{"id":24690,"date":"2025-08-18T09:20:45","date_gmt":"2025-08-18T07:20:45","guid":{"rendered":"https:\/\/makingpharmaindustry.it\/non-categorizzato\/gpt-5-supera-gli-esperti-umani-in-medicina\/"},"modified":"2025-09-08T15:58:05","modified_gmt":"2025-09-08T13:58:05","slug":"gpt-5-supera-gli-esperti-umani-in-medicina","status":"publish","type":"post","link":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/","title":{"rendered":"GPT-5 outperforms human experts in medicine"},"content":{"rendered":"<p>On August 13, 2025, researchers at Emory University published a study on arXiv that made a strong impression on the scientific community.<a href=\"https:\/\/arxiv.org\/abs\/2508.08224\" target=\"_blank\" rel=\"noopener\"> Capabilities of GPT-5 on Multimodal Medical Reasoning <\/a>documents how GPT-5, without any specific training in the medical field, was able to tackle complex exams with a level of accuracy never seen before.<\/p>\n<p data-start=\"434\" data-end=\"737\">The breakthrough lies not only in the final score but in<strong data-start=\"434\" data-end=\"735\"> the model\u2019s ability to integrate heterogeneous information<\/strong>\u2014reports, clinical data, images\u2014and reconstruct a logical thread leading to coherent diagnoses and decisions. <strong data-start=\"434\" data-end=\"735\">Not an algorithm that merely \u201cremembers,\u201d but an assistant that reasons.<\/strong><\/p>\n<h2 data-start=\"78\" data-end=\"115\">Methodology \u2013 How it was tested<\/h2>\n<p>Per testare le capacit\u00e0 di GPT-5, i ricercatori hanno adottato un protocollo standardizzato che riduce al minimo i margini di manipolazione. Il modello ha lavorato in <strong>zero-shot chain-of-thought<\/strong>: nessun addestramento su casi simili, solo la richiesta di \u201cpensare passo dopo passo\u201d.<\/p>\n<p data-start=\"117\" data-end=\"378\">To assess GPT-5\u2019s capabilities, researchers adopted a standardized protocol designed to minimize any margin of manipulation. The model was evaluated in<strong data-start=\"117\" data-end=\"376\"> zero-shot chain-of-thought mode<\/strong>: no training on similar cases, only the prompt to \u201cthink step by step.\u201d<\/p>\n<p data-start=\"380\" data-end=\"435\">Well-established datasets in the field were used:<\/p>\n<ul>\n<li data-start=\"439\" data-end=\"500\"><strong data-start=\"439\" data-end=\"449\">MedQA,<\/strong> containing U.S. medical licensing exam questions<\/li>\n<li data-start=\"503\" data-end=\"567\"><strong data-start=\"503\" data-end=\"520\">MMLU-Medical,<\/strong> which assesses specialized medical knowledge<\/li>\n<li data-start=\"570\" data-end=\"657\"><strong data-start=\"570\" data-end=\"596\">USMLE self-assessment,<\/strong> practical tests from the three stages of medical licensing<\/li>\n<li data-start=\"660\" data-end=\"755\"><strong data-start=\"660\" data-end=\"675\">MedXpertQA,<\/strong> with more than 4,400 questions across 17 specialties, also in multimodal form<\/li>\n<li data-start=\"758\" data-end=\"803\"><strong data-start=\"758\" data-end=\"770\">VQA-RAD,<\/strong> focused on radiological images<\/li>\n<\/ul>\n<p data-start=\"805\" data-end=\"940\">This approach allows the model to be evaluated under conditions comparable to human peers and to earlier versions such as GPT-4o.<\/p>\n<h2 data-start=\"83\" data-end=\"120\">Results \u2013 Numbers that surprise<\/h2>\n<p data-start=\"122\" data-end=\"158\">The data speak for themselves:<\/p>\n<ul>\n<li data-start=\"162\" data-end=\"235\"><strong data-start=\"162\" data-end=\"175\">On MedQA,<\/strong> GPT-5 achieved 95.8% accuracy (+4.8% compared to GPT-4o).<\/li>\n<li data-start=\"238\" data-end=\"345\"><strong data-start=\"238\" data-end=\"271\">On the text-based MedXpertQA,<\/strong> the leap was striking: +26.3% in reasoning and +25.3% in comprehension.<\/li>\n<li data-start=\"348\" data-end=\"458\"><strong data-start=\"348\" data-end=\"365\">On the USMLE,<\/strong> the model scored an average of 95.2%, with Step 2\u2014the most clinically oriented\u2014up by 4.1%.<\/li>\n<li data-start=\"461\" data-end=\"600\"><strong data-start=\"461\" data-end=\"490\">On multimodal MedXpertQA,<\/strong> the most complex challenge, it outperformed human experts: +24.2% in reasoning and +29.4% in comprehension.<\/li>\n<\/ul>\n<p data-start=\"602\" data-end=\"935\">In one of the most compelling clinical cases, GPT-5 correctly diagnosed <strong data-start=\"602\" data-end=\"933\">an esophageal perforation (Boerhaave\u2019s syndrome)<\/strong>, identifying the clinical signs and recommending a Gastrografin exam as the first step. Not only did it get the diagnosis right, but it also clearly explained why the alternative options were inappropriate.