{"id":5239,"date":"2026-02-27T06:25:54","date_gmt":"2026-02-27T06:25:54","guid":{"rendered":"https:\/\/cognitionconferences.com\/artificialintelligence\/?post_type=speaker&#038;p=5239"},"modified":"2026-02-27T06:25:54","modified_gmt":"2026-02-27T06:25:54","slug":"henrik-stelling","status":"publish","type":"speaker","link":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/","title":{"rendered":"Henrik Stelling"},"content":{"rendered":"<p><strong>Abstract<\/strong><\/p>\n<p>Multimodal large language models (MLLMs) offer potential for automated fracture detection, yet their diagnostic stability under repeated inference remains underexplored. This study evaluates the diagnostic accuracy, stability, and intra-model consistency of four MLLMs in detecting hand fractures on plain radiographs.<\/p>\n<p>Methods: Hand radiographs of 65 adult patients with confirmed hand fractures (30 phalangeal, 30 metacarpal, 5 scaphoid) were evaluated by four models: GPT-5 Pro, Gemini 2.5 Pro, Claude Sonnet 4.5, and Mistral Medium 3.1. Each image was independently analyzed five times per model using identical zero-shot prompts (1300 total inferences). Diagnostic accuracy, inter-run reliability (Fleiss\u2019 \u03ba), case-level agreement profiles, and subgroup performance were assessed.<\/p>\n<p>Results: GPT-5 Pro achieved the highest accuracy (64.3%) and consistency (\u03ba = 0.71), followed by Gemini 2.5 Pro (56.9%, \u03ba = 0.57). Mistral Medium 3.1 exhibited high agreement (\u03ba = 0.88) despite low accuracy (38.5%), indicating systematic error. Claude Sonnet 4.5 showed low accuracy (33.8%) and consistency (\u03ba = 0.33), reflecting instability. Phalangeal fractures were reliably detected by top models; scaphoid fractures remained challenging.<\/p>\n<p>Conclusions: Diagnostic accuracy and consistency are distinct performance dimensions; high intra-model agreement does not imply correctness. MLLMs should be regarded as experimental diagnostic reasoning systems rather than reliable standalone tools for clinical fracture detection.<\/p>\n","protected":false},"featured_media":5240,"template":"","meta":{"_acf_changed":false},"schedule":[7],"speaker-category":[10],"class_list":["post-5239","speaker","type-speaker","status-publish","has-post-thumbnail","hentry","schedule-day-2","speaker-category-poster"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Henrik Stelling | Physician in Nuclear Medicine | Germany<\/title>\n<meta name=\"description\" content=\"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Henrik Stelling | Physician in Nuclear Medicine | Germany\" \/>\n<meta property=\"og:description\" content=\"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/\" \/>\n<meta property=\"og:site_name\" content=\"Cognition Conferences\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"502\" \/>\n\t<meta property=\"og:image:height\" content=\"335\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/\",\"url\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/\",\"name\":\"Henrik Stelling | Physician in Nuclear Medicine | Germany\",\"isPartOf\":{\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg\",\"datePublished\":\"2026-02-27T06:25:54+00:00\",\"description\":\"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.\",\"breadcrumb\":{\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage\",\"url\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg\",\"contentUrl\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg\",\"width\":502,\"height\":335},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Henrik Stelling\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/#website\",\"url\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/\",\"name\":\"Cognition Conferences\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/cognitionconferences.com\/artificialintelligence\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Henrik Stelling | Physician in Nuclear Medicine | Germany","description":"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.","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:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/","og_locale":"en_US","og_type":"article","og_title":"Henrik Stelling | Physician in Nuclear Medicine | Germany","og_description":"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.","og_url":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/","og_site_name":"Cognition Conferences","og_image":[{"width":502,"height":335,"url":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/","url":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/","name":"Henrik Stelling | Physician in Nuclear Medicine | Germany","isPartOf":{"@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/#website"},"primaryImageOfPage":{"@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage"},"image":{"@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage"},"thumbnailUrl":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg","datePublished":"2026-02-27T06:25:54+00:00","description":"Dr. Henrik Stelling is a physician-researcher specializing in the intersection of artificial intelligence and clinical medicine, with a particular focus on AI applications in medical imaging diagnostics and medical knowledge assessment. His research encompasses the systematic evaluation of large language models across European board examinations and the development of methodological frameworks for AI performance benchmarking in subspecialty medicine.Clinically, Dr. Stelling practices at the Praxen f\u00fcr Nuklearmedizin in Berlin, where he leads interdisciplinary image evaluation integrating nuclear medicine with musculoskeletal diagnostics. His clinical work centers on radiosynoviorthesis and the coordination of multimodal treatment pathways at the interface of nuclear medicine, orthopedic surgery, hand surgery, and rheumatology \u2014 bridging diagnostic imaging with interventional therapy across subspecialty boundaries.Dr. Stelling collaborates with multiple academic and clinical institutions, contributing to an emerging evidence base on AI capabilities in medical education and clinical decision support.","breadcrumb":{"@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#primaryimage","url":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg","contentUrl":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-content\/uploads\/2026\/02\/henrik.jpg","width":502,"height":335},{"@type":"BreadcrumbList","@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/speaker\/henrik-stelling\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/cognitionconferences.com\/artificialintelligence\/"},{"@type":"ListItem","position":2,"name":"Henrik Stelling"}]},{"@type":"WebSite","@id":"https:\/\/cognitionconferences.com\/artificialintelligence\/#website","url":"https:\/\/cognitionconferences.com\/artificialintelligence\/","name":"Cognition Conferences","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/cognitionconferences.com\/artificialintelligence\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/speaker\/5239","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/speaker"}],"about":[{"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/types\/speaker"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/media\/5240"}],"wp:attachment":[{"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/media?parent=5239"}],"wp:term":[{"taxonomy":"schedule","embeddable":true,"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/schedule?post=5239"},{"taxonomy":"speaker-category","embeddable":true,"href":"https:\/\/cognitionconferences.com\/artificialintelligence\/wp-json\/wp\/v2\/speaker-category?post=5239"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}