{"id":170463,"date":"2025-09-17T15:34:42","date_gmt":"2025-09-17T15:34:42","guid":{"rendered":"https:\/\/teknomers.com\/en\/an-ai-model-is-capable-of-predicting-the-risk-of-a-thousand-diseases\/"},"modified":"2025-09-17T15:34:44","modified_gmt":"2025-09-17T15:34:44","slug":"an-ai-model-is-capable-of-predicting-the-risk-of-a-thousand-diseases","status":"publish","type":"post","link":"https:\/\/teknomers.com\/en\/an-ai-model-is-capable-of-predicting-the-risk-of-a-thousand-diseases\/","title":{"rendered":"An AI model is capable of predicting the risk of a thousand diseases."},"content":{"rendered":"\n<div class=\"ue-c-article__bar-footer\">\n<p>\n<span>Updated <\/span><time datetime=\"2025-09-17T15:16:29Z\"> Wednesday, 17 September 2025 &#8211; <span>17:16<\/span><\/time>\n<\/p>\n<\/div>\n<\/div>\n<div data-section=\"articleBody\">\n<p class=\"ue-c-article__paragraph\">What if an \u00a0AI\u00a0 could predict the likelihood of developing \u00a0diabetes, Alzheimer&#8217;s, or cardiovascular disease\u00a0 up to two decades in advance? This is the promise of \u00a0Delphi-2M\u00a0, an artificial intelligence model capable of forecasting the probability of over a thousand diseases based on an individual\u2019s health history.<\/p>\n<p class=\"ue-c-article__paragraph\">The work, published in <a rel=\"nofollow noopener\" href=\"https:\/\/www.nature.com\/articles\/s41586-025-09529-3\" target=\"_blank\"><i><strong>Nature<\/strong><\/i><\/a>, takes a significant step beyond current tools that typically focus on a handful of specific diseases. Delphi-2M \u00a0not only calculates immediate risks\u00a0 but also simulates health trajectories over a span of 20 years, paving the way for a new paradigm in preventive medicine. Specifically, this tool can predict the probability of developing over \u00a01,000 diseases\u00a0.<\/p>\n<p class=\"ue-c-article__paragraph\">The system was trained using clinical records from \u00a0400,000 individuals\u00a0 in the UK (sourced from the \u00a0UK Biobank\u00a0) and validated with data from nearly \u00a0two million citizens\u00a0 in Denmark. According to the authors, this is the first time a predictive model at this scale has been developed, capable of simultaneously managing \u00a0hundreds of pathologies and dynamically projecting them over time\u00a0.<\/p>\n<p class=\"ue-c-article__paragraph\">The \u00a0utility of such a tool\u00a0 is easy to envision: identifying a patient at high risk of heart attack before symptoms manifest, tailoring cancer screenings, or proactively planning the follow-up for neurodegenerative diseases.<\/p>\n<div class=\"ue-c-article__listing\">\n<p>To learn more<\/p>\n<div class=\"ue-c-article__listing-body\">\n<div class=\"ue-c-article__listing-item\">\n<article class=\"ue-c-cover-content ue-c-cover-content--media2of9-from-desktop ue-c-cover-content--s-from-mobile ue-c-cover-content--media-size2of9-from-desktop ue-c-cover-content--media-right-from-desktop has-byline has-image\">\n<div class=\"ue-c-cover-content__body\">\n<div class=\"ue-c-cover-content__media\">\n<figure class=\"ue-c-cover-content__figure\">\n<div class=\"ue-c-cover-content__img-container\">\n<picture><source type=\"image\/webp\"  data-><source type=\"image\/jpeg\"  data-><\/source><\/source><\/picture>\n<\/div>\n<\/figure>\n<\/div>\n<div class=\"ue-c-cover-content__main\">\n<header class=\"ue-c-cover-content__headline-group\">\n<span class=\"ue-c-cover-content__kicker\">Health.<\/span><\/p>\n<h2 class=\"ue-c-cover-content__headline\">A Brain-Computer System Quadruples Its Capacity Thanks to AI<\/h2>\n<\/header>\n<div class=\"ue-c-cover-content__list-inline\">\n<ul class=\"ue-c-cover-content__byline-list\">\n<li class=\"ue-c-cover-content__byline-item\"><span class=\"ue-c-cover-content__byline-name\"><span class=\"hidden-content\">Written by: <\/span>MARIA TOLDR\u00c0 <\/span><span class=\"ue-c-cover-content__byline-location\">Madrid<\/span><\/li>\n<\/ul>\n<\/div>\n<\/div>\n<\/article>\n<\/div>\n<\/div>\n<\/div>\n<p class=\"ue-c-article__paragraph\">&#8220;This research appears to be a significant step toward a scalable, interpretable, and, more importantly, ethically responsible form of predictive modeling in medicine,&#8221; says \u00a0Gustavo Sudre\u00a0, a professor of Genomic Neuroimaging and Artificial Intelligence at King&#8217;s College London, as reported by Science Media Center (<a rel=\"nofollow noopener\" href=\"https:\/\/www.smc.eu\/es-es\" target=\"_blank\">SMC<\/a>).