<\/p>\n<h2 data-start=\"82\" data-end=\"129\">Beyond the numbers \u2013 What it really means<\/h2>\n<p data-start=\"131\" data-end=\"345\">The point is not that a model \u201cbeats\u201d a doctor on a test. It is that GPT-5 demonstrates multimodal reasoning skills that make it, at least in standardized simulations,<strong data-start=\"131\" data-end=\"343\"> more reliable than a human professional.<\/strong><\/p>\n<p data-start=\"347\" data-end=\"689\">But researchers remain cautious: these evaluations take place in controlled settings, with clean data and well-structured questions. Clinical reality is made of uncertainties\u2014patients who do not tell the whole story, imperfect images, emergencies where time is scarce. In those contexts, AI is not yet ready to replace human experience.<\/p>\n<h2 data-start=\"69\" data-end=\"108\">Ethical and regulatory challenges<\/h2>\n<p data-start=\"110\" data-end=\"202\">If a model outperforms physicians on paper, who authorizes it to step into the clinic?<\/p>\n<ul>\n<li data-start=\"206\" data-end=\"297\"><strong data-start=\"206\" data-end=\"231\">Clinical validation \u2013<\/strong> As with a drug, prospective and comparative studies are needed.<\/li>\n<li data-start=\"300\" data-end=\"410\"><strong data-start=\"300\" data-end=\"317\">Clear rules \u2013<\/strong> EMA and FDA are drafting guidelines, but a \u201csuperhuman\u201d AI makes acceleration unavoidable.<\/li>\n<li data-start=\"413\" data-end=\"503\"><strong data-start=\"413\" data-end=\"431\">Transparency \u2013<\/strong> GPT-5 may deliver results, but its internal reasoning remains opaque.<\/li>\n<li data-start=\"506\" data-end=\"584\"><strong data-start=\"506\" data-end=\"526\">Accountability \u2013<\/strong> If an algorithm misdiagnoses, who bears responsibility?<\/li>\n<\/ul>\n<p data-start=\"586\" data-end=\"727\">These questions concern not only developers but also pharmaceutical companies that choose to integrate such tools into their pipelines.<\/p>\n<h2 data-start=\"83\" data-end=\"133\">What changes for the pharmaceutical industry<\/h2>\n<p data-start=\"135\" data-end=\"182\">The potential for the sector is enormous:<\/p>\n<ul data-start=\"184\" data-end=\"759\">\n<li data-start=\"184\" data-end=\"309\">\n<p data-start=\"186\" data-end=\"309\"><strong data-start=\"186\" data-end=\"200\">Research \u2013<\/strong> GPT-5 can combine genomic, structural, and clinical data to identify promising new molecules more quickly.<\/p>\n<\/li>\n<li data-start=\"310\" data-end=\"475\">\n<p data-start=\"312\" data-end=\"475\"><strong data-start=\"312\" data-end=\"333\">Clinical trials \u2013<\/strong> Automating the analysis of radiological images or extracting data from thousands of medical records can cut timelines from months to hours.<\/p>\n<\/li>\n<li data-start=\"476\" data-end=\"615\">\n<p data-start=\"478\" data-end=\"615\"><strong data-start=\"478\" data-end=\"501\">Pharmacovigilance \u2013<\/strong> Cross-referencing medical reports, literature, and real-world data enables earlier detection of adverse events.<\/p>\n<\/li>\n<li data-start=\"616\" data-end=\"759\">\n<p data-start=\"618\" data-end=\"759\"><strong data-start=\"618\" data-end=\"642\">Digital companions \u2013<\/strong> Multimodal models capable of supporting chronic patients by interpreting symptoms and biometric data in real time.<\/p>\n<\/li>\n<\/ul>\n<p data-start=\"761\" data-end=\"992\">This is not \u201cindustrial science fiction\u201d: these are concrete applications that many companies are already exploring with earlier versions of GPT. GPT-5, with its multimodal reasoning capacity, can bring them to full maturity.<\/p>\n<h2 data-start=\"94\" data-end=\"162\">Conclusion \u2013 An assistant that forces us to rethink the future<\/h2>\n<p data-start=\"164\" data-end=\"456\">The Emory University study does not suggest that physicians are obsolete, but that\u2014for the first time\u2014<strong data-start=\"164\" data-end=\"454\">an AI model outperforms them in standardized tests<\/strong>. It is a powerful signal, one that compels both industry and regulators to address the issue not in abstract terms, but with urgency.<\/p>\n<p data-start=\"458\" data-end=\"715\">GPT-5 is not the end of medicine, but a new actor on stage. It is up to us to decide whether it becomes an ally capable of reducing errors, accelerating research, and improving patients\u2019 lives, or a tool left on the sidelines out of fear of its risks.