Jennifer Gotta, Quang Anh Le Hong, Vitali Koch, Leon D Gruenewald, Tobias Geyer, Simon S Martin, Jan-Erik Scholtz, Christian Booz, Daniel Pinto Dos Santos, Scherwin Mahmoudi, Katrin Eichler, Tatjana Gruber-Rouh, Renate Hammerstingl, Teodora Biciusca, Lisa Joy Juergens, Elena Höhne, Christoph Mader, Thomas J Vogl, Philipp Reschke
{"title":"医学生放射学考试中的大型语言模型(LLM):成绩与后果","authors":"Jennifer Gotta, Quang Anh Le Hong, Vitali Koch, Leon D Gruenewald, Tobias Geyer, Simon S Martin, Jan-Erik Scholtz, Christian Booz, Daniel Pinto Dos Santos, Scherwin Mahmoudi, Katrin Eichler, Tatjana Gruber-Rouh, Renate Hammerstingl, Teodora Biciusca, Lisa Joy Juergens, Elena Höhne, Christoph Mader, Thomas J Vogl, Philipp Reschke","doi":"10.1055/a-2437-2067","DOIUrl":null,"url":null,"abstract":"<p><p>The evolving field of medical education is being shaped by technological advancements, including the integration of Large Language Models (LLMs) like ChatGPT. These models could be invaluable resources for medical students, by simplifying complex concepts and enhancing interactive learning by providing personalized support. LLMs have shown impressive performance in professional examinations, even without specific domain training, making them particularly relevant in the medical field. This study aims to assess the performance of LLMs in radiology examinations for medical students, thereby shedding light on their current capabilities and implications.This study was conducted using 151 multiple-choice questions, which were used for radiology exams for medical students. The questions were categorized by type and topic and were then processed using OpenAI's GPT-3.5 and GPT- 4 via their API, or manually put into Perplexity AI with GPT-3.5 and Bing. LLM performance was evaluated overall, by question type and by topic.GPT-3.5 achieved a 67.6% overall accuracy on all 151 questions, while GPT-4 outperformed it significantly with an 88.1% overall accuracy (p<0.001). GPT-4 demonstrated superior performance in both lower-order and higher-order questions compared to GPT-3.5, Perplexity AI, and medical students, with GPT-4 particularly excelling in higher-order questions. All GPT models would have successfully passed the radiology exam for medical students at our university.In conclusion, our study highlights the potential of LLMs as accessible knowledge resources for medical students. GPT-4 performed well on lower-order as well as higher-order questions, making ChatGPT-4 a potentially very useful tool for reviewing radiology exam questions. Radiologists should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses. · ChatGPT demonstrated remarkable performance, achieving a passing grade on a radiology examination for medical students that did not include image questions.. · GPT-4 exhibits significantly improved performance compared to its predecessors GPT-3.5 and Perplexity AI with 88% of questions answered correctly.. · Radiologists as well as medical students should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses.. · Gotta J, Le Hong QA, Koch V et al. Large language models (LLMs) in radiology exams for medical students: Performance and consequences. Fortschr Röntgenstr 2024; DOI 10.1055/a-2437-2067.</p>","PeriodicalId":21490,"journal":{"name":"Rofo-fortschritte Auf Dem Gebiet Der Rontgenstrahlen Und Der Bildgebenden Verfahren","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Large language models (LLMs) in radiology exams for medical students: Performance and consequences.\",\"authors\":\"Jennifer Gotta, Quang Anh Le Hong, Vitali Koch, Leon D Gruenewald, Tobias Geyer, Simon S Martin, Jan-Erik Scholtz, Christian Booz, Daniel Pinto Dos Santos, Scherwin Mahmoudi, Katrin Eichler, Tatjana Gruber-Rouh, Renate Hammerstingl, Teodora Biciusca, Lisa Joy Juergens, Elena Höhne, Christoph Mader, Thomas J Vogl, Philipp Reschke\",\"doi\":\"10.1055/a-2437-2067\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The evolving field of medical education is being shaped by technological advancements, including the integration of Large Language Models (LLMs) like ChatGPT. These models could be invaluable resources for medical students, by simplifying complex concepts and enhancing interactive learning by providing personalized support. LLMs have shown impressive performance in professional examinations, even without specific domain training, making them particularly relevant in the medical field. This study aims to assess the performance of LLMs in radiology examinations for medical students, thereby shedding light on their current capabilities and implications.This study was conducted using 151 multiple-choice questions, which were used for radiology exams for medical students. The questions were categorized by type and topic and were then processed using OpenAI's GPT-3.5 and GPT- 4 via their API, or manually put into Perplexity AI with GPT-3.5 and Bing. LLM performance was evaluated overall, by question type and by topic.GPT-3.5 achieved a 67.6% overall accuracy on all 151 questions, while GPT-4 outperformed it significantly with an 88.1% overall accuracy (p<0.001). GPT-4 demonstrated superior performance in both lower-order and higher-order questions compared to GPT-3.5, Perplexity AI, and medical students, with GPT-4 particularly excelling in higher-order questions. All GPT models would have successfully passed the radiology exam for medical students at our university.In conclusion, our study highlights the potential of LLMs as accessible knowledge resources for medical students. GPT-4 performed well on lower-order as well as higher-order questions, making ChatGPT-4 a potentially very useful tool for reviewing radiology exam questions. Radiologists should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses. · ChatGPT demonstrated remarkable performance, achieving a passing grade on a radiology examination for medical students that did not include image questions.. · GPT-4 exhibits significantly improved performance compared to its predecessors GPT-3.5 and Perplexity AI with 88% of questions answered correctly.. · Radiologists as well as medical students should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses.. · Gotta J, Le Hong QA, Koch V et al. Large language models (LLMs) in radiology exams for medical students: Performance and consequences. Fortschr Röntgenstr 2024; DOI 10.1055/a-2437-2067.</p>\",\"PeriodicalId\":21490,\"journal\":{\"name\":\"Rofo-fortschritte Auf Dem Gebiet Der Rontgenstrahlen Und Der Bildgebenden Verfahren\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2024-11-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Rofo-fortschritte Auf Dem Gebiet Der Rontgenstrahlen Und Der Bildgebenden Verfahren\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1055/a-2437-2067\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Rofo-fortschritte Auf Dem Gebiet Der Rontgenstrahlen Und Der Bildgebenden Verfahren","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1055/a-2437-2067","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Large language models (LLMs) in radiology exams for medical students: Performance and consequences.
