New Delhi, June 11 (IANS) An international team of scientists has unveiled an artificial intelligence (AI) technique that securely analyses global cancer samples, paving the way for more personalised and privacy-protected cancer treatments. This innovative approach promises to accelerate personalised cancer treatment by enabling clinicians to match therapies to individual patients better, Xinhua news agency reported. The study involved the analysis of protein profiles, known as proteomes, from 7,525 cancer samples collected by 30 collaborating research groups across six countries, including Australia, the United States, Canada, Spain, Greece, and Austria. Strict privacy laws and technical differences in lab methods have long made it difficult to combine large cancer datasets, said the researchers led by Australia’s Children’s Medical Research Institute (CMRI). To overcome these obstacles, the CMRI team in Sydney used federated deep learning, training AI models locally so that only insights — not sensitive data — were shared with a central server, which allowed them to build an accurate global diagnostic tool without transferring patient information between institutions, according to the study published in Cancer Discovery. “It was a very exciting moment when we first saw that the results from data with highly restricted access were just as accurate as the results obtained when the data was all stored in one place,” said CMRI Director and Head of the Cancer Research Unit Roger Reddel. The method successfully integrated proteomic data obtained through different techniques, further enhancing diagnostic precision, said Reddel, also the study’s senior author. The research, part of CMRI’s ProCan programme, aims to use proteomic data to guide cancer treatment, he said, adding this AI-driven approach marks a major step forward in precision oncology by enabling large-scale data analysis. “The purpose of CMRI’s ProCan research programme is to develop proteomic tests that will assist cancer clinicians to choose the best treatment available for each of their patients. By overcoming several major barriers to assembling and analysing large cancer proteomic datasets, we have made a major step towards achieving this goal,” Reddel said.