<\/p>\n<p data-start=\"717\" data-end=\"806\">The real challenge is no longer technical. It is cultural, regulatory, and ethical.<\/p>\n<p><strong>Fonte<\/strong>: Wang S, Hu M, Li Q, Safari M, Yang X. <strong><em>Capabilities of GPT-5 on multimodal medical reasoning. arXiv<\/em> <\/strong>[Preprint]. 2025 [cited 2025 Aug 16]; Available from: <a href=\"https:\/\/arxiv.org\/abs\/2508.08224\" target=\"_blank\" rel=\"noopener\"><em>https:\/\/arxiv.org\/abs\/2508.08224<\/em><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tested on benchmarks such as MedQA, MedXpertQA, and the USMLE, GPT-5 shows a 26\u201329% improvement over GPT-4o and outperforms pre-licensed experts by up to 29% in multimodal tasks. With over 95% accuracy on MedQA and USMLE, the model demonstrates its ability to reason across text, structured data, and clinical images. For pharma, this opens unprecedented scenarios: faster clinical trials, automated analyses, and advanced pharmacovigilance. Ethical and regulatory questions, however, remain unresolved.<\/p>\n","protected":false},"author":33,"featured_media":24523,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[837,1101],"tags":[],"class_list":{"0":"post-24690","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"category-highlights-en"},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.2 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>GPT-5 outperforms human experts in medicine - MakingPharmaIndustry<\/title>\n<meta name=\"description\" content=\"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GPT-5 outperforms human experts in medicine - MakingPharmaIndustry\" \/>\n<meta property=\"og:description\" content=\"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry\" \/>\n<meta property=\"og:url\" content=\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\" \/>\n<meta property=\"og:site_name\" content=\"MakingPharmaIndustry\" \/>\n<meta property=\"article:published_time\" content=\"2025-08-18T07:20:45+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-08T13:58:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"800\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Cristiana Bernini\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Cristiana Bernini\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\"},\"author\":{\"name\":\"Cristiana Bernini\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a\"},\"headline\":\"GPT-5 outperforms human experts in medicine\",\"datePublished\":\"2025-08-18T07:20:45+00:00\",\"dateModified\":\"2025-09-08T13:58:05+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\"},\"wordCount\":810,\"image\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png\",\"articleSection\":[\"Artificial intelligence\",\"HIGHLIGHTS\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\",\"url\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\",\"name\":\"GPT-5 outperforms human experts in medicine - MakingPharmaIndustry\",\"isPartOf\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png\",\"datePublished\":\"2025-08-18T07:20:45+00:00\",\"dateModified\":\"2025-09-08T13:58:05+00:00\",\"author\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a\"},\"description\":\"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry\",\"breadcrumb\":{\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage\",\"url\":\"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png\",\"contentUrl\":\"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png\",\"width\":1200,\"height\":800},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/makingpharmaindustry.it\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GPT-5 outperforms human experts in medicine\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/#website\",\"url\":\"https:\/\/makingpharmaindustry.it\/en\/\",\"name\":\"MakingPharmaIndustry\",\"description\":\"Luogo di incontro\u00a0per approfondire e discutere le pi\u00f9 importanti tematiche del mondo Pharma, dalla ricerca e sviluppo al manufacturing, dal mercato al business\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/makingpharmaindustry.it\/en\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a\",\"name\":\"Cristiana Bernini\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g\",\"caption\":\"Cristiana Bernini\"},\"url\":\"https:\/\/makingpharmaindustry.it\/en\/author\/cristiana\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"GPT-5 