Search Dental Tribune

HKU researchers launch world’s first AI-based oral oncology clinic

Researchers at the University of Hong Kong have recently opened an artificial intelligence-based clinic designed to support clinical treatment decisions for patients with oral cancer and to advance cancer prevention and early detection. (All images: University of Hong Kong)

Fri. 23. May 2025

save

HONG KONG: Oral cancer remains a significant global health concern, highlighting the urgent need to strengthen prevention efforts and promote early detection. In response, researchers from the University of Hong Kong (HKU), in collaboration with the Prince Philip Dental Hospital, have launched the world’s first dedicated artificial intelligence (AI) clinic for patients with potentially malignant oral disorders. Introduced as a new medical service in Hong Kong in April 2025, the clinic uses machine learning-based models to support clinicians in identifying individuals at the highest risk of developing oral cancer. This subsequently facilitates earlier intervention and more rigorous patient monitoring.

According to the World Health Organization, oral cancer is the 13th most common cancer in the world. Globally, the five-year survival rate for oral cancer is approximately 50%, largely owing to the high proportion of cases diagnosed at a late stage. According to an HKU press release, about 60% of oral cancer cases in Hong Kong are diagnosed at an advanced stage, highlighting the need for improved early detection and screening programmes in the region.

Dr John Adeoye says that the opening of an artificial intelligence-based oral oncology clinic in Hong Kong marks a significant milestone in applying intelligent systems to patient care in oral oncology.

Dr John Adeoye, contributing specialist at the clinic and assistant professor of digital and precision dentistry at HKU, believes that the AI-based clinic represents a major milestone in applying intelligent methods to clinical decision support for patients with oral cancer and potentially malignant oral disorders—a journey that began in 2019. “Since then, we have developed machine learning models trained to predict oral cancer outcomes. The models demonstrated notable success in predicting cancer risk among individuals with precursor conditions, and the net benefit of those models was found to be higher than current methods used in clinical practice through internal and external testing,” he told Dental Tribune International (DTI).

In clinical settings, the AI-based tools assist oral and maxillofacial surgeons via decision support, treatment planning and recommendations for disease surveillance. A key innovation from the research team is OralCancerPredict, an AI-based web tool developed in 2021. The model was trained using a large patient cohort with oral leukoplakia and oral lichenoid lesions treated at Queen Mary Hospital in Hong Kong between 2003 and 2022 and validated using similar patient cohorts in the UK and Nigeria. The tool evaluates patient demographics, comorbidities, clinical presentation and histological features to estimate the likelihood of cancer development in patients with oral leukoplakia or oral lichenoid lesions. It also categorises patients by risk level and explains the rationale behind its predictions.

Commenting on the potential of the technology, Dr Adeoye told DTI: “We will continue to assess the long-term impact of the AI tools in improving prevention strategies and enabling earlier detection of oral cancer.”

Topics:
Tags:
To post a reply please login or register
advertisement
advertisement