AI shows promise in early detection of oral cancer, review finds
A recent scoping review highlights the growing potential of artificial intelligence in the early diagnosis of oral cancer, particularly in regions of the world with limited health care access. With the global incidence of oral cancer projected to rise sharply, from 390,000 cases in 2022 to 600,000 by 2045, early detection is increasingly critical, the review notes.
Published studies between January 2016 and May 2025 were reviewed, and from 88 articles initially identified, 28 met the inclusion criteria. Most originated from Southeast Asia, where oral cancer prevalence is high, according to the review. The AI techniques examined included convolutional neural networks, artificial neural networks, random forests and decision trees. Deep convolutional neural networks demonstrated the strongest diagnostic performance in terms of sensitivity, specificity and accuracy.
Common data sources included clinical photographs, mobile images, cytology and radiographs. The review emphasized that AI tools are increasingly accessible via smartphone apps and telehealth platforms, which can facilitate early screening in low-resource settings.
“When used effectively, AI can reduce delays in diagnosis and ultimately enhance patient outcomes,” the authors concluded. While challenges remain, such as addressing algorithmic bias and integrating AI into clinical workflows, the review found that AI shows promise in improving oral cancer prognosis and survival rates.
Read more: Cureus
The article presented here is intended to inform you about the broader media perspective on dentistry, regardless of its alignment with the ADA's stance. It is important to note that publication of an article does not imply the ADA's endorsement, agreement, or promotion of its content.