The evolving field of medical education is being shaped by technological advancements, including the integration of Large Language Models (LLMs) like ChatGPT. These models could be invaluable resources for medical students, by simplifying complex concepts and enhancing interactive learning by providing personalized support. LLMs have shown impressive performance in professional examinations, even without specific domain training, making them particularly relevant in the medical field. This study aims to assess the performance of LLMs in radiology examinations for medical students, thereby shedding light on their current capabilities and implications.This study was conducted using 151 multiple-choice questions, which were used for radiology exams for medical students. The questions were categorized by type and topic and were then processed using OpenAI's GPT-3.5 and GPT- 4 via their API, or manually put into Perplexity AI with GPT-3.5 and Bing. LLM performance was evaluated overall, by question type and by topic.GPT-3.5 achieved a 67.6% overall accuracy on all 151 questions, while GPT-4 outperformed it significantly with an 88.1% overall accuracy (p<0.001). GPT-4 demonstrated superior performance in both lower-order and higher-order questions compared to GPT-3.5, Perplexity AI, and medical students, with GPT-4 particularly excelling in higher-order questions. All GPT models would have successfully passed the radiology exam for medical students at our university.In conclusion, our study highlights the potential of LLMs as accessible knowledge resources for medical students. GPT-4 performed well on lower-order as well as higher-order questions, making ChatGPT-4 a potentially very useful tool for reviewing radiology exam questions. Radiologists should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses. · ChatGPT demonstrated remarkable performance, achieving a passing grade on a radiology examination for medical students that did not include image questions.. · GPT-4 exhibits significantly improved performance compared to its predecessors GPT-3.5 and Perplexity AI with 88% of questions answered correctly.. · Radiologists as well as medical students should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses.. · Gotta J, Le Hong QA, Koch V et al. Large language models (LLMs) in radiology exams for medical students: Performance and consequences. Fortschr Röntgenstr 2024; DOI 10.1055/a-2437-2067.
期刊介绍:
Die RöFo veröffentlicht Originalarbeiten, Übersichtsartikel und Fallberichte aus dem Bereich der Radiologie und den weiteren bildgebenden Verfahren in der Medizin. Es dürfen nur Arbeiten eingereicht werden, die noch nicht veröffentlicht sind und die auch nicht gleichzeitig einer anderen Zeitschrift zur Veröffentlichung angeboten wurden. Alle eingereichten Beiträge unterliegen einer sorgfältigen fachlichen Begutachtung.
Gegründet 1896 – nur knapp 1 Jahr nach der Entdeckung der Röntgenstrahlen durch C.W. Röntgen – blickt die RöFo auf über 100 Jahre Erfahrung als wichtigstes Publikationsmedium in der deutschsprachigen Radiologie zurück. Sie ist damit die älteste radiologische Fachzeitschrift und schafft es erfolgreich, lange Kontinuität mit dem Anspruch an wissenschaftliches Publizieren auf internationalem Niveau zu verbinden. Durch ihren zentralen Platz im Verlagsprogramm stellte die RöFo die Basis für das heute umfassende und erfolgreiche Radiologie-Medienangebot im Georg Thieme Verlag.
Besonders eng verbunden ist die RöFo mit der Geschichte der Röntgengesellschaften in Deutschland und Österreich. Sie ist offizielles Organ von DRG und ÖRG und die Mitglieder der Fachgesellschaften erhalten die Zeitschrift im Rahmen ihrer Mitgliedschaft. Mit ihrem wissenschaftlichen Kernteil und dem eigenen Mitteilungsteil der Fachgesellschaften bietet die RöFo Monat für Monat ein Forum für den Austausch von Inhalten und Botschaften der radiologischen Community im deutschsprachigen Raum.