Related Experiment Video
Updated: Aug 6, 2026
Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia
Published on: February 16, 2024
Predicting Malignant Transformation in Oral Epithelial Dysplasia: A Systematic Comparison of Artificial
Diele Carine Barreto Arantes1,2, Lucas Monteiro Delgado3, Marília de Marco Pinto Paiva Dos Santos1
1Oral Medicine and Pathology, Faculdade São Leopoldo Mandic, Research Institute, Rua Dr. José Rocha Junqueira, Campinas, São Paulo, Brazil.
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; I2 = 57%). Human evaluation also confirmed a significant association between OED and MT (OR = 3.42; 95% CI: 2.07-5.68), with substantial heterogeneity (I2 = 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.
