{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T14:51:34Z","timestamp":1787755894142,"version":"build-2784847793"},"reference-count":27,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010975","name":"Pediatric Orthopaedic Society of North America","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100010975","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Foderaro-Quattrone Grants for AI Innovation in Orthopedic Surgery"},{"name":"Foderaro-Quattrone Grants for AI Innovation in Orthopedics"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Scoliosis has various etiologies, ranging from idiopathic, congenital, to those with spinal cord abnormalities. Advanced imaging is not always feasible and limited by cost, low-yield, and anesthesia risks in children. Given artificial intelligence's potential, we hypothesize that a deep learning (DL)\u2013based image classifier will demonstrate superior performance in radiographic classification of scoliosis etiology compared witht experienced spine surgeons based on spine radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>One thousand thirty-six pediatric patients from single institution with scoliosis diagnosis and paired anterior-posterior - lateral images were included. Patients were manually classified based on their scoliosis etiology from chart review, including previous spine imaging studies when available. Categories included idiopathic, congenital, and spinal cord pathology. Images were randomized and assigned for training, validation, and testing. A DL-classifier using EfficientNet B4 architecture was trained on the radiographs. Accuracy and positive predictive value as defined by precision, recall, and F1-score were calculated to assess final performance metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The trained classifier performed well at identifying correct etiologies, with F1-Score (harmonic mean of precision-recall) of 0.97. Model precision was 0.99 for adolescent idiopathic scoliosis, 0.89 for congenital, and 0.78 for spinal cord pathology. Performance was higher on more common classes, with lower performance observed in class with fewer images. The algorithm has highest overall precision (0.96), recall (0.96), and F1 (0.96), while Surgeons 1 and 2 have lower accuracies (precision 0.80, recall 0.79, and F1 0.79 and precision 0.76, recall 0.67, and F10.71, respectively). There was no clear pattern identified regarding the surgeons' errors and poor agreement on which X-rays corresponded to underlying spinal cord pathology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>A DL-convolutional-neural-network classifier has been trained to high degree of accuracy to distinguish between 3 scoliosis etiologies on pediatric spine radiographs. This model could provide a novel tool to clinicians to decide when to refer for axial imaging. It had superior diagnostic performance compared with experienced spine surgeons. After further validation and refinement, a clinician could put a patient's X-rays into the predictive tool for analysis and use the results to discuss with the family the risk of finding spinal cord pathology, helping them determine together the best timing for an MRI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence:<\/jats:title>\n                    <jats:p>\n                      <jats:underline>Level III<\/jats:underline>\n                      . See Instructions for Authors for a complete description of levels of evidence.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.2106\/jbjs.oa.25.00257","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T19:00:24Z","timestamp":1764097224000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Predicting Nonidiopathic Scoliosis from Plain Radiographs"],"prefix":"10.2106","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1019-5035","authenticated-orcid":false,"given":"Kellen L.","family":"Mulford","sequence":"first","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7566-6980","authenticated-orcid":false,"given":"Hans K.","family":"Nugraha","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3038-1601","authenticated-orcid":false,"given":"Julia E","family":"Todderud","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7413-9708","authenticated-orcid":false,"given":"Andrew","family":"Pumford","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9950-3668","authenticated-orcid":false,"given":"Todd A.","family":"Milbrandt","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8665-3787","authenticated-orcid":false,"given":"Paul