Diagnostic performance of ChatGPT-4.0 in histopathological description analysis of oral and maxillofacial lesions: a comparative study with pathologists

Maria Cuevas-Nunez*, Valentina Ignacia Alvarez Silberberg, Maria Arregui, Bruno C. Jham, Rosa Ballester-Victoria, Inessa Koptseva, María José Biosca Gómez de Tejada, Rodolfo Posada-Caez, Victor Gil Manich, Javier Bara-Casaus, Maria Teresa Fernández-Figueras

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Objective: To evaluate the diagnostic performance of ChatGPT-4.0 in histopathological diagnoses of oral and maxillofacial lesions and compare its performance with pathologists. Study Design: A retrospective analysis of 102 histopathological descriptions was conducted. Data, including site, age and sex, were anonymized from the General University Hospital's Department of Pathology. ChatGPT-4.0 provided diagnoses, which were categorized as correct, similar, or different compared to pathologists' diagnoses. Descriptive statistics, Chi-squared tests, correlation, and regression analyses were used to assess accuracy and the influence of age and gender. Results: ChatGPT-4.0 correctly diagnosed 61 out of 102 cases, yielding an accuracy of 59.8%. The distribution of diagnostic scores did not significantly deviate from expectations (Chi-squared Statistic: 0.0, P = 1.0). A moderate negative correlation between age and diagnostic scores (r = −0.33) was observed, with age significantly predicting scores (P = .001). No significant difference was found between genders (P = .26). ChatGPT-4.0 performed worst with granuloma and inflammation cases (100% incorrect) and best with mucocele cases (93.3% correct). Conclusion: ChatGPT-4.0 shows moderate accuracy in histopathological diagnosis of oral and maxillofacial lesions, with performance varying by lesion type. Improvements are needed to enhance its clinical reliability.

Original languageEnglish
Pages (from-to)453-461
Number of pages9
JournalOral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Volume139
Issue number4
DOIs
StatePublished - Apr 2025

Bibliographical note

Publisher Copyright:
© 2024 Elsevier Inc.

Fingerprint

Dive into the research topics of 'Diagnostic performance of ChatGPT-4.0 in histopathological description analysis of oral and maxillofacial lesions: a comparative study with pathologists'. Together they form a unique fingerprint.

Cite this