Can ChatGPT be used as an education assistant in the field of health sciences? Examining with the integration of meta-analysis and co-citation analysis

Özgür E. G., Bekiroğlu G. N.

HELIYON, cilt.11, 2025 (ESCI) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 11
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.heliyon.2025.e41925
  • Dergi Adı: HELIYON
  • Derginin Tarandığı İndeksler: Scopus, Emerging Sources Citation Index (ESCI), CAB Abstracts, Food Science & Technology Abstracts, Veterinary Science Database, Directory of Open Access Journals
  • Marmara Üniversitesi Adresli: Evet

Özet

Background: Meta-analysis studies are frequently included in the literature, but studies integrated

with co-citation analysis are very few. There is no study that evaluates the success of ChatGPT in

the field of health sciences, especially by integrating these two methods.

Objective: This study aims to reveal whether ChatGPT can be used as an educational assistant by

comparing the performance of students in exams in the field of health sciences with ChatGPT

through the integration of meta-analysis and co-citation analysis.

Methods: We searched Web of Science for articles until May 2024. The studies comparing students’

exam performances with ChatGPT 3.5 and 4.0 versions in the field of health sciences were

included in the meta-analysis. Co-citation analysis was performed for the references of the studies

included in the meta-analysis and the relationship between the studies and the references was

examined.

Results: It is seen that the exam performance of the students is better than ChatGPT 3.5 (OR =

3.173, 95 % CI (1.132–8.869). In the co-citation analysis, three clusters were obtained. It is seen

that the exam performances of ChatGPT 4.0 are better than the students (OR = 2.589, 95 % CI

(1.046–6.409). In the co-citation analysis obtained with the references of these four studies, two

clusters were identified. The most cited studies, namely Kung et al., Aidan et al., and Hopkins

et al., intersect in one cluster.

Conclusion: The results obtained with the integration of meta-analysis and co-citation analysis are

agree with the literature for both ChatGPT 3.5 and ChatGPT 4.0. In general, using co-citation

analysis and meta-analysis together, increases the depth and scope of the analysis. The results

obtained in these analyzes also show that the use of ChatGPT as an educational assistant in the

field of health sciences is increasing day by day.