<\/p>\n<p class=\"ue-c-article__paragraph\">&#8220;The clear demonstration of how explainable AI can be utilized for predictive modeling is \u00a0crucial\u00a0 if this technology is to be applied in clinical practice and suggests that it might be possible to \u00a0identify high-risk individuals requiring intervention\u00a0,&#8221; the expert continues.<\/p>\n<p class=\"ue-c-article__paragraph\">Moreover, Sudre emphasizes that Delphi-2M is not limited to current data alone. &#8220;It is encouraging to see that the model&#8217;s architecture has been deliberately designed to accommodate richer data types, such as \u00a0biomarkers\u00a0, \u00a0medical imaging\u00a0, or even \u00a0genomics\u00a0. With these future integrations, the platform is well positioned to evolve into a truly multimodal precision medicine tool,&#8221; he adds.<\/p>\n<h2 class=\"ue-c-article__subheadline\">How far can &#8220;AI Doctor&#8221; go?<\/h2>\n<p class=\"ue-c-article__paragraph\">The potential of Delphi-2M is enormous, but it is not without limitations. Like any AI system trained on population data, predictions may be influenced by \u00a0biases\u00a0 related to age, ethnicity, or the socioeconomic background of the patients included in the records.<\/p>\n<p class=\"ue-c-article__paragraph\">&#8220;The authors have developed an AI model capable of predicting diseases with accuracy and demonstrated that it works with data from the UK Biobank, as well as with data from nearly two million people in Denmark,&#8221; acknowledges \u00a0Peter Bannister\u00a0, a member of the Institution of Engineering and Technology. However, he warns: &#8220;There is still much work to be done to improve healthcare, as the authors themselves acknowledge that both datasets exhibit age, ethnic, and current health outcome biases.&#8221;<\/p>\n<p class=\"ue-c-article__paragraph\">For Bannister, the \u00a0immediate challenge\u00a0 is not just refining algorithms but ensuring that there is the necessary digital infrastructure and training for these technologies to reach everyone. &#8220;The challenge is to ensure that they are provided \u00a0equitably\u00a0, \u00a0regardless of socioeconomic background\u00a0, and that they do not exacerbate inequalities in treatment access,&#8221; he details.<\/p>\n<p class=\"ue-c-article__paragraph\"><strong>The research presents a profound shift in understanding medicine<\/strong>: moving from a \u00a0reactive\u00a0 practice\u2014centered on treating diseases once diagnosed\u2014to a \u00a0predictive\u00a0 and \u00a0preventive\u00a0 model, where the information of each patient allows for timely intervention and action.<\/p>\n<p class=\"ue-c-article__paragraph\">Does this mean one can self-diagnose by consulting a chat interface? Absolutely not. The authors themselves acknowledge that Delphi-2M \u00a0does not replace doctors\u00a0, but it can serve as an invaluable complement to health planning and clinical decision-making. It remains to be seen how it will be implemented in practice and under what ethical and legal conditions, but the path toward \u00a0more anticipatory medicine\u00a0 appears increasingly tangible.<\/p>\n<p><br \/>\n<br \/><a href=\"https:\/\/teknomers.com\/category\/general\/\" rel=\"dofollow\">General News &#8211; 2<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Updated Wednesday, 17 September 2025 &#8211; 17:16 What if an \u00a0AI\u00a0 could predict the likelihood of developing \u00a0diabetes, Alzheimer&#8217;s, or cardiovascular disease\u00a0 up to two decades in advance? This is the promise of \u00a0Delphi-2M\u00a0, an artificial intelligence model capable of forecasting the probability of over a thousand diseases based on an individual\u2019s health history. The [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":170464,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[36400],"tags":[36717,36729,26681],"class_list":["post-170463","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-health","tag-ciencia-y-salud","tag-ciencia-y-salud-salud","tag-salud"],"_links":{"self":[{"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/posts\/170463","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/comments?post=170463"}],"version-history":[{"count":0,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/posts\/170463\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/media\/170464"}],"wp:attachment":[{"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/media?parent=170463"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/categories?post=170463"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/teknomers.com\/en\/wp-json\/wp\/v2\/tags?post=170463"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}