Fraga-Sastrías JM, Navarrini HJ, Silva-Brehuer M, Espejo-Gonzalez R, Olvera-Cortes HE, Rubio-Martínez R

Language: Spanish
References: 8
Page: 64-71
PDF size: 429.49 Kb.

ABSTRACT

Introduction: technological advances in the field of computing have been accelerated, particularly in recent years with the creation of artificial intelligence systems (Generative Pre-trained Transformers) capable of generating new information from massive datasets incorporated as part of their learning. Recently, the OpenAI's Chat-GPT 4 version has shown great ability to generate natural language and solve problems, even demonstrating outstanding results in medical knowledge exams. This study evaluates a simulator generated with Chat-GPT 4 capable of generating and conducting scenarios for the learning of soft skills. Material and methods: a GPT was configured using the commercial version of Chat-GPT 4 capable of generating scenarios for the practice of non-technical skills and providing feedback at the end of each scenario. Likewise, a scale was created and validated to assess the design, conduct of the scenario, relevance of the scenario, and feedback after it. After a snowball sampling, the simulator was tested, and a survey was administered to 64 users, who were also asked openly about the use given to the simulator and provided general comments. Results: according to the survey conducted, user satisfaction was very high, with positive responses exceeding 90% in practically all items. Likewise, positive comments were found in 75% of occasions, with areas of opportunity identified in 25% of the comments. The uses varied, including practice in communication, delivering bad news, empathy, patience, and overcoming communication barriers, among others. Conclusions: Chat-GPT is capable of creating and conducting scenarios for the practice and learning of non-technical skills with a high level of user satisfaction.

REFERENCES

1. Wójcik S, Rulkiewicz A, Pruszczyk P, Lisik W, Pobozy M, Domienik-Kar?owicz J. Beyond ChatGPT: what does GPT-4 add to healthcare? The dawn of a new era. Cardiol J. 2023; 30 (6): 1018-1025. doi: 10.5603/cj.97515.

2. Abd-Alrazaq A, AlSaad R, Alhuwail D, Ahmed A, Healy PM, Latifi S, et al. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023; 9: e48291. doi: 10.2196/48291.

3. Brin D, Sorin V, Vaid A, Soroush A, Glicksberg BS, Charney AW, et al. Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments. Sci Rep. 2013; 13 (1): 16492. doi: 10.1038/s41598-023-43436-9.

4. Nori H, King N, McKinney SM, Carignan D, Horvitz E. Capabilities of GPT-4 on medical challenge problems. arXiv. 2023. Available in: http://arxiv.org/abs/2303.13375

5. Roos J, Kasapovic A, Jansen T, Kaczmarczyk R Artificial intelligence in medical education: comparative analysis of ChatGPT, Bing, and medical students in Germany. JMIR Med Educ. 2023; 9: e46482. doi: 10.2196/46482.

6. Haruna-Cooper L, Rashid MA. GPT-4: the future of artificial intelligence in medical school assessments. Journal of the Royal Society of Medicine. 2023; 116 (6): 218-219. doi: 10.1177/01410768231181251.

7. Eysenbach G. The Role of ChatGPT, generative language models, and artificial intelligence in medical education: a conversation with ChatGPT and a call for papers. JMIR Med Educ. 2023; 9: e46885. doi: 10.2196/46885.

8. Safranek CW, Sidamon-Eristoff AE, Gilson A, Chartash D. The role of large language models in medical education: applications and implications. JMIR Med Educ. 2023; 9: e50945. doi: 10.2196/50945.