دورية أكاديمية
أعرض في EDS

Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses.

التفاصيل البيبلوغرافية
العنوان: Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses.
المؤلفون: Silva TP; Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Sao Paulo, 13414-903, Brazil., Andrade-Bortoletto MFS; Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Sao Paulo, 13414-903, Brazil., Ocampo TSC; Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Sao Paulo, 13414-903, Brazil., Alencar-Palha C; Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Sao Paulo, 13414-903, Brazil., Bornstein MM; Department of Oral Health & Medicine, University Center for Dental Medicine Basel UZB, University of Basel, Basel, 4058, Switzerland., Oliveira-Santos C; Department of Diagnosis and Oral Health, University of Louisville School of Dentistry, Louisville, KY, 40202, USA., Oliveira ML; Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Sao Paulo, 13414-903, Brazil. matheus.limadeoliveira@unibas.ch.; Department of Oral Health & Medicine, University Center for Dental Medicine Basel UZB, University of Basel, Basel, 4058, Switzerland. matheus.limadeoliveira@unibas.ch.
المصدر: Clinical oral investigations [Clin Oral Investig] 2024 Mar 09; Vol. 28 (3), pp. 204. Date of Electronic Publication: 2024 Mar 09.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Springer-Verlag Country of Publication: Germany NLM ID: 9707115 Publication Model: Electronic Cited Medium: Internet ISSN: 1436-3771 (Electronic) Linking ISSN: 14326981 NLM ISO Abbreviation: Clin Oral Investig
أسماء مطبوعة: Publication: Berlin : Springer-Verlag
Original Publication: Berlin : Springer, c1997-
مواضيع طبية MeSH: Diagnosis, Differential*, Radiography, Panoramic ; Consensus
مستخلص: Objectives: To evaluate the performance of a commercially available Generative Pre-trained Transformer (GPT) in describing and establishing differential diagnoses for radiolucent lesions in panoramic radiographs.
Materials and Methods: Twenty-eight panoramic radiographs, each containing a single radiolucent lesion, were evaluated in consensus by three examiners and a commercially available ChatGPT-3.5 model. They provided descriptions regarding internal structure (radiodensity, loculation), periphery (margin type, cortication), shape, location (bone, side, region, teeth/structures), and effects on adjacent structures (effect, adjacent structure). Diagnostic impressions related to origin, behavior, and nature were also provided. The GPT program was additionally prompted to provide differential diagnoses. Keywords used by the GPT program were compared to those used by the examiners and scored as 0 (incorrect), 0.5 (partially correct), or 1 (correct). Mean score values and standard deviation were calculated for each description. Performance in establishing differential diagnoses was assessed using Rank-1, -2, and - 3.
Results: Descriptions of margination, affected bone, and origin received the highest scores: 0.93, 0.93, and 0.87, respectively. Shape, region, teeth/structures, effect, affected region, and nature received considerably lower scores ranging from 0.22 to 0.50. Rank-1, -2, and - 3 demonstrated accuracy in 25%, 57.14%, and 67.85% of cases, respectively.
Conclusion: The performance of the GPT program in describing and providing differential diagnoses for radiolucent lesions in panoramic radiographs is variable and at this stage limited in its use for clinical application.
Clinical Relevance: Understanding the potential role of GPT systems as an auxiliary tool in image interpretation is imperative to validate their clinical applicability.
(© 2024. The Author(s).)
References: Dentomaxillofac Radiol. 2008 Dec;37(8):458-63. (PMID: 19033431)
Radiographics. 2006 Nov-Dec;26(6):1751-68. (PMID: 17102048)
Insights Imaging. 2022 Jun 4;13(1):100. (PMID: 35662384)
Imaging Sci Dent. 2023 Jun;53(2):175-176. (PMID: 37405199)
AJR Am J Roentgenol. 2011 Jun;196(6 Suppl):WS66-77. (PMID: 21606244)
Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 1998 Jun;85(6):731-5. (PMID: 9638709)
Sci Rep. 2024 Jan 30;14(1):2497. (PMID: 38291068)
Dentomaxillofac Radiol. 2019 Mar;48(3):20180218. (PMID: 30379570)
JMIR Med Inform. 2023 Oct 9;11:e48808. (PMID: 37812468)
Dentomaxillofac Radiol. 2023 Jul;52(5):20220413. (PMID: 37192044)
J Endod. 2012 Jun;38(6):729-32. (PMID: 22595103)
Int J Environ Res Public Health. 2023 Feb 15;20(4):. (PMID: 36834073)
Acad Radiol. 2013 Mar;20(3):305-11. (PMID: 23452475)
J Dent Educ. 2022 Nov;86(11):1545-1551. (PMID: 35781809)
J Am Coll Radiol. 2017 Mar;14(3):345-352. (PMID: 27927590)
Dentomaxillofac Radiol. 2021 Oct 01;50(7):20210002. (PMID: 33882255)
Dentomaxillofac Radiol. 2006 May;35(3):170-4. (PMID: 16618850)
J Dent Educ. 2023 Aug 4;:. (PMID: 37539925)
Forensic Sci Int. 2020 Sep;314:110416. (PMID: 32721824)
فهرسة مساهمة: Keywords: Artificial intelligence; Differential diagnosis; Generative pre-trained transformer; Panoramic radiography
تواريخ الأحداث: Date Created: 20240308 Date Completed: 20240311 Latest Revision: 20240322
رمز التحديث: 20240322
مُعرف محوري في PubMed: PMC10924032
DOI: 10.1007/s00784-024-05587-5
PMID: 38459362
قاعدة البيانات: MEDLINE
الوصف
تدمد:1436-3771
DOI:10.1007/s00784-024-05587-5