A team of doctors, scientists, and researchers have developed an artificial intelligence model that can accurately detect cancer, potentially speeding up the diagnosis process and allowing patients to receive treatment more quickly.
Cancer is a major cause of death globally, with approximately 10 million deaths annually, or one in six deaths, as reported by the World Health Organization. Early detection and prompt treatment can often lead to a cure.
The AI tool created by experts from the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research in London, and Imperial College London can determine if abnormal growths seen on CT scans are cancerous.
The research team employed radiomics to develop an AI algorithm by using CT scans of approximately 500 patients who had large lung nodules.
This technique is useful for extracting essential information from medical images that may not be readily visible to the human eye. Subsequently, the AI model’s ability to identify cancerous nodules was evaluated.
The study measured the model’s efficacy using the area under the curve (AUC), where a score of 1 indicates a perfect model, while 0.5 represents a random guess. The results indicated that the AI model could determine each nodule’s cancer risk with an AUC score of 0.87, which was higher than the Brock score, currently in use in clinics, with a score of 0.67.
Furthermore, the model performed comparably to the Herder score, which scored 0.83 in AUC.