outperforms human experts in medicine - MakingPharmaIndustry","description":"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/","og_locale":"en_US","og_type":"article","og_title":"GPT-5 outperforms human experts in medicine - MakingPharmaIndustry","og_description":"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry","og_url":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/","og_site_name":"MakingPharmaIndustry","article_published_time":"2025-08-18T07:20:45+00:00","article_modified_time":"2025-09-08T13:58:05+00:00","og_image":[{"width":1200,"height":800,"url":"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png","type":"image\/png"}],"author":"Cristiana Bernini","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Cristiana Bernini","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#article","isPartOf":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/"},"author":{"name":"Cristiana Bernini","@id":"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a"},"headline":"GPT-5 outperforms human experts in medicine","datePublished":"2025-08-18T07:20:45+00:00","dateModified":"2025-09-08T13:58:05+00:00","mainEntityOfPage":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/"},"wordCount":810,"image":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage"},"thumbnailUrl":"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png","articleSection":["Artificial intelligence","HIGHLIGHTS"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/","url":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/","name":"GPT-5 outperforms human experts in medicine - MakingPharmaIndustry","isPartOf":{"@id":"https:\/\/makingpharmaindustry.it\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage"},"image":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage"},"thumbnailUrl":"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png","datePublished":"2025-08-18T07:20:45+00:00","dateModified":"2025-09-08T13:58:05+00:00","author":{"@id":"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a"},"description":"GPT-5 outperforms human experts in medicine, opening a new frontier for diagnosis, research, and the pharmaceutical industry","breadcrumb":{"@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#primaryimage","url":"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png","contentUrl":"https:\/\/makingpharmaindustry.it\/wp-content\/uploads\/2025\/08\/Capabilities-of-GPT-5-on-Multimodal-Medical-Reasoning.png","width":1200,"height":800},{"@type":"BreadcrumbList","@id":"https:\/\/makingpharmaindustry.it\/en\/artificial-intelligence\/gpt-5-supera-gli-esperti-umani-in-medicina\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/makingpharmaindustry.it\/en\/"},{"@type":"ListItem","position":2,"name":"GPT-5 outperforms human experts in medicine"}]},{"@type":"WebSite","@id":"https:\/\/makingpharmaindustry.it\/en\/#website","url":"https:\/\/makingpharmaindustry.it\/en\/","name":"MakingPharmaIndustry","description":"Luogo di incontro\u00a0per approfondire e discutere le pi\u00f9 importanti tematiche del mondo Pharma, dalla ricerca e sviluppo al manufacturing, dal mercato al business","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/makingpharmaindustry.it\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/makingpharmaindustry.it\/en\/#\/schema\/person\/ee100eb37b0cb2cb5a5daee9bcd05a6a","name":"Cristiana Bernini","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2f72dff643e811e45f82ed89758985ef032d7e8554f8a49e99e00ff250a44397?s=96&d=mm&r=g","caption":"Cristiana Bernini"},"url":"https:\/\/makingpharmaindustry.it\/en\/author\/cristiana\/"}]}},"_links":{"self":[{"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/posts\/24690","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/users\/33"}],"replies":[{"embeddable":true,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/comments?post=24690"}],"version-history":[{"count":2,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/posts\/24690\/revisions"}],"predecessor-version":[{"id":24692,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/posts\/24690\/revisions\/24692"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/media\/24523"}],"wp:attachment":[{"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/media?parent=24690"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/categories?post=24690"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/makingpharmaindustry.it\/en\/wp-json\/wp\/v2\/tags?post=24690"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}