{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:13:48Z","timestamp":1784837628070,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Lumbar disc herniation (LDH) recurrence remains a pressing clinical challenge, with limited predictive tools available to support early identification and personalized intervention. Predicting recurrence after lumbar disc herniation (LDH) remains clinically important but algorithmically difficult due to extreme class imbalance and low signal-to-noise ratio. Objective: This study proposes a hybrid machine learning framework that integrates supervised classifiers, unsupervised anomaly detection, and decision threshold tuning to predict LDH recurrence using routine clinical data. Methods: A dataset of 977 patients from a Romanian neurosurgical center was used. We trained a deep neural network, random forest, and an autoencoder (trained only on non-recurrence cases) to model baseline and anomalous patterns. Their outputs were stacked into a meta-classifier and optimized via sensitivity-focused threshold tuning. Evaluation was performed via stratified cross-validation and external holdout testing. Results: Baseline models achieved high accuracy but failed to recall recurrence cases (0% sensitivity). The proposed ensemble reached 100% recall internally with a threshold of 0.05. Key predictors included hospital stay duration, L4\u2013L5 herniation, obesity, and hypertension. However, external holdout performance dropped to 0% recall, revealing poor generalization. Conclusions: The ensemble approach enhances detection of rare recurrence cases under internal validation but exhibits poor external performance, emphasizing the challenge of rare-event modeling in clinical datasets. Future work should prioritize external validation, longitudinal modeling, and interpretability to ensure clinical adoption.<\/jats:p>","DOI":"10.3390\/diagnostics15131628","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T11:15:23Z","timestamp":1750936523000},"page":"1628","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A Hybrid Ensemble Learning Framework for Predicting Lumbar Disc Herniation Recurrence: Integrating Supervised Models, Anomaly Detection, and Threshold Optimization"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3092-2324","authenticated-orcid":false,"given":"M\u0103d\u0103lina","family":"Duceac (Covrig)","sequence":"first","affiliation":[{"name":"Faculty of Medicine and Pharmacy, Doctoral School of Biomedical Sciences, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, 800008 Gala\u021bi, Romania"},{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2791-3400","authenticated-orcid":false,"given":"C\u0103lin Gheorghe","family":"Buzea","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"},{"name":"National Institute of Research and Development for Technical Physics, IFT Ia\u0219i, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2710-7284","authenticated-orcid":false,"given":"Alina","family":"Ple\u0219ea-Condratovici","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucian","family":"Eva","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"},{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-2618","authenticated-orcid":false,"given":"Leti\u021bia Doina","family":"Duceac","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"},{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius Gabriel","family":"Dabija","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"},{"name":"Neurosurgery Department, \u201cGrigore T. Popa\u201d University of Medicine and Pharmacy, 16, Universit\u0103\u021bii Street, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Cost\u0103chescu","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d, 700309 Ia\u0219i, Romania"},{"name":"Neurosurgery Department, \u201cGrigore T. Popa\u201d University of Medicine and Pharmacy, 16, Universit\u0103\u021bii Street, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2094-1089","authenticated-orcid":false,"given":"Eva Maria","family":"Elkan","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5081-3577","authenticated-orcid":false,"given":"Cristian","family":"Gu\u021bu","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doina Carina","family":"Voinescu","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University of Gala\u021bi, 47 Domneasc\u0103 Street, RO-800008 Gala\u021bi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"ref_1","first-page":"1118","article-title":"Herniated lumbar disc","volume":"2009","author":"Jordan","year":"2009","journal-title":"BMJ Clin. Evid."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1302\/0301-620X.101B4.BJJ-2018-1184.R1","article-title":"Complications, reoperations, readmissions, and length of hospital stay in 34 639 surgical cases of lumbardisc herniation","volume":"101","author":"Fjeld","year":"2019","journal-title":"Bone Joint J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1016\/S0140-6736(15)61340-X","article-title":"Global, regional, and national disability-adjustedlife years (DALYs) for 306 diseases and injuries and healthy lifeexpectancy (HALE) for 188 countries, 1990\u20132013: Quantifyingthe epidemiological transition","volume":"386","author":"Murray","year":"2015","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kim, J.