Artificial intelligence in oral oncology: Current advances and future potential in diagnosis, prognosis, and therapeutic decision-making

Oral squamous cell carcinoma (OSCC) poses a significant global health challenge owing to its rising incidence, late-stage diagnosis, and poor five-year survival rates. Traditional diagnostic and prognostic frameworks are limited by subjectivity, delayed turnaround times, and insufficient integration of molecular and imaging data. In this context, artificial intelligence (AI), which encompasses machine learning, deep learning, and natural language processing, has emerged as a promising tool for supporting diagnostic, prognostic, and therapeutic decision-making in oral oncology. This review summarizes current research on the application of AI in three core domains: diagnosis, prognosis, and therapeutic decision-making. Diagnostic advancements include convolutional neural network-based models for image analysis, digital pathology, and mobile screening tools, which demonstrate high accuracy in early lesion detection and tumor grading. Prognostic tools leverage multimodal data, including histopathology, radiomics, and genomic profiles, to improve risk stratification and survival prediction, often outperforming conventional staging systems in these aspects. In therapeutic planning, AI has the potential to assist in precision radiotherapy planning and surgical navigation, and predictive modeling of treatment responses through radiogenomic integration. Despite promising outcomes, widespread clinical adoption is hindered by data scarcity, model overfitting, interpretability issues, and ethical concerns regarding bias and privacy. Future directions emphasize federated learning, explainable AI, and multi-omics integration to enhance the scalability, transparency, and equity of cancer care. This review underscores the pivotal role of AI in reshaping oral oncology into a predictive, personalized, and data-driven discipline.