{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T09:24:58Z","timestamp":1792315498813,"version":"4.4.0"},"reference-count":14,"publisher":"FapUNIFESP (SciELO)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Braz. Dent. J."],"abstract":"<jats:p>Abstract This study evaluated the diagnostic performance of large language models (LLMs)-ChatGPT 5.0 (OpenAI) and Gemini Flash 2.0 (Google Inc.)-in detecting periapical lesions on periapical radiographs using a standardized multimodal prompt. Seventy-five anonymized periapical radiographs of anterior teeth from the maxilla and mandible were analyzed, evenly distributed between cases with and without lesions. A calibrated endodontic specialist provided the reference diagnosis. Each image was independently assessed five times by both LLMs using the prompt: \u201cDoes this image show a periapical lesion? Answer \u2018Yes\u2019 or \u2018No\u2019. If \u2018Yes\u2019, which tooth?\u201d. Balanced accuracy, sensitivity, specificity, and F1-score were calculated with 95% confidence intervals (CIs) obtained via bootstrap resampling. Performance was also stratified by diagnostic difficulty, and the models were compared using the exact McNemar test (\u03b1 = 0.05). ChatGPT 5.0 showed higher overall performance than Gemini Flash 2.0, with sensitivity of 0.97 (95% CI: 0.95-0.99), specificity of 0.11 (95% CI: 0.07-0.16), and balanced accuracy of 0.54 (95% CI: 0.52-0.57). Gemini Flash 2.0 achieved sensitivity of 0.84 (95% CI: 0.79-0.89), specificity of 0.11 (95% CI: 0.07-0.16), and balanced accuracy of 0.48 (95% CI: 0.44-0.51). Both models showed high false-positive rates and frequent errors in tooth localization. The McNemar test confirmed a significant difference between models (p &lt; 0.05), favoring ChatGPT 5.0. Both LLMs demonstrated high sensitivity but poor specificity, resulting in intermediate diagnostic performance and a bias toward positive classifications. General-purpose LLMs are therefore not yet suitable for radiographic diagnostic use.<\/jats:p>","DOI":"10.1590\/0103-644020256861","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T15:06:57Z","timestamp":1765811217000},"source":"Crossref","is-referenced-by-count":4,"title":["Can Large Language Models Detect Periapical Lesions in Anterior Teeth? A Comparative Study"],"prefix":"10.1590","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0337-4206","authenticated-orcid":false,"given":"Diulia Pereira","family":"Bubna","sequence":"first","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2755-2270","authenticated-orcid":false,"given":"Natanael Henrique Ribeiro","family":"Mattos","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3252-2187","authenticated-orcid":false,"given":"Luana Beatriz das Portas","family":"Luiz","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5649-7234","authenticated-orcid":false,"given":"Flares","family":"Baratto-Filho","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil; University of Joinville,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2606-9336","authenticated-orcid":false,"given":"May Tostes de","family":"Mattos-Calil","sequence":"additional","affiliation":[{"name":"University of Ribeir\u00e3o Preto,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-1656","authenticated-orcid":false,"given":"May Tostes de","family":"Silva-Sousa","sequence":"additional","affiliation":[{"name":"University of Ribeir\u00e3o Preto,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5351-2526","authenticated-orcid":false,"given":"Erika Calvano","family":"K\u00fcchler","sequence":"additional","affiliation":[{"name":"University Hospital Bonn,  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1852-8423","authenticated-orcid":false,"given":"\u00c2ngela Graciela Deliga","family":"Schroder","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1325-4248","authenticated-orcid":false,"given":"Cristiano Miranda de","family":"Araujo","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7507-4667","authenticated-orcid":false,"given":"Bianca Marques de Mattos de","family":"Araujo","sequence":"additional","affiliation":[{"name":"Tuiuti University of Paran\u00e1,  Brazil; University of Joinville,  Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"530","published-online":{"date-parts":[[2025]]},"reference":[{"issue":"4","key":"ref1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/s11282-024-00759-1","article-title":"Comparing the accuracy of two machine learning models in detection and classification of periapical lesions using periapical radiographs","volume":"40","author":"Viet DH","year":"2024","journal-title":"Oral Radiol"},{"issue":"1","key":"ref2","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1186\/s12903-025-06104-0","article-title":"A comparative analysis