{"id":2279,"date":"2026-10-07T18:03:54","date_gmt":"2026-10-07T13:03:54","guid":{"rendered":"https:\/\/ipp-news.com\/?p=2279"},"modified":"2026-10-07T18:03:54","modified_gmt":"2026-10-07T13:03:54","slug":"ai-companies-run-virtual-drug-trials-aim-to-improve-success-of-human-studies","status":"publish","type":"post","link":"https:\/\/ipp-news.com\/?p=2279","title":{"rendered":"AI companies run virtual drug trials, aim to improve success of human studies"},"content":{"rendered":"
\n

Novartis\u2019 experimental drug for a rare type of muscular dystrophy was expected to be a winner, with the Swiss company\u2019s CEO predicting annual peak sales of $5 billion. When a late-stage trial missed its goal last month, shares fell 11%, erasing $30 billion in market value.<\/strong><\/p>\n

AI start-up BioinvestGPT was not surprised. In July, it ran a simulated trial to measure how virtual patients would respond to del-desiran and predicted an insignificant clinical benefit.<\/p>\n

It and other \u200bartificial intelligence companies say they are working with some drugmakers on virtual trials to boost the odds an experimental medicine will prove safe and effective when used by actual patients in an \u200cexpensive traditional clinical trial.<\/p>\n

The global biopharmaceutical industry spends some $140 billion a year on human clinical testing, but only around 12% of drug candidates are approved by regulators \u2014 a rate that has changed little in decades.<\/p>\n

AI firms say simulations are being used to identify which pharmaceutical programs are worth moving forward and to assess the value of acquisition targets. As AI tools get better at flagging clinical risks, they say unexpected trial failures may become less frequent.<\/p>\n

Human clinical trials typically start with small Phase 1 studies primarily to gauge safety, followed by \u200bmid-stage Phase 2 and the large Phase 3 trials required by regulators that also assess efficacy. The process takes years, compared with a month or less for some AI simulations.<\/p>\n

\u201cWe shouldn\u2019t only ask how to \u200brun trials faster. We should ask how to run fewer trials that are going to fail,\u201d said Francisco Beca, chief medical officer at QuantHealth, an AI clinical trial \u2060simulation platform headquartered in Tel Aviv.<\/p>\n

Investment in AI drug discovery more than doubled to $8.4 billion in 2025 compared to 2023, according to a recent report from McKinsey. It said spending is currently focused where the technology works best today, \u200bparticularly molecule design, rather than the industry\u2019s major bottlenecks, such as proving a drug will work as intended through lengthy trials.<\/p>\n

Pharma companies are \u201cdipping their toes\u201d into AI trial modelling, said McKinsey partner Alex Devereson. They are using different types of \u200bthe technology, internally or with partners, to do things like assess drug candidates before committing capital to a program, he said.<\/p>\n

US health regulators last week announced a set of initiatives aimed at speeding drug trials. If successful, the program could help create a path for predictive AI to be used in clinical development, a federal health official said.<\/p>\n

<\/a>Five out of six correct<\/h3>\n

Copenhagen-based BioinvestGPT in July shared with Reuters its detailed analyses of the likely outcome of several high-profile drug trials before the results were known and has so far \u200bbeen correct in five of six.<\/p>\n

They include the negative result for del-desiran, success for Moderna and Merck\u2019s melanoma vaccine, a weak clinical benefit for AstraZeneca and Ionis\u2019 heart drug Wainua, the first failed trial for Novo Nordisk\u2019s heart drug ziltivekimab, and success \u200bfor Vaxcyte\u2019s pneumococcal vaccine.<\/p>\n

The fundamental goal of the pharma industry is proof of a superior clinical benefit compared to the standard of care, said Bragi Lovetrue, who co-founded BioinvestGPT with his wife Idonae Lovetrue in 2024.<\/p>\n

The AI platform uses DNA sequencing to simulate \u200ca human body \u2060matching the eligibility criteria for a specific clinical trial. A virtual trial is then done using a model of the test drug.<\/p>\n

