A groundbreaking AI-powered clinic for early detection of oral cancer has been launched at the Faculty of Dentistry, University of Hong Kong. The new facility uses advanced machine learning to assess the risk of precancerous lesions developing into malignancy, potentially revolutionizing head and neck cancer diagnostics.
-
World-first innovation: HKU opens the first clinic globally using artificial intelligence to detect oral cancer early.
-
AI-based system: OralCancerPredict analyzes multidimensional patient data to assess cancer risk with 94% accuracy.
-
Targeted care: Patients are stratified into high or low risk, improving diagnosis and treatment efficiency.
-
Improved outcomes: The AI-assisted approach helps avoid unnecessary surgeries and ensures timely intervention.
Hong Kong launches world’s first AI-powered oral cancer detection clinic
The world’s first clinic dedicated to early detection of oral cancer using artificial intelligence (AI) has opened at the Faculty of Dentistry of the University of Hong Kong (HKU). Launched in April 2025, the clinic represents a major advancement in the early identification and management of oral potentially malignant disorders (OPMDs), a group of lesions that can precede oral cancer—one of the most common cancers in the head and neck region.
Tackling late diagnoses with AI
In Hong Kong, approximately 60% of oral cancer cases are diagnosed at an advanced stage, significantly reducing treatment success rates. The new clinic was created to address this gap by enhancing early detection and prevention. It accepts patients with clinically confirmed precancerous oral lesions referred by dentists or general practitioners.
The core of the clinic’s innovative approach is OralCancerPredict, a proprietary clinical decision support system developed by researchers at HKU. This AI-based tool analyzes a wide range of patient data, including demographic factors, comorbidities, clinical observations, and histopathological findings, to calculate the likelihood of malignant transformation.
Risk-based stratification for optimized care
OralCancerPredict categorizes patients into two groups—high-risk and low-risk—based on their potential for malignant progression. It focuses particularly on lesions such as leukoplakia, erythroplakia, oral lichen planus, and oral submucous fibrosis.
According to HKU’s press release, the AI-assisted system achieves an average predictive accuracy of 94%, surpassing traditional risk assessment methods. This not only improves diagnostic precision and enables timely treatment but also reduces overtreatment by avoiding unnecessary surgical interventions in low-risk cases.
A new era of personalized oncology in dentistry
The clinic sets a new standard in personalized care by combining clinical expertise with AI-driven analytics. By improving the accuracy and efficiency of oral cancer risk assessment, it offers a powerful tool for clinicians seeking to deliver precision care while managing healthcare resources more effectively.