-H., van Rijn, R.M., van Tulder, M.W., Koes, B.W., de Boer, M.R., Ginai, A.Z., Ostelo, R.W.G.J., van der Windt, D.A.M.W., and Verhagen, A.P. (2018). Diagnostic accuracy of diagnostic imaging for lumbar disc herniation in adults with low back pain or sciatica is unknown; a systematic review. Chiropr. Man. Ther., 26.","DOI":"10.1186\/s12998-018-0207-x"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"93","DOI":"10.4103\/1793-5482.116384","article-title":"Risk factors of recurrent lumbar disk herniation","volume":"8","author":"Shimia","year":"2013","journal-title":"Asian J. Neurosurg."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Woudneh, A.F. (2025). Understanding the dynamics of post-surgical recovery and its predictors in resource-limited settings: A prospective cohort study. BMC Surg., 25.","DOI":"10.1186\/s12893-025-02786-z"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"323","DOI":"10.21037\/jss-22-121","article-title":"The use of machine learning for predicting candidates for outpatient spine surgery: A review","volume":"9","author":"Wellington","year":"2023","journal-title":"J. Spine Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e300","DOI":"10.1016\/j.wneu.2024.06.041","article-title":"Natural Language Processing-Driven Artificial Intelligence Models for the Diagnosis of Lumbar Disc Herniation with L5 and S1 Radiculopathy: A Preliminary Evaluation","volume":"189","author":"Wang","year":"2024","journal-title":"World Neurosurg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1177\/21925682221097650","article-title":"Machine Learning Predicts Recurrent Lumbar Disc Herniation Following Percutaneous Endoscopic Lumbar Discectomy","volume":"14","author":"Ren","year":"2022","journal-title":"Glob. Spine J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3171\/foc.2003.15.3.10","article-title":"Recurrent lumbar disc herniation","volume":"15","author":"Swartz","year":"2003","journal-title":"Neurosurg. Focus"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100275","DOI":"10.1016\/j.wnsx.2024.100275","article-title":"Lumbar disc herniation: Prevention and treatment of recurrence: WFNS spine committee recommendations","volume":"22","author":"Zileli","year":"2024","journal-title":"World Neurosurg. X"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"481","DOI":"10.3171\/2020.6.SPINE20598","article-title":"Radiological predictors of recurrent lumbar disc herniation: A systematic review and meta-analysis","volume":"34","author":"Brooks","year":"2020","journal-title":"J. Neurosurg. Spine"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1007\/s00586-022-07116-y","article-title":"Overweight and smoking promote recurrent lumbar disk herniation after discectomy","volume":"31","author":"Siccoli","year":"2022","journal-title":"Eur. Spine J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"486","DOI":"10.14740\/jocmr3121w","article-title":"Recurrence Is Associated With Body Mass Index in Patients Undergoing a Single-Level Lumbar Disc Herniation Surgery","volume":"10","author":"Fotakopoulos","year":"2018","journal-title":"J. Clin. Med. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e2378","DOI":"10.1097\/MD.0000000000002378","article-title":"Risk Factors for Recurrent Lumbar Disc Herniation: A Systematic Review and Meta-Analysis","volume":"95","author":"Huang","year":"2016","journal-title":"Medicine"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1016\/j.spinee.2021.07.012","article-title":"Adjuvant surgical decision-making system for lumbar intervertebral disc herniation after percutaneous endoscopic lumber discectomy: A retrospective nonlinear multiple logistic regression prediction model based on a large sample","volume":"21","author":"Li","year":"2021","journal-title":"Spine J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1007\/s13755-025-00343-9","article-title":"Enhanced prediction of spine surgery outcomes using advanced machine learning techniques and oversampling methods","volume":"13","author":"Blanco","year":"2025","journal-title":"Heal. Inf. Sci. Syst."},{"key":"ref_18","first-page":"e48078","article-title":"Machine Learning Applications in Spine Surgery","volume":"15","author":"Tragaris","year":"2023","journal-title":"Cureus"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1016\/j.spinee.2016.08.003","article-title":"A systematic review of preoperative predictors for postoperative clinical outcomes following lumbar discectomy","volume":"16","author":"Wilson","year":"2016","journal-title":"Spine J."},{"key":"ref_20","first-page":"239","article-title":"Predicting postoperative outcomes in lumbar spinal fusion: Development of a machine learning model","volume":"24","author":"Caffard","year":"2023","journal-title":"Spine J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e953","DOI":"10.1016\/j.wneu.2023.11.020","article-title":"An Artificial Intelligence-Based Support Tool for Lumbar Spinal Stenosis Diagnosis from Self-Reported History Questionnaire","volume":"181","author":"Abel","year":"2024","journal-title":"World Neurosurg."