M.","family":"Huddleston","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0907-1668","authenticated-orcid":false,"given":"Melvin D.","family":"Helgeson","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-6975","authenticated-orcid":false,"given":"A. Noelle","family":"Larson","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory, Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,10]]},"reference":[{"issue":"6","key":"R1-20251125","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1097\/BPO.0000000000001808","article-title":"Trends in incidence of adolescent idiopathic scoliosis: a modern US population-based study","volume":"41","author":"Thomas","year":"2021","journal-title":"J Pediatr Orthop"},{"key":"R2-20251125","doi-asserted-by":"crossref","first-page":"1399049","DOI":"10.3389\/fped.2024.1399049","article-title":"Prevalence of scoliosis in children and adolescents: a systematic review and meta-analysis","volume":"12","author":"Li","year":"2024","journal-title":"Front Pediatr."},{"issue":"9","key":"R3-20251125","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1016\/j.spinee.2022.03.016","article-title":"The incidence and prevalence of early-onset scoliosis: a regional multicenter epidemiological study","volume":"22","author":"AlNouri","year":"2022","journal-title":"Spine J."},{"issue":"8","key":"R5-20251125","doi-asserted-by":"crossref","first-page":"2209","DOI":"10.3390\/jcm13082209","article-title":"How long can you delay? Curve progression while awaiting vertebral body tethering surgery","volume":"13","author":"Regan","year":"2024","journal-title":"J Clin Med."},{"issue":"2","key":"R6-20251125","doi-asserted-by":"crossref","first-page":"e186","DOI":"10.1097\/BPO.0000000000002839","article-title":"Do not forget the spine MRI in children with arthrogryposis multiplex congenita: high prevalence of tethered spinal cord and preliminary clinical findings following detethering","volume":"45","author":"Nugraha","year":"2025","journal-title":"J Pediatr Orthop."},{"issue":"1","key":"R7-20251125","doi-asserted-by":"crossref","first-page":"53","DOI":"10.3171\/2020.1.PEDS18755","article-title":"Radiological and clinical associations with scoliosis outcomes after posterior fossa decompression in patients with Chiari malformation and syrinx from the Park-Reeves Syringomyelia Research Consortium","volume":"26","author":"Strahle","year":"2020","journal-title":"J Neurosurg Pediatr."},{"issue":"10","key":"R8-20251125","doi-asserted-by":"crossref","first-page":"1629","DOI":"10.1007\/s00586-007-0472-1","article-title":"Scoliosis associated with syringomyelia: analysis of MRI and curve progression","volume":"16","author":"Yeom","year":"2007","journal-title":"Eur Spine J."},{"issue":"5","key":"R9-20251125","first-page":"597","article-title":"Adolescent idiopathic scoliosis and mental health disorders: a narrative review of the literature","volume":"9","author":"Mitsiaki","year":"2022","journal-title":"Children (Basel)"},{"issue":"14","key":"R10-20251125","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.3390\/healthcare11142078","article-title":"Diagnostic technology: trends of use and availability in a 10-Year period (2011-2020) among sixteen OECD countries","volume":"11","author":"Martella","year":"2023","journal-title":"Healthcare (Basel)"},{"issue":"8","key":"R11-20251125","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1097\/BRS.0b013e3181da218c","article-title":"Use and outcome of MRI in the surgical treatment of adolescent idiopathic scoliosis","volume":"36","author":"Diab","year":"2011","journal-title":"Spine (Phila Pa 1976)"},{"issue":"6","key":"R12-20251125","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1111\/pan.13390","article-title":"The impact of general anesthesia on child development and school performance: a population-based study","volume":"28","author":"Schneuer","year":"2018","journal-title":"Pediatr Anesth."},{"issue":"2","key":"R13-20251125","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.mayocp.2011.11.008","article-title":"Attention-deficit\/hyperactivity disorder after early exposure to procedures requiring general anesthesia","volume":"87","author":"Sprung","year":"2012","journal-title":"Mayo Clinic Proc."},{"issue":"6","key":"R14-20251125","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1007\/s43390-024-00933-9","article-title":"Deep learning classification of pediatric spinal radiographs for use in large scale imaging registries","volume":"12","author":"Mulford","year":"2024","journal-title":"Spine Deform"},{"issue":"2","key":"R15-20251125","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.spinee.2023.09.011","article-title":"Automated measurements of interscrew angles in vertebral body tethering patients with deep learning","volume":"24","author":"Mulford","year":"2024","journal-title":"Spine J."