{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:29:42Z","timestamp":1783571382211,"version":"3.55.0"},"reference-count":27,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"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\/Objectives: Chest radiography is the primary first-line imaging tool for diagnosing pneumothorax in pediatric emergency settings. However, interpretation under clinical pressures such as high patient volume may lead to delayed or missed diagnosis, particularly for subtle cases. This study aimed to evaluate the diagnostic performance of ChatGPT-5, a multimodal large language model, in detecting and localizing pneumothorax on pediatric chest radiographs using multiple prompting strategies. Methods: In this retrospective study, 380 pediatric chest radiographs (190 pneumothorax cases and 190 matched controls) from a tertiary hospital were interpreted using ChatGPT-5 with three prompting strategies: instructional, role-based, and clinical-context. Performance metrics, including accuracy, sensitivity, specificity, and conditional side accuracy, were evaluated against an expert-adjudicated reference standard. Results: ChatGPT-5 achieved an overall accuracy of 0.77\u20130.79 and consistently high specificity (0.96\u20130.98) across all prompts, with stable reproducibility. However, sensitivity was limited (0.57\u20130.61) and substantially lower for small pneumothoraces (American College of Chest Physicians [ACCP]: 0.18\u20130.22; British Thoracic Society [BTS]: 0.41\u20130.46) than for large pneumothoraces (ACCP: 0.75\u20130.79; BTS: 0.85\u20130.88). The conditional side accuracy exceeded 0.96 when pneumothorax was correctly detected. No significant differences were observed among prompting strategies. Conclusions: ChatGPT-5 showed consistent but limited diagnostic performance for pediatric pneumothorax. Although the high specificity and reproducible detection of larger pneumothoraces reflect favorable performance characteristics, the unacceptably low sensitivity for subtle pneumothoraces precludes it from independent clinical interpretation and underscores the necessity of oversight by emergency clinicians.<\/jats:p>","DOI":"10.3390\/diagnostics16020232","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:30:34Z","timestamp":1768203034000},"page":"232","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic Performance of ChatGPT-5 for Detecting Pediatric Pneumothorax on Chest Radiographs: A Multi-Prompt Evaluation"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0901-0654","authenticated-orcid":false,"given":"Chih-Hao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Pediatrics, MacKay Children\u2019s Hospital, Taipei 104217, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1812-2041","authenticated-orcid":false,"given":"Po-Chih","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, MacKay Children\u2019s Hospital, Taipei 104217, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin-Lin","family":"Shih","sequence":"additional","affiliation":[{"name":"Department of Radiology, MacKay Memorial Hospital, Taipei 104217, Taiwan"},{"name":"School of Medicine, Taipei Medical University, Taipei 110301, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Shan","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Radiology, MacKay Memorial Hospital, Taipei 104217, Taiwan"},{"name":"Department of Medicine, Mackay Medical University, New Taipei City 252005, Taiwan"},{"name":"Mackay Junior College of Medicine, Nursing and Management, Taipei 112021, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, MacKay Memorial Hospital, Taipei 104217, Taiwan"},{"name":"Department of Medicine, Mackay Medical University, New Taipei City 252005, Taiwan"},{"name":"Mackay Junior College of Medicine, Nursing and Management, Taipei 112021, Taiwan"},{"name":"Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/s13613-023-01181-2","article-title":"SPLF\/SMFU\/SRLF\/SFAR\/SFCTCV Guidelines for the management of patients with primary spontaneous pneumothorax","volume":"13","author":"Jouneau","year":"2023","journal-title":"Ann. Intensive Care"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.jacr.2013.12.016","article-title":"Actionable findings and the role of IT support: Report of the ACR Actionable Reporting Work Group","volume":"11","author":"Larson","year":"2014","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1007\/s00247-024-06053-w","article-title":"Spontaneous pneumothorax in children: A radiological perspective","volume":"54","author":"Ayaz","year":"2024","journal-title":"Pediatr. Radiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s13049-019-0623-5","article-title":"Chest wall thickness and depth to vital structures in paediatric patients\u2014Implications for prehospital needle decompression of tension pneumothorax","volume":"27","author":"Terboven","year":"2019","journal-title":"Scand. J. Trauma. Resusc. Emerg. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e191095","DOI":"10.1001\/jamanetworkopen.2019.1095","article-title":"Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs","volume":"2","author":"Hwang","year":"2019","journal-title":"JAMA Netw. Open"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2003061","DOI":"10.1183\/13993003.03061-2020","article-title":"Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs","volume":"57","author":"Nam","year":"2021","journal-title":"Eur. Respir. J."