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5831","DOI":"10.2147\/JMDH.S493302","article-title":"Deep-Learning-Based Radiomics to Predict Surgical Risk Factors for Lumbar Disc Herniation in Young Patients: A Multicenter Study","volume":"17","author":"Fan","year":"2024","journal-title":"J. Multidiscip. Heal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1007\/s00586-020-06613-2","article-title":"Artificial intelligence facilitates decision-making in the treatment of lumbar disc herniations","volume":"30","author":"Wirries","year":"2021","journal-title":"Eur. Spine J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1007\/s11764-023-01465-3","article-title":"Machine learning (ML) techniques to predict breast cancer in imbalanced datasets: A systematic review","volume":"19","author":"Ghavidel","year":"2025","journal-title":"J. Cancer Surviv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Roy, P., Srijon, F.M.S., Bhowmik, P., and Chatterjee, J.M. (2024). An explainable ensemble approach for advanced brain tumor classification applying Dual-GAN mechanism and feature extraction techniques over highly imbalanced data. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0310748"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.1177\/21925682231173353","article-title":"Machine Learning Prediction Model and Risk Factor Analysis of Reoperation in Recurrent Lumbar Disc Herniation Patients After Percutaneous Endoscopic Lumbar Discectomy","volume":"14","author":"Shan","year":"2024","journal-title":"Glob. Spine J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2167","DOI":"10.1007\/s00586-021-06866-5","article-title":"Artificial intelligence predicts disk re-herniation following lumbar microdiscectomy: Development of the \u201cRAD\u201d risk profile","volume":"30","author":"Harada","year":"2021","journal-title":"Eur. Spine J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3764","DOI":"10.1007\/s00586-023-07718-0","article-title":"Are current machine learning applications comparable to radiologist classification of degenerate and herniated discs and Modic change? A systematic review and meta-analysis","volume":"32","author":"Compte","year":"2023","journal-title":"Eur. Spine J."},{"key":"ref_29","first-page":"425947","article-title":"Automatic Segmentation of Lumbar Spine MRI Images Based on Improved Attention U-Net","volume":"2022","author":"Wang","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"em630","DOI":"10.29333\/ejgm\/15929","article-title":"Diagnostic and therapeutic particularities of a case admitted for low back pain and sciatica","volume":"22","author":"Marinescu","year":"2025","journal-title":"Electron. J. Gen. Med."},{"key":"ref_31","first-page":"44","article-title":"Does oral health affect your bone loss? The link between periodontitis disease and osteoporosis\u2014An epidemiological approach to lumbar disc herniation in a neurosurgery hospital in the northeastern region of Romania","volume":"14","author":"Eva","year":"2023","journal-title":"Rom. J. Oral Rehab."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"666","DOI":"10.12680\/balneo.2024.666","article-title":"Retrospective study of lumbar disc herniation in a hospital in North-Eastern Romania","volume":"15","author":"Gutu","year":"2024","journal-title":"Balneo PRM Res. J."},{"key":"ref_33","first-page":"402","article-title":"The Evolution of Microscope (Aeos) Exoscope in the World of Artificial Intelligence and its Application in Lumbar Disc Herniations Surgery: A Comprehensive Study from Historical Perspective to Current Practices in Romania at the Hospital \u201cProf.Dr.N.Oblu\u201d","volume":"16","author":"Eva","year":"2024","journal-title":"Rom. J. Oral Rehabil."},{"key":"ref_34","unstructured":"ClinicalTrials.gov (2025, April 20). The Prediction of Recurrence Lumbar Disc Herniation at L5-S1 Level Through Machine Learning Models. Identifier: NCT06254585, Available online: https:\/\/ctv.veeva.com\/study\/the-prediction-of-recurrence-lumbar-disc-herniation-at-l5-s1-level-through-machine-learning-models-b."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12880-024-01450-x","article-title":"Radiomics based on MRI to predict recurrent L4-5 disc herniation after percutaneous endoscopic lumbar discectomy","volume":"24","author":"Lin","year":"2024","journal-title":"BMC Med. Imaging"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"\u017dlahti\u010d, B., Zavr\u0161nik, J., Vo\u0161ner, H.B., and Kokol, P. (2024). Transferring Black-Box Decision Making to a White-Box Model. Electronics, 13.","DOI":"10.3390\/electronics13101895"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/13\/1628\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:59:22Z","timestamp":1760032762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/13\/1628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":36,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["diagnostics15131628"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15131628","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]}}}