Artificial intelligence model has been created by scientists which can identify cancer accurately

A group of scientists, doctors, and researchers have created an AI model that can accurately identify cancer, marking a significant development in the diagnosis and treatment of the fatal disease. Cancer is a leading cause of death worldwide, responsible for around 10 million deaths annually or one in six deaths, according to the World Health Organisation.

However, early detection and swift treatment can cure cancer and save lives. A team from the Royal Marsden NHS foundation trust, Imperial College London, and the Institute of Cancer Research, London designed an AI tool that can identify whether abnormal growths seen on a person’s CT scans are cancerous. The AI algorithm outperformed current methods, according to a study published in the eBioMedicine journal of the Lancet.

The researchers used CT scans of around 500 patients who had large lung nodules to create an AI algorithm using radiomics. Radiomics extracts essential information from medical images that the human eye may fail to identify.

The AI model identified the risk of cancer in each nodule with an AUC of 0.87, with an AUC of 1 indicating perfect accuracy and an AUC of 0.5 indicating random guessing. The research team plans to test the technology on patients with large lung nodules in the clinic to see if it can accurately predict their risk of lung cancer.

Dr Benjamin Hunter, a clinical research fellow at Imperial and a clinical oncology registrar who works at the Royal Marsden, said, ‘In the future, we hope it will improve early detection and potentially make cancer treatment more successful by highlighting high-risk patients and fast-tracking them to earlier intervention.’

The chief investigator of the Libra study, Dr Richard Lee, said that the work aimed to push boundaries to speed up the detection of the disease using innovative technologies such as AI. He added that people diagnosed with lung cancer at the earliest stage are much more likely to survive for five years than those whose cancer is detected late.

Thus, finding ways to speed up the detection of the disease is a priority, and the study could one day support clinicians in identifying high-risk patients.