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chang, J., Lee, K.J., Wang, T.H., and Chen, C.M. (2024). Utilizing ChatGPT for Curriculum Learning in Developing a Clinical Grade Pneumothorax Detection Model: A Multisite Validation Study. J. Clin. Med., 13.","DOI":"10.3390\/jcm13144042"},{"key":"ref_8","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_9","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1148\/radiol.2019191293","article-title":"Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiologist-adjudicated Reference Standards and Population-adjusted Evaluation","volume":"294","author":"Majkowska","year":"2020","journal-title":"Radiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2120","DOI":"10.1007\/s00247-021-05146-0","article-title":"Current and emerging artificial intelligence applications in chest imaging: A pediatric perspective","volume":"52","author":"Schalekamp","year":"2022","journal-title":"Pediatr. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e2229289","DOI":"10.1001\/jamanetworkopen.2022.29289","article-title":"Association of Artificial Intelligence-Aided Chest Radiograph Interpretation with Reader Performance and Efficiency","volume":"5","author":"Ahn","year":"2022","journal-title":"JAMA Netw. Open"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4374","DOI":"10.1007\/s00330-024-11339-6","article-title":"CXR-LLaVA: A multimodal large language model for interpreting chest X-ray images","volume":"35","author":"Lee","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/s41746-023-00873-0","article-title":"The imperative for regulatory oversight of large language models (or generative AI) in healthcare","volume":"6","author":"Topol","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1016\/S0140-6736(07)61602-X","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: Guidelines for reporting observational studies","volume":"370","author":"Altman","year":"2007","journal-title":"Lancet"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1378\/chest.119.2.590","article-title":"Management of spontaneous pneumothorax: An American College of Chest Physicians Delphi consensus statement","volume":"119","author":"Baumann","year":"2001","journal-title":"Chest"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"ii39","DOI":"10.1136\/thx.58.suppl_2.ii39","article-title":"BTS guidelines for the management of spontaneous pneumothorax","volume":"58","author":"Henry","year":"2003","journal-title":"Thorax"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lacaita, P.G., Galijasevic, M., Swoboda, M., Gruber, L., Scharll, Y., Barbieri, F., Widmann, G., and Feuchtner, G.M. (2025). The Accuracy of ChatGPT-4o in Interpreting Chest and Abdominal X-Ray Images. J. Pers. Med., 15.","DOI":"10.3390\/jpm15050194"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bulut, B., \u00d6z, M.A., Gen\u00e7, M., G\u00fcr, A., Yortanl\u0131, M., Yortanl\u0131, B.\u00c7., Sariyildiz, O., Yaz\u0131c\u0131, R., Mutlu, H., and Kotanoglu, M.S. (2025). New frontiers in radiologic interpretation: Evaluating the effectiveness of large language models in pneumothorax diagnosis. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0331962"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ajem.2025.03.060","article-title":"Evaluating a large language model\u2019s accuracy in chest X-ray interpretation for acute thoracic conditions","volume":"93","author":"Ostrovsky","year":"2025","journal-title":"Am. J. Emerg. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"220259","DOI":"10.1183\/16000617.0259-2022","article-title":"Deep learning for pneumothorax diagnosis: A systematic review and meta-analysis","volume":"32","author":"Sugibayashi","year":"2023","journal-title":"Eur. Respir. Rev."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106646","DOI":"10.1016\/j.compbiomed.2023.106646","article-title":"High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images","volume":"155","author":"Shamrat","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.crad.2022.08.129","article-title":"Validation study of machine-learning chest radiograph software in primary and emergency medicine","volume":"78","author":"Ahn","year":"2023","journal-title":"Clin. Radiol."},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"900","DOI":"10.3348\/kjr.2025.0599","article-title":"Multimodal Large Language Models in Medical Imaging: Current State and Future Directions","volume":"26","author":"Nam","year":"2025","journal-title":"Korean J. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2336100","DOI":"10.1001\/jamanetworkopen.2023.36100","article-title":"Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department","volume":"6","author":"Huang","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lee, R.W., Lee, K.H., Yun, J.S., Kim, M.S., and Choi, H.S. (2024). Comparative Analysis of M4CXR, an LLM-Based Chest X-Ray Report Generation Model, and ChatGPT in Radiological Interpretation. J. Clin. Med., 13.","DOI":"10.3390\/jcm13237057"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e57896","DOI":"10.2196\/57896","article-title":"Current Status of ChatGPT Use in Medical Education: Potentials, Challenges, and Strategies","volume":"26","author":"Xu","year":"2024","journal-title":"J. Med. Internet Res."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/232\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:41:43Z","timestamp":1768203703000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,11]]},"references-count":27,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diagnostics16020232"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16020232","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,11]]}}}