ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study

被引:45
作者
Scherr, Riley [1 ,3 ]
Halaseh, Faris F. [1 ]
Spina, Aidin [1 ]
Andalib, Saman [1 ]
Rivera, Ronald [2 ]
机构
[1] Univ Calif Irvine, Irvine Sch Med, Irvine, CA USA
[2] Univ Calif Irvine, Irvine Sch Med, Dept Emergency Med, Irvine, CA USA
[3] Univ Calif Irvine, Irvine Sch Med, 1001 Hlth Sci Rd, Irvine, CA 92617 USA
关键词
ChatGPT; medical school simulations; preclinical curriculum; artificial intelligence; AI; AI in medical education; medical education; simulation; generative; curriculum; clinical education; simulations;
D O I
10.2196/49877
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
Background: The transition to clinical clerkships can be difficult for medical students, as it requires the synthesis and application of preclinical information into diagnostic and therapeutic decisions. ChatGPT-a generative language model with many medical applications due to its creativity, memory, and accuracy-can help students in this transition. Objective: This paper models ChatGPT 3.5's ability to perform interactive clinical simulations and shows this tool's benefit to medical education. Methods: Simulation starting prompts were refined using ChatGPT 3.5 in Google Chrome. Starting prompts were selected based on assessment format, stepwise progression of simulation events and questions, free-response question type, responsiveness to user inputs, postscenario feedback, and medical accuracy of the feedback. The chosen scenarios were advanced cardiac life support and medical intensive care (for sepsis and pneumonia). Results: Two starting prompts were chosen. Prompt 1 was developed through 3 test simulations and used successfully in 2 simulations. Prompt 2 was developed through 10 additional test simulations and used successfully in 1 simulation. Conclusions: ChatGPT is capable of creating simulations for early clinical education. These simulations let students practice novel parts of the clinical curriculum, such as forming independent diagnostic and therapeutic impressions over an entire patient encounter. Furthermore, the simulations can adapt to user inputs in a way that replicates real life more accurately than premade question bank clinical vignettes. Finally, ChatGPT can create potentially unlimited free simulations with specific feedback, which increases access for medical students with lower socioeconomic status and underresourced medical schools. However, no tool is perfect, and ChatGPT is no exception; there are concerns about simulation accuracy and replicability that need to be addressed to further optimize ChatGPT's performance as an educational resource.
引用
收藏
页数:12
相关论文
共 21 条
[1]  
[Anonymous], 2012, Curriculum reports
[2]  
[Anonymous], Adult cardiac arrest algorithm
[3]  
[Anonymous], USMLE Step 3 CCS case simulator
[4]   High Rates of Fabricated and Inaccurate References in ChatGPT-Generated Medical Content [J].
Bhattacharyya, Mehul ;
Miller, Valerie M. ;
Bhattacharyya, Debjani ;
Miller, Larry E. .
CUREUS JOURNAL OF MEDICAL SCIENCE, 2023, 15 (05)
[5]  
Brown TB, 2020, ADV NEUR IN, V33
[6]   Medical education today: all that glitters is not gold [J].
Buja, L. Maximilian .
BMC MEDICAL EDUCATION, 2019, 19 (1)
[7]  
ChatGPT, OpenAI
[8]   The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education: A Conversation With ChatGPT and a Call for Papers [J].
Eysenbach, Gunther .
JMIR MEDICAL EDUCATION, 2023, 9
[9]   Assessing the accuracy of ChatGPT references in head and neck and ENT disciplines [J].
Frosolini, Andrea ;
Franz, Leonardo ;
Benedetti, Simone ;
Vaira, Luigi Angelo ;
de Filippis, Cosimo ;
Gennaro, Paolo ;
Marioni, Gino ;
Gabriele, Guido .
EUROPEAN ARCHIVES OF OTO-RHINO-LARYNGOLOGY, 2023, 280 (11) :5129-5133
[10]   AI-Generated Medical Advice-GPT and Beyond [J].
Haupt, Claudia E. ;
Marks, Mason .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2023, 329 (16) :1349-1350