\u201cWe can pinpoint the reason why a drug is effective and safe, and in many cases, why not,\u201d Lovetrue said.<\/p>\n

The simulations are not always right. The predictive AI forecast positive results for Novartis\u2019 pelacarsen, which lowers blood levels of a cholesterol-carrier called lipoprotein(a). Novartis in September said the drug did not cut the risk of a major heart attack or stroke in patients with a genetic risk factor in a late-stage trial.<\/p>\n

A subsequent analysis showed \u201cwe got the mechanism wrong,\u201d by not accounting for genetically set variations in the size of the lipoprotein, Lovetrue said.<\/p>\n

QuantHealth, which uses real-world data \u200band AI to simulate patient-level responses to therapies, has published \u200bits simulations of ulcerative colitis and cholesterol drug trials.<\/p>\n

<\/a>Biogen, Takeda trials predicted to fail<\/h3>\n

BioinvestGPT has done predictions for a wide range of trials.<\/p>\n

For anticipated trial results expected before year-end, the AI company predicts failure for two Phase 3 trials of Biogen\u2019s in the most common type of lupus, as well as for Phase 2 studies of Japanese drugmaker Takeda\u2019s in Crohn\u2019s disease and ulcerative colitis.<\/p>\n

The AI model shows \u200bthat both drugs are \u201csuboptimal\u201d for those specific trial populations.<\/p>\n

Biogen\u2019s drug, which targets an immune cell receptor called BDCA2, is also being studied in a different type of lupus. Takeda filed recently for US approval of \u2060zasocitinib, which blocks an enzyme called tyrosine kinase 2, in plaque psoriasis and has a Phase 3 trial in psoriatic arthritis.<\/p>\n

Takeda research chief Andy Plump said TYK2 was identified as a target by analysing human genetics, while machine learning was used to optimise and \u201cpolish\u201d the structure of the daily pill.<\/p>\n

\u201cI have immense confidence in this mechanism,\u201d Plump said. \u201cI don\u2019t think we are near being able to use tools like AI to make definitive predictions.\u201d<\/p>\n

Diana Gallagher, Biogen\u2019s head of clinical development for multiple sclerosis, immunology \u2060, and Alzheimer\u2019s, said \u200bthe company uses \u201cevery tool available to us,\u201d including AI.<\/p>\n

She said only two biologic drugs have been approved for lupus, and AI algorithms that \u200brely on historical data could be prone to predicting a negative result.<\/p>\n

QuantHealth\u2019s Beca and other experts said human trials will always be necessary, but AI simulations can be valuable when assessing the potential of an experimental drug.<\/p>\n

\u201cIs it still ethical in 2026 to expose patients to a trial \u200bthat most likely will fail?\u201d he said. \u201cWith the advancement of this (AI) technology, come 2027, 2028, or 2029, probably the answer is going to be that it no longer is.\u201d<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Novartis\u2019 experimental drug for a rare type of muscular dystrophy was expected to be a winner, with the Swiss company\u2019s CEO predicting annual peak sales of $5 billion. When a late-stage trial missed its goal last month, shares fell 11%, erasing $30 billion in market value. AI start-up BioinvestGPT was not surprised. In July, it ran a simulated trial to measure how virtual patients would respond to del-desiran and predicted an insignificant clinical benefit. It and other \u200bartificial intelligence companies say they are working with some drugmakers on virtual trials…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[19],"tags":[],"class_list":["post-2279","post","type-post","status-publish","format-standard","hentry","category-english"],"gutentor_comment":0,"_links":{"self":[{"href":"https:\/\/ipp-news.com\/index.php?rest_route=\/wp\/v2\/posts\/2279","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ipp-news.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ipp-news.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ipp-news.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ipp-news.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2279"}],"version-history":[{"count":0,"href":"https:\/\/ipp-news.com\/index.php?rest_route=\/wp\/v2\/posts\/2279\/revisions"}],"wp:attachment":[{"href":"https:\/\/ipp-news.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ipp-news.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ipp-news.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}