Hong Kong: The University of Hong Kong’s Li Ka Shing Faculty of Medicine has announced the creation of the world’s first artificial intelligence (AI) model specifically designed for diagnosing and classifying thyroid cancer. This development represents a significant advancement in medical technology and cancer diagnostics.

According to Anadolu Agency, the AI model was developed in collaboration with the London School of Hygiene and Tropical Medicine. It boasts the capability to identify the stage of cancer and classify its risk category with an accuracy exceeding 90%. The university emphasized that this innovative AI model is expected to reduce the pre-consultation preparation time for frontline clinicians by approximately 50%.

Thyroid cancer is one of the most common cancers in Hong Kong as well as globally. The AI model developed by the university achieves over 90% accuracy in classifying cancer stages as per the American Joint Committee on Cancer (AJCC) and in identifying risk categories according to the American Thyroid Association (ATA), according to Professor Joseph T. Wu, the Managing Director of Hong Kong University of Medicine.

The research teams have created an AI assistant that utilizes large language models, such as ChatGPT and DeepSeek, to analyze clinical documents. These models are designed to comprehend and process human language, thereby enhancing the accuracy and efficiency of thyroid cancer staging and risk classification.