[China Tech] Local Experts Develop AI Model for Precise Breast Cancer Diagnosis, Treatment

China Tech is a column dedicated to the innovations reshaping China – and, inevitably, the world. From cutting-edge AI labs and next-gen robotics to homegrown apps that redefine daily life, we explore the breakthroughs that emerge from the country's relentless drive for technological dominance. Some are game-changers, others cautionary tales, but all offer a glimpse into the future as it's being built, at breakneck speed, in China.

Local medical experts have developed an artificial intelligence (AI) model to do subtyping for the most common kind of breast cancer in order to look for targets for precise medication for drug-resistant patients with high speed and high accuracy.

Breast cancer is the most prevalent female cancer and the Luminal type covers nearly 70 percent of the cases. Patients with such type of breast cancer usually receive endocrine therapy.

"New small molecular medicines have had important impacts on patients with terminal Luminal breast cancer. However, some patients can develop drug resistance. It means the same therapy for different patients can't work, so we must develop a precise diagnosis and treatment in line with the cancer's molecular features to offer patients different and individualized treatment for better effects," said Dr Shao Zhimin from Fudan University Shanghai Cancer Center, who led the research.

In 2023, Shao's team completed the world's biggest multi-omics genomic map on the Luminal type and found four subtypes to guide precise medication.

In this research, they targeted treating the difficulty for terminal Luminal patients with drug resistance.

Based on the subtyping system they had developed previously, experts designed and developed an AI model to do quick identification for subtyping.

"By analyzing the clinical biological information on the pathological section, the AI system can give the result of subtyping within five minutes, greatly improving efficiency and supporting precise medicine," explained Shao, whose team is now further training the AI system to judge potential targets and give recommendations for matched targeted drugs to support doctors.

The research, published by the world-leading journal Cancer Cell, has drawn international attention.