Researchers have created a tool that allows glycomics datasets to be analysed using artificial intelligence for early cancer diagnoses. A team at the University of California (UC) San Diego, US, have developed a tool called GlyCompare that enables researchers to analyse glycomics datasets using artificial intelligence (AI), potentially leading to early cancer diagnoses. GlyCompare takes a systems-level perspective that accounts for shared biosynthetic pathways of glycans within and across samples. According to the team, one of the keys to the GlyCompare approach is that it looks at the biological steps needed to synthesise the subunits that make up glycans, rather than only looking at only the whole glycans themselves, thereby improving the accuracy of statistical analyses of glycomics data. To introduce their technology, the team demonstrated their ability to enhance comparisons of glycomics datasets by focusing on the hidden relationships between glycans in several contexts, including gastric cancer tissues.

The new decade opened with some intriguing news: The journal Nature reported that artificial intelligence was better at identifying breast cancers on mammograms than radiologists. Researchers at Google Health teamed up with academic medical centers in the United States and Britain to train an AI system using tens of thousands of mammograms. To understand why, it helps to have a sense of how AI systems learn. In this case, the system was trained with images labeled as either "cancer" or "not cancer." From them, it learned to deduce features -- such as shape, density and edges -- that are associated with the cancer label.

The new decade opened with some intriguing news: The journal Nature reported that artificial intelligence was better at identifying breast cancers on mammograms than radiologists. Researchers at Google Health teamed up with academic medical centers in the United States and Britain to train an AI system using tens of thousands of mammograms. To understand why, it helps to have a sense of how AI systems learn. In this case, the system was trained with images labeled as either "cancer" or "not cancer." From them, it learned to deduce features -- such as shape, density and edges -- that are associated with the cancer label.

The new decade opened with some intriguing news: the journal Nature reported that artificial intelligence was better at identifying breast cancers on mammograms than radiologists. Researchers at Google Health teamed up with academic medical centers in the United States and Britain to train an AI system using tens of thousands of mammograms. To understand why, it helps to have a sense of how AI systems learn. In this case, the system was trained with images labeled as either "cancer" or "not cancer." From them, it learned to deduce features from the images -- such as shape, density and edges -- that are associated with the cancer label.

The British government has announced ambitious plans to prevent an estimated 22,000 cancer deaths by 2033, through the use of artificial intelligence to predict those individuals at greater risk of developing the disease. The platforms being developed under funding from the British government are targeted at prostate, lung and bowel cancer. The specific aim of the platform is to detect individuals at a greater risk from these types of cancers earlier by assessing the millions of data points held by the National Health Service (NHS), drawing upon information contained in patient records, such as genetic information, and lifestyle factors. With lifestyle factors, this could include social media profiles. This will help to determine which patients to screen and when to refer people for medical assessments.

Theresa May will pledge millions of pounds of government funding to develop artificial intelligence able to transform outcomes through early diagnosis of cancer and chronic disease. In a speech in Mansfield on Monday that is being billed as the first of a series on industrial strategy, May will say: "Late diagnosis of otherwise treatable illnesses is one of the biggest causes of avoidable deaths. "The development of smart technologies to analyse great quantities of data quickly and with a higher degree of accuracy than is possible by human beings, opens up a whole new field of medical research and gives us a new weapon in our armoury in the fight against disease." May wants industry and charities to work with the NHS to develop algorithms that can use patient data and lifestyle information to warn GPs when a patient should be referred to an oncologist or another specialist. The plans envisage at least 50,000 people being diagnosed at an early stage of prostate, ovarian, lung or bowel ...