EUVIMEDEUVIMED entdecken
Systematische ÜbersichtVergleichsstudieMetaanalyseOpen Access · CC BY 4.0

Predicting Malignant Transformation in Oral Epithelial Dysplasia: A Systematic Comparison of Artificial Intelligence‐Based Risk Models and Pathologist‐Based Microscopy

Diele Carine Barreto Arantes, Lucas Monteiro Delgado iD, Marília de Marco Pinto Paiva Dos Santos, Saman Warnakulasuriya iD, Marcelo Sperandio

Journal of Oral Pathology & Medicine · 2026

DOI: 10.1111/jop.70168 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of Oral Pathology & Medicine, 2026. Verfasst von Diele Carine Barreto Arantes und 4 weiteren Autor:innen. Beteiligte Einrichtung: Oral Medicine and Pathology, Faculdade São Leopoldo Mandic, Research Institute, Rua Dr. José Rocha Junqueira, Campinas, São Paulo, Brazil. Hauptthemen laut MEDLINE: Artificial Intelligence, Cell Transformation, Neoplastic, Mouth Neoplasms, Microscopy. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: São Paulo Research Foundation (FAPESP), Fundação de Amparo à Pesquisa do Estado de São Paulo.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Aims Risk prediction models (RPMs) based on histopathological analysis of oral epithelial dysplasia (OED) are increasingly used to stratify patients with oral potentially malignant disorders (OPMDs) and support personalized management. This systematic review and meta‐analysis evaluated artificial intelligence (AI)‐based models compared with conventional human microscopy for predicting malignant transformation (MT).

Methods

A total of 32 studies published between 1998 and 2026 were included (9 AI‐based and 23 human‐based), focusing on OED in oral leukoplakia (OL), erythroleukoplakia, and erythroplakia. AI approaches addressed prediction or prognostic tasks using machine learning (ML), deep learning (DL), or hybrid methods, with multilayer perceptron and random forest among the most frequently used algorithms.

Results

Meta‐analysis demonstrated strong discriminative performance for AI models (pooled odds ratio [OR] = 12.64; 95% CI: 5.65–28.26; I 2 = 57%). Human evaluation also confirmed a significant association between OED and MT (OR = 3.42; 95% CI: 2.07–5.68), with substantial heterogeneity ( I 2 = 85%). AI‐based models showed higher specificity and more consistent performance, while sensitivity remained comparable to human assessment.

Conclusions

Overall, AI‐based RPMs demonstrate promising and more reliable discriminative ability, primarily by improving decision precision rather than detection rates. However, further standardization, external validation, and larger multicentric datasets are required for clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceCell Transformation, NeoplasticMouth NeoplasmsMicroscopyLeukoplakia, OralPrecancerous ConditionsHumansPrediction AlgorithmsPredictive Learning ModelsErythroplasiaRisk AssessmentMachine LearningDeep LearningRandom ForestAlgorithmsSoft Computing

Stichwörter der Autor:innen

artificial intelligencemalignant transformationoral epithelial dysplasiaoral leukoplakiarisk prediction models

Autor:innen und Institutionen

  • Oral Medicine and Pathology, Faculdade São Leopoldo Mandic, Research Institute, Rua Dr. José Rocha Junqueira, Campinas, São Paulo, Brazil.
  • Modelo Clinic, Oral and Digestive Medicine, Belo Horizonte, Minas Gerais, Brazil.
  • Faculty of Medicine, Federal University of Minas Gerais, Belo Horizonte, Minas Gerais, Brazil.
  • WHO Collaborating Centre for Oral Cancer and Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London, UK.

ORCID-Profile: Lucas Monteiro Delgado, Saman Warnakulasuriya

Förderung

  • São Paulo Research Foundation (FAPESP)
  • Fundação de Amparo à Pesquisa do Estado de São Paulo

Zitieren

APA

Arantes, D. C. B., Delgado, L. M., Dos Santos, M. M. P. P., Warnakulasuriya, S., & Sperandio, M. (2026). Predicting Malignant Transformation in Oral Epithelial Dysplasia: A Systematic Comparison of Artificial Intelligence‐Based Risk Models and Pathologist‐Based Microscopy. Journal of Oral Pathology & Medicine. https://doi.org/10.1111/jop.70168

Vancouver

Arantes DCB, Delgado LM, Dos Santos MMPP, Warnakulasuriya S, Sperandio M. Predicting Malignant Transformation in Oral Epithelial Dysplasia: A Systematic Comparison of Artificial Intelligence‐Based Risk Models and Pathologist‐Based Microscopy. Journal of Oral Pathology & Medicine. 2026. doi:10.1111/jop.70168

BibTeX
@article{Arantes2026,
  author = {Arantes, Diele Carine Barreto and Delgado, Lucas Monteiro and Dos Santos, Marília de Marco Pinto Paiva and Warnakulasuriya, Saman and Sperandio, Marcelo},
  title = {Predicting Malignant Transformation in Oral Epithelial Dysplasia: A Systematic Comparison of Artificial Intelligence‐Based Risk Models and Pathologist‐Based Microscopy},
  journal = {Journal of Oral Pathology & Medicine},
  year = {2026},
  doi = {10.1111/jop.70168}
}
Kostenlos starten →