of deep learning models for assisting in the diagnosis of periapical lesions in periapical radiographs","volume":"25","author":"Liu J","year":"2025","journal-title":"BMC Oral Health"},{"issue":"11","key":"ref3","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1007\/s00784-024-05989-5","article-title":"Machine learning and deep learning models for the diagnosis of apical periodontitis: a scoping review","volume":"28","author":"Basso \u00c1","year":"2024","journal-title":"Clin Oral Investig"},{"issue":"Suppl 3","key":"ref4","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1111\/iej.13921","article-title":"Efficacy of imaging techniques for the diagnosis of apical periodontitis: A systematic review","volume":"56","author":"Hilmi A","year":"2023","journal-title":"International endodontic journa"},{"issue":"1","key":"ref5","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1186\/s12903-025-06050-x","article-title":"Evaluation of the performance of large language models in clinical decision-making in endodontics","volume":"25","author":"\u00d6zbay Y","year":"2025","journal-title":"BMC Oral Health"},{"issue":"1","key":"ref6","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1186\/s12909-024-06389-9","article-title":"Performance of artificial intelligence on Turkish dental specialization exam: can ChatGPT-4.0 and gemini advanced achieve comparable results to humans?","volume":"25","author":"Sismanoglu S","year":"2025","journal-title":"BMC Med Educ"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"106006","DOI":"10.1016\/j.ijmedinf.2025.106006","article-title":"Development and evaluation of a retrieval-augmented large language model framework for enhancing endodontic education","volume":"203","author":"Xu X","year":"2025","journal-title":"Int J Med Inform"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.2196\/47564","article-title":"User Intentions to Use ChatGPT for Self-Diagnosis and Health-Related Purposes: Cross-sectional Survey Study","volume":"10","author":"Shahsavar Y","year":"2023","journal-title":"JMIR Hum Factors"},{"issue":"3","key":"ref9","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1016\/j.jds.2025.03.030","article-title":"Performance of ChatGPT in answering the oral pathology questions of various types or subjects from Taiwan National Dental Licensing Examinations","volume":"20","author":"Wu YH","year":"2025","journal-title":"J Dent Sci"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"105764","DOI":"10.1016\/j.jdent.2025.105764","article-title":"Accuracy, consistency, and contextual understanding of large language models in restorative dentistry and endodontics","volume":"157","author":"Lafourcade C","year":"2025","journal-title":"J Dent"},{"issue":"3","key":"ref11","article-title":"Comparative Analysis of ChatGPT-4o and Gemini Advanced Performance on Diagnostic Radiology In-Training Exams","volume":"17","author":"Huang KA","year":"2025","journal-title":"Cureus"},{"issue":"2","key":"ref12","doi-asserted-by":"crossref","first-page":"e224","DOI":"10.4317\/medoral.26824","article-title":"Accuracy of ChatGPT 3.5, 4.0, 4o and Gemini in diagnosing oral potentially malignant lesions based on clinical case reports and image recognition","volume":"30","author":"Pradhan P","year":"2025","journal-title":"Med Oral Patol Oral Cir Bucal"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"7049360","DOI":"10.1155\/2023\/7049360","article-title":"Evaluation of the Diagnostic and Prognostic Accuracy of Artificial Intelligence in Endodontic Dentistry: A Comprehensive Review of Literature","volume":"2023","author":"Karobari MI","year":"2023","journal-title":"Comput Math Methods Med"},{"issue":"2","key":"ref14","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1111\/aej.12669","article-title":"Prevalence of pulp canal obliteration and periapical pathology in human anterior teeth: A three-dimensional analysis based on CBCT scans","volume":"49","author":"Vera J","year":"2023","journal-title":"Australian Endodontic Journal"}],"container-title":["Brazilian Dental Journal"],"original-title":[],"link":[{"URL":"http:\/\/www.scielo.br\/scielo.php?script=sci_pdf&pid=S0103-64402025000100263&tlng=en","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T15:07:00Z","timestamp":1765811220000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.scielo.br\/scielo.php?script=sci_arttext&pid=S0103-64402025000100263&tlng=en"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":14,"alternative-id":["S0103-64402025000100263"],"URL":"https:\/\/doi.org\/10.1590\/0103-644020256861","relation":{},"ISSN":["1806-4760","0103-6440"],"issn-type":[{"value":"1806-4760","type":"electronic"},{"value":"0103-6440","type":"print"}],"subject":[],"published":{"date-parts":[[2025]]},"article-number":"e25-6861"}}