{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T01:47:39Z","timestamp":1777513659168,"version":"3.51.4"},"reference-count":30,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"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: Spontaneous pneumothorax (SP) in adolescents has a high recurrence risk, particularly without surgical treatment. This study aimed to predict recurrence using machine learning (ML) algorithms applied to chest computed tomography (CT) and to visualize CT features associated with recurrence. Methods: We retrospectively reviewed 299 adolescents with conservatively managed SP from January 2018 to December 2022. Clinical risk factors were statistically analyzed. Chest CT images were evaluated using ML models, with performance assessed by AUC, accuracy, precision, recall, and F1 score. Gradient-weighted Class Activation Mapping (Grad-CAM) was used for visual interpretation. Results: Among 164 right-sided and 135 left-sided SP cases, recurrence occurred in 54 and 43 cases, respectively. Mean recurrence intervals were 10.5 \u00b1 9.9 months (right) and 12.7 \u00b1 9.1 months (left). Presence of blebs or bullae was significantly associated with recurrence (p &lt; 0.001). Neural networks achieved the best performance (AUC: 0.970 right, 0.958 left). Grad-CAM confirmed the role of blebs\/bullae and highlighted apical lung regions in recurrence, even in their absence. Conclusions: ML algorithms applied to chest CT demonstrate high accuracy in predicting SP recurrence in adolescents. Visual analyses support the clinical relevance of blebs\/bullae and suggest a key role of apical lung regions in recurrence, even when blebs\/bullae are absent.<\/jats:p>","DOI":"10.3390\/jcm14175956","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:09:53Z","timestamp":1756080593000},"page":"5956","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Visual and Predictive Assessment of Pneumothorax Recurrence in Adolescents Using Machine Learning on Chest CT"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2103-3122","authenticated-orcid":false,"given":"Kwanyong","family":"Hyun","sequence":"first","affiliation":[{"name":"Department of Thoracic and Cardiovascular Surgery, St. Vincent\u2019s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae Jun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Thoracic and Cardiovascular Surgery, Uijeongbu St. Mary\u2019s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyong Shil","family":"Im","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Uijeongbu St Mary\u2019s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1241-9537","authenticated-orcid":false,"given":"Sang Chul","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Uijeongbu St Mary\u2019s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeong Hwan","family":"Ryu","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Uijeongbu St Mary\u2019s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"ezae189","DOI":"10.1093\/ejcts\/ezae189","article-title":"Joint ERS\/EACTS\/ESTS clinical practice guidelines on adults with spontaneous pneumothorax","volume":"65","author":"Walker","year":"2024","journal-title":"Eur. J. Cardiothorac. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Hallifax, R. (2022). Aetiology of Primary Spontaneous Pneumothorax. J. Clin. Med., 11.","DOI":"10.3390\/jcm11030490"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/j.surg.2022.03.011","article-title":"Association of initial management on readmissions for spontaneous pneumothorax in adolescents","volume":"172","author":"Tran","year":"2022","journal-title":"Surgery"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1056\/NEJMoa1910775","article-title":"Conservative versus Interventional Treatment for Spontaneous Pneumothorax","volume":"382","author":"Brown","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hung, C.S., Chen, Y.C., Yang, T.F., and Huang, F.H. (2021). Systematic review and meta-analysis on juvenile primary spontaneous pneumothorax: Conservative or surgical approach first?. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0250929"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1093\/icvts\/ivaa064","article-title":"Analysis of pneumothorax recurrence risk factors in 843 patients who underwent videothoracoscopy for primary spontaneous pneumothorax: Results of a multicentric study","volume":"31","author":"Cattoni","year":"2020","journal-title":"Interact. Cardiovasc. Thorac. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.21037\/jtd.2020.03.39","article-title":"Bullae formation hypothesis in primary spontaneous pneumothorax","volume":"12","author":"Yang","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1055\/s-0041-1739420","article-title":"European Pediatric Surgeons\u2019 Association Survey on the Management of Primary Spontaneous Pneumothorax in Children","volume":"32","author":"Soyer","year":"2022","journal-title":"Eur. J. Pediatr. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1089\/lap.2019.0493","article-title":"Feasibility of a Standardized Management for Primary Spontaneous Pneumothorax in Children and Adolescents: A Retrospective Multicenter Study and Review of the Literature","volume":"30","author":"Cerchia","year":"2020","journal-title":"J. Laparoendosc. Adv. Surg. Tech. A"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e230860","DOI":"10.1148\/radiol.230860","article-title":"Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs","volume":"309","author":"Bennani","year":"2023","journal-title":"Radiology"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Deng, L.Y., Lim, X.Y., Luo, T.Y., Lee, M.H., and Lin, T.C. (2023). Application of Deep Learning Techniques for Detection of Pneumothorax in Chest Radiographs. Sensors, 23.","DOI":"10.3390\/s23177369"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"m689","DOI":"10.1136\/bmj.m689","article-title":"Artificial intelligence versus clinicians: Systematic review of design, reporting standards, and claims of deep learning studies","volume":"368","author":"Nagendran","year":"2020","journal-title":"BMJ"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Iyoda, A., Azuma, Y., Sakai, T., Koezuka, S., Otsuka, H., and Sano, A. (2021). A novel finding related to bulla and bleb formation in patients with primary spontaneous pneumothorax. BMC Pulm. Med., 21.","DOI":"10.1186\/s12890-021-01402-z"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"311","DOI":"10.21037\/jtd-23-1430","article-title":"Prediction of postoperative final degree and recurrence of pectus excavatum using machine learning algorithms","volume":"16","author":"Hyun","year":"2024","journal-title":"J. Thorac. Dis."