\u201cAI for cancer detection has great, great promise,\u201d Associate Counsel at TechFreedom Andy Jung told the DCNF. \u201cWe should keep human doctors in the diagnostic loop while continuing to study how AI performs in real-world medical settings and increasing training for physicians on how to use AI, so that they gain comfort and confidence using the tools.\u201d<\/p>\n
\u201cIn 2024, researchers conducted a randomized trial<\/a> with 50 physicians to test how access to GPT-4 affected their diagnostic performance,\u201d Jung added. \u201cThe researchers compared diagnostic reasoning between three groups: physicians using conventional resources, physicians using GPT-4, and the AI model acting entirely on its own. GPT-4, acting alone, scored the highest, with physicians [plus] AI scoring second, and physicians alone scoring lowest. Even when the physicians had assistance from GPT-4, they often incorrectly overruled the AI when it provided the correct diagnosis.\u201d<\/p>\n GPT-4 is an advanced<\/a> multimodal large language model (LLM) developed<\/a> by OpenAI. LLMs refer<\/a> to AI systems that can understand and generate human language by processing massive amounts of text data.<\/p>\n In October 2025, researchers at the University of Southern California (USC) Viterbi School of Engineering and the USC Dornsife College of Letters, Arts and Sciences announced<\/a> they had created a new AI algorithm intended to automate the detection of a few cancer cells among millions of normal blood cells in approximately 10 minutes.<\/p>\n A separate AI model from<\/a>\u00a0the Mayo Clinic can help detect pancreatic cancer on routine abdominal CT scans up to three years before clinical diagnosis. In 2026, about 67,530 individuals will be diagnosed with pancreatic cancer in the U.S., while roughly 52,740 people will die from it, according<\/a> to American Cancer Society estimates.<\/p>\n This photograph shows an x-ray on a screen, helped by artificial intelligence for medical imaging which indicates possible bone fractures and dislocations at the university hospital in Rennes, western France on September 26, 2023. (Photo by DAMIEN MEYER\/AFP via Getty Images)<\/p>\n \u201cSo, for example, and there have been some studies in the radiology literature, suggesting that AI could be superior to humans in detecting lesions on CT scans and MRIs [and] probably even mammograms \u2026 it\u2019s very common that all of us, we\u2019re human, so when we\u2019re looking over a very complicated image, especially if we\u2019re distracted, our eyes might pass right over a very subtle finding that AI wouldn\u2019t, because AI can\u2019t get distracted,\u201d Jeffrey Singer, a senior fellow at the CATO Institute and president emeritus and founder of Valley Surgical Clinics Ltd., told the DCNF. \u201cSo, the easiest way, when you\u2019re doing screening imaging studies, AI is gonna be very helpful, and [there is] already evidence to that effect.\u201d<\/p>\n \u201cAlso, just in terms of clinical workups, when people come in for getting blood tests done, and then their data, there\u2019s gonna be these platforms where you can enter lab test results, plus imaging, studies, plus any other pertinent data, and there\u2019s evidence that \u2026 the LLMs can think of things that a regular human doctor might not think of,\u201d Singer continued. \u201cAnd that\u2019s because, first of all, it\u2019s purely impossible for us to be aware of every single piece of literature out there every day. But these AI [programs] can do that.\u201d<\/p>\n Researchers at Washington University School of Medicine in St. Louis have developed<\/a> new technology that utilizes AI to analyze mammograms and boost the accuracy of predicting a woman\u2019s personalized five-year risk of developing breast cancer.<\/p>\n AI technology also has the potential to optimize radiation dosing, assist with surgical procedures and enable real-time adjustments to cancer treatment plans as needed, per<\/a>\u00a0the Cancer Research Institute (CRI). It can also streamline processes involved in researching, developing and bringing new cancer treatments or drugs to market, according to the CRI.<\/p>\n Though, one possible downside of using AI programs in the healthcare industry is that it can sometimes result in patient injury or other medical problems due to system errors, according<\/a> to the Brookings Institution.<\/p>\n Some Americans have begun relying on AI for medical advice. Recent research<\/a> from the West Health-Gallup Center on Healthcare in America shows that 25% of Americans have used an AI tool or chatbot when seeking health information or advice.\u00a0<\/p>\n The Trump administration has also promoted<\/a> the use of AI in healthcare. In December 2025, the Department of Health and Human Services issued<\/a> a new AI strategy<\/a>\u00a0aiming to fulfill the agency\u2019s \u201ccommitment to utilize leading technologies to enhance efficiency, foster American innovation, improve patient outcomes, and Make America Healthy Again.\u201d<\/p>\n All content created by the Daily Caller News Foundation, an independent and nonpartisan newswire service, is available without charge to any legitimate news publisher that can provide a large audience. All republished articles must include our logo, our reporter\u2019s byline and their DCNF affiliation. For any questions about our guidelines or partnering with us, please contact\u00a0licensing@dailycallernewsfoundation.org.<\/p>\n","protected":false},"excerpt":{"rendered":"Artificial intelligence is poised to disrupt how U.S. doctors detect and treat cancer, according to experts. AI technology…\n","protected":false},"author":2,"featured_media":635044,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[59],"tags":[97,252,253],"class_list":["post-635043","post","type-post","status-publish","format-standard","has-post-thumbnail","category-health-care","tag-health","tag-health-care","tag-healthcare"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/635043","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=635043"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/635043\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/635044"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=635043"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=635043"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=635043"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}![\"(Photo](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/05\/GettyImages-1689929351-scaled-e1778170978549.jpg\")
<\/p>\n