},{"issue":"3","key":"R16-20251125","doi-asserted-by":"crossref","first-page":"e210206","DOI":"10.1148\/ryai.210206","article-title":"Deep learning for radiographic measurement of femoral component subsidence following total hip arthroplasty","volume":"4","author":"Rouzrokh","year":"2022","journal-title":"Radiol Artif Intelligence"},{"issue":"18","key":"R17-20251125","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.2106\/JBJS.21.01229","article-title":"Applying deep learning to establish a total hip arthroplasty radiography registry: a stepwise approach","volume":"104","author":"Rouzrokh","year":"2022","journal-title":"J Bone Jt Surg."},{"issue":"7","key":"R20-20251125","doi-asserted-by":"crossref","first-page":"4845","DOI":"10.1007\/s10994-022-06268-8","article-title":"The class imbalance problem in deep learning","volume":"113","author":"Ghosh","year":"2024","journal-title":"Machine Learn."},{"key":"R21-20251125","doi-asserted-by":"crossref","first-page":"120253","DOI":"10.1016\/j.neuroimage.2023.120253","article-title":"Class imbalance should not throw you off balance: choosing the right classifiers and performance metrics for brain decoding with imbalanced data","volume":"277","author":"Th\u00f6lke","year":"2023","journal-title":"Neuroimage"},{"issue":"10","key":"R22-20251125","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1097\/BRS.0000000000004885","article-title":"Causes of delays in treatment of patients with pediatric scoliosis in the Brazilian health system","volume":"49","author":"Meves","year":"2024","journal-title":"Spine (Phila Pa 1976)"},{"key":"R23-20251125","doi-asserted-by":"crossref","first-page":"213","DOI":"10.3389\/fnhum.2019.00213","article-title":"Analysis of perceptual expertise in radiology - current knowledge and a new perspective","volume":"13","author":"Waite","year":"2019","journal-title":"Front Hum Neurosci."},{"issue":"3","key":"R24-20251125","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1007\/s10278-024-00990-6","article-title":"Deep learning for chest X-ray diagnosis: competition between radiologists with or without artificial intelligence assistance","volume":"37","author":"Guo","year":"2024","journal-title":"J Imaging Inform Med."},{"issue":"6","key":"R25-20251125","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s12178-024-09893-z","article-title":"Artificial intelligence for clinically meaningful outcome prediction in orthopedic research: current applications and limitations","volume":"17","author":"Jang","year":"2024","journal-title":"Curr Rev Musculoskelet Med."},{"issue":"10","key":"R26-20251125","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2106\/JBJS.RVW.24.00122","article-title":"Generative artificial intelligence and prompt engineering: a primer for orthopaedic surgeons","volume":"12","author":"Carroll","year":"2024","journal-title":"JBJS Rev"},{"issue":"1","key":"R27-20251125","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1093\/brain\/82.1.23","article-title":"The cervical spinal canal in syringomyelia","volume":"82","author":"Wells","year":"1959","journal-title":"Brain"},{"issue":"1","key":"R28-20251125","doi-asserted-by":"crossref","first-page":"99","DOI":"10.4184\/asj.2015.9.1.99","article-title":"Diastematomyelia: a surgical case with long-term follow-up","volume":"9","author":"Bekki","year":"2015","journal-title":"Asian Spine J."},{"issue":"1","key":"R30-20251125","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/s41746-022-00689-4","article-title":"Integrated multimodal artificial intelligence framework for healthcare applications","volume":"5","author":"Soenksen","year":"2022","journal-title":"NPJ Digit Med."},{"key":"R31-20251125","first-page":"100236","article-title":"The use of deep learning in medical imaging to improve spine care: a scoping review of current literature and clinical applications","volume":"15","author":"Constant","year":"2023","journal-title":"North Am Spine Soc J"}],"container-title":["JBJS Open Access"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.OA.25.00257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:54:45Z","timestamp":1787752485000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.OA.25.00257"}},"subtitle":["A Deep-Learning Approach"],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.2106\/jbjs.oa.25.00257","relation":{},"ISSN":["2472-7245"],"issn-type":[{"value":"2472-7245","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}