{"id":256762,"date":"2025-12-29T20:37:13","date_gmt":"2025-12-29T20:37:13","guid":{"rendered":"https:\/\/www.europesays.com\/ie\/256762\/"},"modified":"2025-12-29T20:37:13","modified_gmt":"2025-12-29T20:37:13","slug":"new-ai-driven-tool-could-help-find-heart-disease-drugs-faster","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ie\/256762\/","title":{"rendered":"New AI-driven tool could help find heart disease drugs faster"},"content":{"rendered":"

<\/p>\n

\"Cardio<\/p>\n

<\/a><\/p>\n

image:\u00a0<\/p>\n

Visual representation of the\u00a0CardioKG. The image has been\u00a0tweaked with AI to make it look heart\u00a0shaped,\u00a0but it\u00a0is based on a real network. Credit: MRC Laboratory\u00a0of Medical Sciences<\/p>\n

<\/strong>
\n view more\u00a0<\/a><\/p>\n

Credit: MRC Laboratory of Medical Sciences<\/p>\n

Knowledge graphs\u00a0are a powerful tool for bringing together information from biological databases and linking what is already known about genes, diseases,\u00a0treatments,\u00a0molecular\u00a0pathways\u00a0and\u00a0symptoms in a structured network. Until now, they have lacked detailed, individual-level information about how the affected organ\u00a0actually looks\u00a0and functions.\u00a0\u00a0<\/p>\n

The latest research,\u00a0led by\u00a0postdoctoral researcher\u00a0Dr Khaled\u00a0Rjoob\u00a0and\u00a0group leader\u00a0Professor Declan O\u2019Regan\u00a0from the\u00a0Computational Cardiac Imaging Group\u00a0at the MRC Laboratory of Medical Sciences, has\u00a0advanced\u00a0this technology\u00a0by\u00a0adding imaging data to\u00a0a knowledge graph\u00a0for the first time.\u00a0CardioKG\u00a0provides\u00a0a detailed view of the heart\u2019s structure and function\u00a0which\u00a0dramatically improves the accuracy of predicting which genes are linked to disease and whether existing\u00a0drugs could\u00a0treat\u00a0them.\u00a0<\/p>\n

Capturing\u00a0heart\u00a0variation\u00a0\u00a0<\/strong><\/p>\n

To build\u00a0CardioKG, the team used heart-imaging data from 4,280\u00a0UK Biobank\u00a0participants\u00a0with atrial fibrillation, heart\u00a0failure\u00a0or heart attack, plus 5,304\u00a0healthy participants, capturing variation\u00a0in the structure and function of the heart. In total, over 200,000 image-based traits were generated and used to train the model.\u00a0The\u00a0team integrated\u00a0these\u00a0with\u00a0data from 18 diverse biological databases\u00a0and used artificial intelligence (AI)\u00a0to\u00a0predict\u00a0gene-disease associations and opportunities for drug repurposing.\u00a0\u00a0<\/p>\n

\u201cOne of the advantages\u00a0of knowledge graphs is that they\u00a0integrate information about genes, drugs and diseases,\u201d says\u00a0Declan, \u201cthis means\u00a0you have\u00a0more power to make discoveries\u00a0about new therapies.\u00a0We found that\u00a0including\u00a0heart\u00a0imaging\u00a0in the graph transformed\u00a0how well new genes and drugs could be\u00a0identified.\u201d\u00a0<\/p>\n

Predicting new drug opportunities\u00a0<\/strong><\/p>\n

The model\u00a0identified\u00a0a\u00a0list\u00a0of new\u00a0disease-associated\u00a0genes and\u00a0predicted\u00a0two drugs\u00a0to\u00a0treat\u00a0heart conditions; methotrexate,\u00a0a\u00a0rheumatoid\u00a0arthritis\u00a0drug, could\u00a0improve\u00a0heart failure\u00a0and\u00a0gliptins,\u00a0to treat\u00a0diabetes,\u00a0could be beneficial for atrial fibrillation.\u00a0The team also made a surprising\u00a0discovery that\u00a0caffeine, which makes the heart more excitable,\u00a0has a protective effect\u00a0in patients with atrial fibrillation\u00a0who\u00a0have\u00a0an irregular and fast pulse.\u00a0<\/p>\n

\u201cWhat\u2019s exciting is\u00a0there are\u00a0other\u00a0recent\u00a0studies\u00a0in the field which\u00a0support\u00a0our\u00a0preliminary findings,\u201d says Declan, \u201cthis highlights\u00a0the huge potential of knowledge graphs in uncovering\u00a0existing drugs that might be repurposed as new treatments.\u201d\u00a0<\/p>\n

Extending the technology to other\u00a0organs\u00a0<\/strong><\/p>\n

CardioKG\u00a0provides a proof-of-concept technology that can extend far beyond the heart.\u00a0Researchers\u00a0could\u00a0now develop\u00a0knowledge graphs that integrate imaging data\u00a0wherever\u00a0organ\u00a0imaging exists,\u00a0meaning\u00a0the same approach could be\u00a0applied to\u00a0brain\u00a0scans, to body-fat imaging, or to other organs and tissues to explore new therapeutic possibilities in areas such as dementia or obesity.\u00a0<\/p>\n

The ability of\u00a0these\u00a0knowledge graphs to\u00a0accurately and rapidly\u00a0generate lists of high-priority genes\u00a0for a range of diseases\u00a0would\u00a0provide pharmaceutical companies with a valuable starting point by\u00a0highlighting biological targets they can explore,\u00a0validate\u00a0and potentially develop into new therapies far more efficiently than traditional discovery methods.\u00a0<\/p>\n

\u201cBuilding on this work,\u00a0we will\u00a0extend the knowledge graph into a dynamic, patient-centred framework that captures real disease trajectories,\u201d says Khaled,\u00a0\u201cThis will open new possibilities for personalised treatment\u00a0and\u00a0predicting\u00a0when diseases are likely to develop.\u201d\u00a0<\/p>\n

This study was supported by the Medical Research Council, the British Heart Foundation, Bayer AG, and the National Institute for Health\u00a0and Care\u00a0Research (NIHR) Imperial College Biomedical Research Centre.\u00a0\u00a0\u00a0<\/p>\n

Alongside his role at the LMS, Declan is a British Heart Foundation Professor of Cardiovascular AI and Clinical Theme Lead for the British Heart Foundation Centre of Research Excellence within Imperial\u2019s National Heart and Lung Institute.\u00a0<\/p>\n

Article Title<\/p>\n

A multi-modal vision knowledge graph of cardiovascular disease<\/p>\n

Article Publication Date<\/p>\n

29-Dec-2025<\/p>\n

Disclaimer:<\/strong> AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.<\/p>\n","protected":false},"excerpt":{"rendered":"image:\u00a0 Visual representation of the\u00a0CardioKG. The image has been\u00a0tweaked with AI to make it look heart\u00a0shaped,\u00a0but it\u00a0is based…\n","protected":false},"author":2,"featured_media":256763,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[78],"tags":[18,135,19,17],"class_list":{"0":"post-256762","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-health","8":"tag-eire","9":"tag-health","10":"tag-ie","11":"tag-ireland"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@ie\/115804782336238318","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/256762","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/comments?post=256762"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/256762\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media\/256763"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media?parent=256762"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/categories?post=256762"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/tags?post=256762"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}