{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T20:56:05Z","timestamp":1790974565348,"version":"4.1.0"},"reference-count":57,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,3,9]],"date-time":"2025-03-09T00:00:00Z","timestamp":1741478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Scaphoid fractures are notorious for a high rate of nonunion, resulting in chronic pain and impaired wrist function. The decision for surgical intervention often involves extensive imaging and prolonged conservative management, leading to delays in definitive treatment. The effectiveness of such treatment remains a subject of ongoing clinical debate, with no universally accepted predictive tool for surgical success. The objective of this study was to train a deep learning algorithm to reliably identify cases of nonunion with a high probability of subsequent union following operative revision. Methods: This study utilized a comprehensive database of 346 patients diagnosed with scaphoid nonunions, with preoperative and postoperative X-rays available for analysis. A classical logistic regression for clinical parameters was used, as well as a TensorFlow deep learning algorithm on X-rays. The latter was developed and applied to these imaging datasets to predict the likelihood of surgical success based solely on the preoperative anteroposterior (AP) X-ray view. The model was trained and validated over six epochs to optimize its predictive accuracy. Results: The logistic regression yielded an accuracy of 66.3% in predicting the surgical outcome based on patient parameters. The deep learning model demonstrated remarkable predictive accuracy, achieving a success rate of 93.6%, suggesting its potential as a reliable tool for guiding clinical decision-making in scaphoid nonunion management. Conclusions: The findings of this study indicate that the preoperative AP X-ray of a scaphoid nonunion provides sufficient information to predict the likelihood of surgical success when analyzed using our deep learning model. This approach has the potential to streamline decision-making and reduce reliance on extensive imaging and prolonged conservative treatment.<\/jats:p>","DOI":"10.3390\/jcm14061850","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T05:46:52Z","timestamp":1741585612000},"page":"1850","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning in Scaphoid Nonunion Treatment"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7182-9404","authenticated-orcid":false,"given":"Leyla","family":"T\u00fcmen","sequence":"first","affiliation":[{"name":"Department of Trauma and Reconstructive Surgery, Eberhard Karls University T\u00fcbingen, BG Trauma Center T\u00fcbingen, Siegfried Weller Institute for Trauma Research, 72076 T\u00fcbingen, Germany"},{"name":"Department of Trauma and Reconstructive Surgery, Eberhard Karls University T\u00fcbingen, BG Trauma Center T\u00fcbingen, 72076 T\u00fcbingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Medved","sequence":"additional","affiliation":[{"name":"Department of Hand, Plastic, Reconstructive and Burn Surgery, BG Trauma Center T\u00fcbingen, Eberhard Karls University T\u00fcbingen, 72076 T\u00fcbingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarzyna","family":"Rachunek-Medved","sequence":"additional","affiliation":[{"name":"Department of Hand, Plastic, Reconstructive and Burn Surgery, BG Trauma Center T\u00fcbingen, Eberhard Karls University T\u00fcbingen, 72076 T\u00fcbingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeaeun","family":"Han","sequence":"additional","affiliation":[{"name":"Kogod Center on Aging and Division of Endocrinology, Mayo Clinic, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0673-3710","authenticated-orcid":false,"given":"Dominik","family":"Saul","sequence":"additional","affiliation":[{"name":"Kogod Center on Aging and Division of Endocrinology, Mayo Clinic, Rochester, MN 55905, USA"},{"name":"Robert Bosch Center for Tumor Diseases, 70469 Stuttgart, Germany"},{"name":"Maybach Clinic, 70469 Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4S","DOI":"10.1177\/17531934231165419","article-title":"Scaphoid fracture and nonunion: New directions","volume":"48","author":"Gray","year":"2023","journal-title":"J. Hand Surg. Eur. Vol."