","volume":"26","author":"Kwak","year":"2023","journal-title":"Pain Physician"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.2147\/JPR.S259212","article-title":"The successful treatment of herniated lumbar discs that are refractory to repeated epidural steroid injection by using a navigable percutaneous disc decompression device: A case series","volume":"13","author":"Lee","year":"2020","journal-title":"J. Pain Res."},{"key":"ref_3","unstructured":"Dydyk, A.M., Khan, M.Z., and Singh, P. (2025, December 23). Radicular Back Pain, StatPearls, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK546593\/."},{"key":"ref_4","first-page":"1837","article-title":"Quality of life and functional status of patients with lumbar radiculopathy","volume":"53","author":"Safiye","year":"2024","journal-title":"Iran. J. Public Health"},{"key":"ref_5","first-page":"e48701","article-title":"Traditional Safe Triangle Approach Versus Kambin\u2019s Triangle Approach: Does Approach Really Matter in Transforaminal Epidural Steroid Injection (TFESI) for Lumbar Disc Herniation?","volume":"15","author":"Agarawal","year":"2023","journal-title":"Cureus"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"296","DOI":"10.21037\/jss-24-140","article-title":"Comparative effectiveness of transforaminal epidural steroid injection: Subpedicular versus Kambin\u2019s triangle technique: A single-centre experience","volume":"11","author":"Liawrungrueang","year":"2025","journal-title":"J. Spine Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"80","DOI":"10.56718\/ijp.24-022","article-title":"The Understanding and Appropriate Use of Corticosteroid in Epidural Injection: A Narrative Review","volume":"15","author":"Lee","year":"2024","journal-title":"Int. J. Pain"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.jcot.2020.06.004","article-title":"Role of transforaminal epidural injections or selective nerve root blocks in the management of lumbar radicular syndrome\u2014A narrative, evidence-based review","volume":"11","author":"Viswanathan","year":"2020","journal-title":"J. Clin. Orthop. Trauma"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1097\/PHM.0000000000000730","article-title":"The 1-year results of lumbar transforaminal epidural steroid injection in patients with chronic unilateral radicular pain: The relation to MRI findings and clinical features","volume":"96","author":"Ekedahl","year":"2017","journal-title":"Am. J. Phys. Med. Rehabil."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Park, D.Y., Kang, S., and Park, J.H. (2019). Factors predicting favorable short-term response to transforaminal epidural steroid injections for lumbosacral radiculopathy. Medicina, 55.","DOI":"10.3390\/medicina55050162"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"327","DOI":"10.3233\/BMR-230051","article-title":"Predictors of successful treatment after transforaminal epidural steroid injections in patients with lumbar disc herniation","volume":"37","author":"Sariyildiz","year":"2024","journal-title":"J. Back Musculoskelet. Rehabil."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"347","DOI":"10.36076\/ppj.2023.26.347","article-title":"Predictors of a favorable response to transforaminal epidural steroid injections for lumbar radiculopathy in the elderly","volume":"26","author":"Wang","year":"2023","journal-title":"Pain Physician"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"58","DOI":"10.3934\/publichealth.2024004","article-title":"Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities","volume":"11","author":"Rahman","year":"2024","journal-title":"AIMS Public Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1186\/s40001-025-02680-7","article-title":"Unveiling the potential of artificial intelligence in revolutionizing disease diagnosis and prediction: A comprehensive review of machine learning and deep learning approaches","volume":"30","author":"Sadr","year":"2025","journal-title":"Eur. J. Med. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1038\/s10038-024-01231-y","article-title":"Advances in AI and machine learning for predictive medicine","volume":"69","author":"Sharma","year":"2024","journal-title":"J. Hum. Genet."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"8490","DOI":"10.1038\/s41598-024-59288-w","article-title":"Convolutional neural network algorithm trained on lumbar spine radiographs to predict outcomes of transforaminal epidural steroid injection for lumbosacral radicular pain from spinal stenosis","volume":"14","author":"Kim","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s40122-023-00573-3","article-title":"Deep learning algorithm trained on oblique cervical radiographs to predict outcomes of transforaminal epidural steroid injection for pain from cervical foraminal stenosis","volume":"13","author":"Wang","year":"2024","journal-title":"Pain Ther."},{"key":"ref_18","first-page":"587","article-title":"Deep learning algorithm trained on lumbar magnetic resonance imaging to predict outcomes of transforaminal epidural steroid injection for chronic lumbosacral radicular pain","volume":"25","author":"Kim","year":"2022","journal-title":"Pain Physician"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1111\/papr.13029","article-title":"Long-term outcomes of transforaminal epidural steroid injection in patients with lumbosacral radicular pain according to the location, type, and size of herniated lumbar disc","volume":"21","author":"Kwak","year":"2021","journal-title":"Pain Pract."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"E93","DOI":"10.1097\/00007632-200103010-00006","article-title":"Nomenclature and classification of lumbar disc pathology. Recommendations of the Combined task Forces of the North American Spine Society, American Society of Spine Radiology, and American Society of Neuroradiology","volume":"26","author":"Fardon","year":"2001","journal-title":"Spine"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1111\/j.1526-4637.2010.00908.x","article-title":"The efficacy of transforaminal injection of steroids for the treatment of lumbar radicular pain","volume":"11","author":"Ghahreman","year":"2010","journal-title":"Pain Med."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Greenberg, M., and Frid, V. (2025). Physics-guided random forest classification of marine sediments using frequency-dependent acoustic reflection spectra. Appl. Sci., 15.","DOI":"10.3390\/app152412930"},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","article-title":"Verification of forecasts expressed in terms of probability","volume":"78","author":"Brier","year":"1950","journal-title":"Mon. Weather Rev."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: The convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100705","DOI":"10.1016\/j.modpat.2025.100705","article-title":"Future of Artificial Intelligence-Machine Learning Trends in Pathology and Medicine","volume":"38","author":"Hanna","year":"2025","journal-title":"Mod. Pathol. Off. J. United States Can. Acad. Pathol. Inc."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Acici, K. (2025). Comparative Analysis of Machine and Deep Learning Algorithms for Bragg Peak Estimation in Polymeric Materials for Tissue-Sparing Radiotherapy. Polymers, 17.","DOI":"10.3390\/polym17152068"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/1\/18\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T05:26:21Z","timestamp":1767072381000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/1\/18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,25]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["bioengineering13010018"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13010018","relation":{},"ISSN":["2306-5354"],"issn-type":[{"type":"electronic","value":"2306-5354"}],"subject":[],"published":{"date-parts":[[2025,12,25]]}}}