AI-driven diagnostics and personalized treatment planning in oral oncology: Innovations and future directions

The increasing incidence and complexity of oral cancers demand advancements in both diagnostic precision and individualized treatment strategies. This study investigates the application of artificial intelligence (AI), particularly through deep learning and machine learning models, to enhance diagnostic accuracy and support personalized treatment planning in oral oncology. Recent advancements in AI-driven diagnostics, particularly using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have significantly improved early detection and treatment prediction for oral cancer. By integrating datasets from medical imaging, clinical records, and histopathological profiles, our AI-driven models achieved a diagnostic accuracy of 93 %, with a sensitivity of 91 % and specificity of 94 %, surpassing traditional diagnostic approaches. Furthermore, our treatment prediction models, employing patient-specific tumour characteristics and clinical variables, demonstrated an 87 % accuracy in forecasting optimal therapeutic responses, effectively tailoring treatment strategies to individual patients. These findings underscore AI's transformative potential in oral oncology, providing a foundation for improved patient outcomes and paving the way for future innovations in personalized medicine, as highlighted by recent studies in the field. • The study aims to enhance oral cancer diagnostics using AI, especially with convolutional neural networks (CNNs). • The CNN model achieved 93 % accuracy, 91 % sensitivity, and 94 % specificity in detecting oral cancers. • AI models accurately tailored treatment recommendations with 87 % prediction accuracy based on patient characteristics. • The study utilized a comprehensive dataset of imaging, clinical, and histopathological data to enhance AI's capabilities. • AI-recommended treatments improved survival rates by 20 % and extended progression-free periods by 15%.