},{"key":"ref_2","first-page":"e47732","article-title":"Application of Artificial Intelligence and Machine Learning in Diagnosing Scaphoid Fractures: A Systematic Review","volume":"15","author":"Orji","year":"2023","journal-title":"Cureus"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1055\/s-0040-1720963","article-title":"Incidence of Scaphoid Fractures and Associated Injuries at US Trauma Centers","volume":"10","author":"Wells","year":"2021","journal-title":"J. Wrist Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"E41","DOI":"10.1097\/TA.0b013e31822458e8","article-title":"Scaphoid fracture epidemiology","volume":"72","author":"Duckworth","year":"2012","journal-title":"J. Trauma Acute Care Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1055\/s-0039-1693147","article-title":"Systematic Review of Diagnosis of Clinically Suspected Scaphoid Fractures","volume":"9","author":"Wu","year":"2020","journal-title":"J. Wrist Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1302\/2058-5241.5.190025","article-title":"Acute scaphoid fractures: Guidelines for diagnosis and treatment","volume":"5","author":"Clementson","year":"2020","journal-title":"EFORT Open Rev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4341","DOI":"10.1007\/s00330-023-10473-x","article-title":"Artificial intelligence for X-ray scaphoid fracture detection: A systematic review and diagnostic test accuracy meta-analysis","volume":"34","author":"Kraus","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s10140-014-1278-1","article-title":"Wrist fractures: Sensitivity of radiography, prevalence, and patterns in MDCT","volume":"22","author":"Balci","year":"2015","journal-title":"Emerg. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10","DOI":"10.2214\/AJR.07.2699","article-title":"MDCT and radiography of wrist fractures: Radiographic sensitivity and fracture patterns","volume":"190","author":"Welling","year":"2008","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1007\/s00330-022-09205-4","article-title":"Musculoskeletal radiologist-level performance by using deep learning for detection of scaphoid fractures on conventional multi-view radiographs of hand and wrist","volume":"33","author":"Hendrix","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1007\/s00167-021-06838-8","article-title":"Artificial intelligence in orthopedics: Three strategies for deep learning with orthopedic specific imaging","volume":"30","author":"Ko","year":"2022","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Bidyuk, P., Gozhyj, A., Kalinina, I., Vysotska, V., Vasilev, M., and Malets, R. (2020, January 21\u201325). Forecasting Nonlinear Nonstationary Processes in Machine Learning Task. Proceedings of the 2020 IEEE Third International Conference on Data Stream Mining & Processing (DSMP), Lviv, Ukraine.","DOI":"10.1109\/DSMP47368.2020.9204077"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1136\/emermed-2022-213057","article-title":"Using clinical risk models to predict outcomes: What are we predicting and why?","volume":"40","author":"Goodacre","year":"2023","journal-title":"Emerg. Med. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s40635-024-00706-8","article-title":"Comparison of artificial intelligence and logistic regression models for mortality prediction in acute respiratory distress syndrome: A systematic review and meta-analysis","volume":"13","author":"He","year":"2025","journal-title":"Intensive Care Med. Exp."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3188","DOI":"10.1007\/s00330-022-09354-6","article-title":"Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection","volume":"33","author":"Germann","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/j.jhsa.2022.02.023","article-title":"A Machine Learning Algorithm to Estimate the Probability of a True Scaphoid Fracture After Wrist Trauma","volume":"47","author":"Bulstra","year":"2022","journal-title":"J. Hand Surg. Am."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106165","DOI":"10.1016\/j.engappai.2023.106165","article-title":"Automated detection of scaphoid fractures using deep neural networks in radiographs","volume":"122","author":"Singh","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1097\/CORR.0000000000002612","article-title":"Can a Deep Learning Algorithm Improve Detection of Occult Scaphoid Fractures in Plain Radiographs? A Clinical Validation Study","volume":"481","author":"Yoon","year":"2023","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e216096","DOI":"10.1001\/jamanetworkopen.2021.6096","article-title":"Development and Validation of a Deep Learning Model Using Convolutional Neural Networks to Identify Scaphoid Fractures in Radiographs","volume":"4","author":"Yoon","year":"2021","journal-title":"JAMA Netw. Open"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Machrowska, A., Karpi\u0144ski, R., Maciejewski, M., Jonak, J., Krakowski, P., and Syta, A. (2025). Multi-Scale Analysis of Knee Joint Acoustic Signals for Cartilage Degeneration Assessment. Sensors, 25.","DOI":"10.3390\/s25030706"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1109\/4233.897061","article-title":"Skeletal growth estimation using radiographic image processing and analysis","volume":"4","author":"Mahmoodi","year":"2000","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lee, J., and