AI system securely detects cancer from patient data

Artificial intelligence (AI) can analyse large amounts of data, such as images or trial results, and can identify patterns often undetectable by humans, making it highly valuable in speeding up disease detection, diagnosis and treatment. But using the technology in medical settings can be controversial because of the risk of accidental data release. Many systems are owned and controlled by private companies, giving them access to confidential patient data – and the responsibility for protecting it. A team of researchers has set out to discover whether a form of AI called swarm learning could be used to help computers predict cancer in medical images of patient tissue samples, without releasing the data from hospitals. Their research, titled'Swarm learning for decentralized artificial intelligence in cancer histopathology', was published on April 25 in Nature Magazine.