Download PDF
Appl Clin Inform 2024; 15(05): 1121-1129
DOI: 10.1055/a-2414-7790
Special Topic on Teaching and Training Future Health Informaticians

Exploring the Impact of GitHub Copilot on Health Informatics Education

Sanja Avramovic
1   Deprtment of Health Administration and Policy, College of Public Health, George Mason University, Fairfax, Virginia, United States
,
Ivan Avramovic
2   Deprtment of Computer Science, College of Engineering and Computing, George Mason University, Fairfax, Virginia, United States
,
Janusz Wojtusiak
1   Deprtment of Health Administration and Policy, College of Public Health, George Mason University, Fairfax, Virginia, United States
› Author Affiliations Funding None.
› Further Information
Also available at
    Permissions and Reprints

Abstract

Background The use of artificial intelligence-driven code completion tools, particularly the integration of GitHub Copilot with Visual Studio, has potential implications for Health Informatics education, particularly for students learning SQL and Python.

Objectives This study aims to evaluate the effectiveness of these tools in solving or assisting with the solution of problems found in Health Informatics coursework, ranging from simple to complex.

Methods The study assesses the performance of GitHub Copilot in generating code to solve programming problems normally given to students in introductory Health Informatics programming courses. Problem statements are provided to the tool; the response is assessed on correctness. The focus is on the impact of detailed explanations on the tool's effectiveness.

Results Findings reveal that GitHub Copilot can generate correct code for straightforward problems. The correctness and effectiveness of solutions decrease with problem complexity, and the tool struggles with the most challenging problems, although performance on complex problems improves with more detailed explanations.

Conclusion The study not only underscores the relevance of these tools to programming in Health Informatics education but also highlights the need for critical evaluation by students. It concludes with a call for educators to adapt swiftly to this rapidly evolving technology.

Keywords

GitHub copilot - visual studio - health informatics education - SQL - Python

Protection of Human and Animal Subjects

This study did not involve human subjects and therefore did not require approval from an Institutional Review Board or Ethics Committee.




Publication History

Received: 29 May 2024

Accepted: 11 September 2024

Accepted Manuscript online:
13 September 2024

Article published online:
25 December 2024

© 2024. Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany

 

  • References

  • 1 Puryear B, Sprint G. Github Copilot in the classroom: learning to code with AI assistance. J Comput Sci Coll 2022; 38 (01) 37-47
    PubMedSearch in Google Scholar
  • 2 Becker BA, Denny P, Finnie-Ansley J, Luxton-Reilly A, Prather J, Santos EA. Programming is hard-or at least it used to be: Educational opportunities and challenges of AI code generation. ACM Technical Symposium on Computer Science Education 2023; 54 (01) 500-506
    PubMedSearch in Google Scholar
  • 3 Dakhel AM, Majdinasab V, Nikanjam A, Khomh F, Desmarais MC, Jiang ZM. GitHub Copilot AI pair programmer: asset or liability?. J Syst Softw 2023; 203: 111734
    CrossrefPubMedSearch in Google Scholar
  • 4 Finnie-Ansley J, Denny P, Becker BA, Luxton-Reilly A, Prather J. The robots are coming: Exploring the implication of OpenAI Codex on introductory programming. Proceedings of the 24th Australasian Computing Education Conference; 2022:10–19
    PubMed
  • 5 Zhang B, Liang P, Zhou X, Ahmad A, Waseem M. Practices and challenges of using GitHub Copilot: An empirical study. Proceedings of the 35th International Conference on Software Engineering and Knowledge Management; 2023.
    PubMed
  • 6 Avramovic S, Avramovic I. Exploring the potential benefits and limitations of using AI text generation tools in health informatics education: an examination of ChatGPT's performance on assessments. J Health Adm Educ 2024
    PubMedSearch in Google Scholar
  • 7 Imai S. Is Github Copilot a substitute for human pair-programming? An empirical study. Proceedings of the 44th International Conference on Software Engineering. 2022: 319–321
    PubMed
  • 8 Bird C, Ford D, Zimmermann T. et al. Taking flight with Copilot: early insights and opportunities of AI-powered pair-programming tools. ACM Queue 2023; 20 (06) 35-57
    CrossrefPubMedSearch in Google Scholar