Chung, S.W. (2022). Deep Learning for Orthopedic Disease Based on Medical Image Analysis: Present and Future. Appl. Sci., 12.","DOI":"10.3390\/app12020681"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e231","DOI":"10.1016\/j.surge.2022.05.006","article-title":"The progress in the classification and treatment of scaphoid nonunion","volume":"20","author":"Li","year":"2022","journal-title":"Surgeon"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1016\/j.injury.2009.01.140","article-title":"Examination tests predictive of bone injury in patients with clinically suspected occult scaphoid fracture","volume":"40","author":"Unay","year":"2009","journal-title":"Injury"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/j.jhsg.2023.04.014","article-title":"Defining Nonunion for Metacarpal Fractures: A Systematic Review","volume":"5","author":"Hayes","year":"2023","journal-title":"J. Hand Surg. Glob. Online"},{"key":"ref_26","unstructured":"Medtronic Sofamor Danek, Inc. (2025, February 22). INFUSE\u00ae Bone Graft Important Medical Information, Available online: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf\/p000054c.pdf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e162775","DOI":"10.1001\/jamasurg.2016.2775","article-title":"Epidemiology of Fracture Nonunion in 18 Human Bones","volume":"151","author":"Zura","year":"2016","journal-title":"JAMA Surg."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1016\/j.jhsa.2011.01.018","article-title":"Scapholunate advanced collapse and scaphoid nonunion advanced collapse arthritis--update on evaluation and treatment","volume":"36","author":"Strauch","year":"2011","journal-title":"J. Hand Surg. Am."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1302\/0301-620X.78B4.0780519","article-title":"Herbert screw fixation of scaphoid fractures","volume":"78","author":"Filan","year":"1996","journal-title":"J. Bone Jt. Surg. Br."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"20","DOI":"10.2106\/00004623-200300004-00003","article-title":"Percutaneous internal fixation of selected scaphoid nonunions with an arthroscopically assisted dorsal approach","volume":"85","author":"Slade","year":"2003","journal-title":"J. Bone Jt. Surg. Am."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1097\/01.blo.0000205886.66081.9d","article-title":"Minimally invasive management of scaphoid nonunions","volume":"445","author":"Slade","year":"2006","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1051\/sicotj\/2023018","article-title":"Artificial intelligence for fracture diagnosis in orthopedic X-rays: Current developments and future potential","volume":"9","author":"Sharma","year":"2023","journal-title":"SICOT J."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3974","DOI":"10.1007\/s00330-022-09349-3","article-title":"Artificial intelligence vs. radiologist: Accuracy of wrist fracture detection on radiographs","volume":"33","author":"Cohen","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1097\/CORR.0000000000001318","article-title":"Is Deep Learning On Par with Human Observers for Detection of Radiographically Visible and Occult Fractures of the Scaphoid?","volume":"478","author":"Langerhuizen","year":"2020","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e200260","DOI":"10.1148\/ryai.2021200260","article-title":"Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs","volume":"3","author":"Hendrix","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1080\/17453674.2018.1453714","article-title":"Automated detection and classification of the proximal humerus fracture by using deep learning algorithm","volume":"89","author":"Chung","year":"2018","journal-title":"Acta Orthop."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zargari Khuzani, A., Heidari, M., and Shariati, S.A. (2021). COVID-Classifier: An automated machine learning model to assist in the diagnosis of COVID-19 infection in chest X-ray images. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-88807-2"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s12539-020-00403-6","article-title":"A machine learning-based framework for diagnosis of COVID-19 from chest X-ray images","volume":"13","author":"Rasheed","year":"2021","journal-title":"Interdiscip. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e23174","DOI":"10.1002\/ima.23174","article-title":"Intervertebral Cervical Disc Intensity (IVCDI) Detection and Classification on MRI Scans Using Deep Learning Methods","volume":"34","author":"Erkoc","year":"2024","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"100379","DOI":"10.1016\/j.cosrev.2021.100379","article-title":"A survey on deep learning and its applications","volume":"40","author":"Dong","year":"2021","journal-title":"Comput. Sci. Rev."