Learing the natural history of human energy with permanent transformations<\/a><\/p>\nEMBL Staff member of the European Institute of Bioinformatics (EMBL-EBI), Tomas Fitzgerald, says: \u201cMedical events often follow a pattern. Our AI model can learn these patterns and predict future health.\"<\/p>\n
Delphi-2M tool by assessing someoneWhether and when cancer, diabetes, heart disease, respiratory diseases are likely to occur<\/strong>Health risks are judged by multiple diseases\u3002<\/p>\nThe tool willAnalysis of \u201cmedical events\u201d in patient history<\/strong>For example, the timing of the diagnosis of a disease combined with lifestyle factors, including obesity, smoking or drinking, age and sex. From anonymous patient records, Delphi-2M can also predictA healthy development for the next decade or more<\/strong>.<\/p>\nThe model is based onBritish Biobank, 400,000 people and Danish National Patient Registry, 1.9 million anonymous data<\/strong>TRAINING AND TESTING. HEALTH RISKS ARE PRESENTED WITH THE PROBABILITY OF CHANGE OVER TIME, WITH SIMILAR PREDICTIONS OF THE POSSIBILITY OF RAIN ON WEEKENDS\u3002<\/p>\nEMBL Interim Executive Director Ewan Birney said that patients might benefit from this tool in the coming years. \"When you go to the doctor, the doctor hasGet used to these tools<\/strong>And they can tell you, \"This is your four major health risks in the future, two key measures you can take to change the risk. 'I think everyone will be advised to lose weight, and if you smoke, you will be advised to quit smoking, and the recommendations will be based on overall data and will not change significantly. However, there may be more specific measures for certain diseases. This is the future we want to achieve.\u201d<\/p>\nHe noted that the advantage of Delphi-2M compared to existing tools such as the Qrisk method used to calculate the risk of heart disease or stroke over the next 10 years was thatAll diseases can be predicted at the same time and covered for longer periods<\/strong>It's a single disease model\u3002<\/p>\nAccording to the research team: \u201cDelphi-2M predicts the incidence of more than 1,000 diseases, based on the history of past diseases of each individual, with the same accuracy as the existing single disease model. In addition, Delphi-2M can produce synthetic data on future health trajectories that will inform the potential burden of disease for up to 20 years in the future.\u201d<\/p>\n
Professor Moritz Gerstung, Head of the AI Department of the German Cancer Research Centre on Oncology, said: \u201cThis marks a new starting point for understanding how human health and disease develop. Generating models like usThe future is expected to help in individualizing health care<\/strong>and large-scale forecasting of medical needs.\u201d<\/p>","protected":false},"excerpt":{"rendered":"On September 21st, according to The Guardian, scientists developed a new artificial intelligence tool that can predict the potential risk of individuals exceeding 1,000 diseases and predict health change 10 years ahead. Experts from the European Molecular Biology Laboratory (EMBL), the German Cancer Research Centre and the University of Copenhagen have jointly tailored this generated AI tool, with algorithmic concepts similar to large language models. This is one of the most comprehensive applications to date in the development of large-scale simulations of human diseases, with the tool using data from two independent medical systems for training. The results were published in Nature magazine. 1AI with links: Learning the natural history o<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3257,383,2885],"collection":[],"class_list":["post-43681","post","type-post","status-publish","format-standard","hentry","category-news","tag-3257","tag-ai","tag-2885"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/43681","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=43681"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/43681\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=43681"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=43681"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=43681"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=43681"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"e62284383j00t2xafw003sd000v4013p\"](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/09\/e6284383j00t2xafw003sd000v4013sp.jpg\" "\\"e62284383j00t2xafw003sd000v4013p\\"")
<\/p>\n