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"39211","DOI":"10.1007\/s11042-023-14831-1","article-title":"MediNet: Transfer learning approach with MediNet medical visual database","volume":"25","author":"Reis","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yue, X., Cui, J., Huang, S., Liu, W., Qi, J., He, K., and Li, T. (2025). An Interpretable Radiomics-Based Machine Learning Model for Predicting Reverse Left Ventricular Remodeling in STEMI Patients Using Late Gadolinium Enhancement of Myocardial Scar. Eur. Radiol.","DOI":"10.1007\/s00330-025-11419-1"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, L., Chen, W., Zhang, J., Wang, Y., Zhou, H., Xu, Y., Li, H., and Ma, X. (2024). Machine Learning-Based Immune Signature for Predicting Prognosis and Immunotherapy Response in Hepatocellular Carcinoma. Front. Immunol., 15.","DOI":"10.3389\/fimmu.2024.1371829"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, Q., Liu, Q., Luo, G., Liu, Z., Huang, J., Zhou, Y., Zhou, Y., Xu, W., and Cheng, J.Z. (2020). Automated segmentation and diagnosis of pneumothorax on chest X-rays with fully convolutional multi-scale ScSE-DenseNet: A retrospective study. BMC Med. Inf. Decis. Mak., 20.","DOI":"10.1186\/s12911-020-01325-5"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shamrat, F., Azam, S., Karim, A., Islam, R., Tasnim, Z., Ghosh, P., and De Boer, F. (2022). LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images. J. Pers. Med., 12.","DOI":"10.3390\/jpm12050680"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Ogasawara, K. (2023). Grad-CAM-Based Explainable Artificial Intelligence Related to Medical Text Processing. Bioengineering, 10.","DOI":"10.3390\/bioengineering10091070"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7421","DOI":"10.1021\/acsomega.2c00362","article-title":"Google Colab and Virtual Simulations: Practical e-Learning Tools to Support the Teaching of Thermodynamics and to Introduce Coding to Students","volume":"7","author":"Vallejo","year":"2022","journal-title":"ACS Omega"},{"key":"ref_22","first-page":"e71922","article-title":"Age-Specific Body Shape Characteristics in the Onset of Spontaneous Pneumothorax: A Comparison Between Teens and 20s","volume":"16","author":"Nonomura","year":"2024","journal-title":"Cureus"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3696","DOI":"10.21037\/jtd-24-175","article-title":"Incidence and risk factors for recurrent primary spontaneous pneumothorax after video-assisted thoracoscopic surgery: A systematic review and meta-analysis","volume":"16","author":"Huang","year":"2024","journal-title":"J. Thorac. Dis."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1016\/j.ccm.2021.08.008","article-title":"Management of Pneumothorax","volume":"42","author":"DeMaio","year":"2021","journal-title":"Clin. Chest Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e38639","DOI":"10.1097\/MD.0000000000038639","article-title":"Is there a change in the view of treatment for primary spontaneous pneumothorax?: The effect of thoracic CT and autologous blood pleurodesis: A retrospective cohort study","volume":"103","author":"Karapinar","year":"2024","journal-title":"Medicine"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.21037\/jtd-22-1486","article-title":"A retrospective analysis of treatment selection and risk factors of treatment failure and recurrence in patients with spontaneous pneumothorax","volume":"15","author":"Nakano","year":"2023","journal-title":"J. Thorac. Dis."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e231236","DOI":"10.1148\/radiol.231236","article-title":"Commercially Available Chest Radiograph AI Tools for Detecting Airspace Disease, Pneumothorax, and Pleural Effusion","volume":"308","author":"Laustrup","year":"2023","journal-title":"Radiology"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1007\/s00247-007-0537-7","article-title":"CT findings for blebs and bullae in children with spontaneous pneumothorax and comparison with findings in normal age-matched controls","volume":"37","author":"Guimaraes","year":"2007","journal-title":"Pediatr. Radiol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1055\/s-0033-1348196","article-title":"Natural course of spontaneous pneumothorax without bullae or blebs under high-resolution computed tomography","volume":"62","author":"Kim","year":"2014","journal-title":"Thorac. Cardiovasc. Surg."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"oa-23","DOI":"10.5761\/atcs.oa.23-00206","article-title":"Prospective Observation Study for Primary Spontaneous Pneumothorax: Incidence of and Risk Factors for Postoperative Neogenesis of Bullae","volume":"30","author":"Furuta","year":"2024","journal-title":"Ann. Thorac. Cardiovasc. Surg."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/17\/5956\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:34:37Z","timestamp":1760034877000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/17\/5956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,23]]},"references-count":30,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["jcm14175956"],"URL":"https:\/\/doi.org\/10.3390\/jcm14175956","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,23]]}}}