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1016\/j.bjps.2023.10.098","article-title":"Postoperative scaphoid alignment, smoking, and avascular necrosis mostly influence union rate after scaphoid reconstruction: Results from a retrospective single center study involving 370 patients","volume":"87","author":"Illg","year":"2023","journal-title":"J. Plast. Reconstr. Aesthet. Surg."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1002\/sam.11583","article-title":"Optimal ratio for data splitting","volume":"15","author":"Joseph","year":"2022","journal-title":"Stat. Anal."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"4314","DOI":"10.1038\/s41467-023-39902-7","article-title":"Detecting shortcut learning for fair medical AI using shortcut testing","volume":"14","author":"Brown","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_45","unstructured":"Busfield, T. (2020). Image Classification with TensorFlow, Analytics Vidhya. Available online: https:\/\/medium.com\/analytics-vidhya\/image-classification-with-tensorflow-2a406bdfe0c1."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s12593-015-0206-2","article-title":"Factors Associated with Patient Delay in Scaphoid Nonunions","volume":"7","author":"Heidsieck","year":"2015","journal-title":"J. Hand Microsurg."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1055\/s-0035-1564983","article-title":"The Missed Scaphoid Fracture-Outcomes of Delayed Cast Treatment","volume":"4","author":"Grewal","year":"2015","journal-title":"J. Wrist Surg."},{"key":"ref_48","first-page":"118","article-title":"The treatment of pseudoarthrosis of the scaphoid by bone grafting and three methods of internal fixation","volume":"43","author":"Ritter","year":"2000","journal-title":"Can. J. Surg."},{"key":"ref_49","first-page":"510","article-title":"Bone Graft and Fixation Options in the Surgical Management of Scaphoid Nonunion","volume":"24","author":"Ayalon","year":"2024","journal-title":"J. Am. Acad. Orthop. Surg."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.jhsa.2024.10.008","article-title":"MRI for Scaphoid Nonunion: Utilization Rates, Factors Associated with Utilization, and Subsequent Vascularized Bone Graft Use","volume":"50","author":"Shapiro","year":"2024","journal-title":"J. Hand Surg. Am."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1016\/S0895-4356(01)00372-9","article-title":"Logistic regression in the medical literature: Standards for use and reporting, with particular attention to one medical domain","volume":"54","author":"Bagley","year":"2001","journal-title":"J. Clin. Epidemiol."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1007\/s00586-022-07188-w","article-title":"Machine learning versus logistic regression for prognostic modelling in individuals with non-specific neck pain","volume":"31","author":"Liew","year":"2022","journal-title":"Eur. Spine J."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1053\/jhsu.1999.0761","article-title":"Prognostic factors in the treatment of carpal scaphoid nonunions","volume":"24","author":"Schuind","year":"1999","journal-title":"J. Hand Surg. Am."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1097\/BRS.0000000000004510","article-title":"A Predictive Model to Identify Treatment-related Risk Factors for Odontoid Fracture Nonunion Using Machine Learning","volume":"48","author":"Leister","year":"2023","journal-title":"Spine"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"3788","DOI":"10.1007\/s00586-022-07431-4","article-title":"Machine-learning-based approach for nonunion prediction following osteoporotic vertebral fractures","volume":"32","author":"Takahashi","year":"2023","journal-title":"Eur. Spine J."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1213\/ANE.0000000000004575","article-title":"Realistically Integrating Machine Learning into clinical practice: A road map of opportunities, challenges, and a potential future","volume":"130","author":"Hofer","year":"2020","journal-title":"Anesth. Analg."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Naik, N., Hameed, B.M.Z., Shetty, D.K., Swain, D., Shah, M., Paul, R., Aggarwal, K., Ibrahim, S., Patil, V., and Smriti, K. (2022). Legal and Ethical Consideration in Artificial Intelligence in Healthcare: Who Takes Responsibility?. Front. Surg., 9.","DOI":"10.3389\/fsurg.2022.862322"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/6\/1850\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:49:45Z","timestamp":1760028585000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/6\/1850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,9]]},"references-count":57,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["jcm14061850"],"URL":"https:\/\/doi.org\/10.3390\/jcm14061850","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,9]]}}}