Warfarin Use: A Readability Comparison of Gemini and ChatGPT: Warfarin Use: A Readability Comparison of Gemini and ChatGPT

Ahmet Mert Aydemir

doi:10.5281/zenodo.17156371

Authors

Ahmet Mert Aydemir Elazığ Fethi Sekin City Hospital https://orcid.org/0009-0007-2232-0223

DOI:

https://doi.org/10.5281/zenodo.17156371

Keywords:

Artificial Intelligence, Gemini, ChatGPT, readability

Abstract

Background

Warfarin, an anticoagulant medication, is employed in the prevention and treatment of thromboembolic disorders. Given its narrow therapeutic window and substantial interactions with both diet and other medications, the substance necessitates personalized dosing and meticulous monitoring. The integration of artificial intelligence in the dosing of warfarin signifies a substantial advancement in the realm of personalized medicine. The utilization of advanced artificial intelligence models, such as ChatGPT and Gemini, holds promise in the development of coding templates for pharmacometric modeling.

Methods

ChatGPT and Gemini were queried with inquiries regarding warfarin, and the resulting responses were assessed based on various readability indices. The following indices are included: The following terms are used to describe the readability of a text: average reading level, automatic readability index, Flesch readability index, Flesch-Kincaid grade level, Coleman-Liau index, SMOG index, Linsear writing formula, and predicted readability formula. Subsequently, a statistical comparison was conducted between the results of these metrics.

Results

The majority of readability metrics (i.e., Average Reading Level Consensus, Automatic Readability Index, Flesch Readability Index, Flesch-Kincaid Grade Level, Coleman-Liau Index, and Predicted Readability Formula) revealed that texts generated by Gemini were statistically significantly more readable than OpenAI texts (p<0.001). The SMOG Index (p=0.075) and the Linear Writing Formula (p=0.104) exhibited no statistically significant discrepancy between the two models.

Conclusion

The findings of this study demonstrate that texts generated by Gemini exhibit superior readability in comparison to those produced by OpenAI.

References

1. Price, R. (2014). Drug focus on warfarin—an anticoagulant medication. Nursing and Residential Care, 16(1), 14–16. https://doi.org/10.12968/NREC.2014.16.1.14

2. Fiumara, K., & Goldhaber, S. Z. (2009). A Patient’s Guide to Taking Coumadin/Warfarin.Circulation,119(8).https://doi.org/10.1161/CIRCULATIONAHA.108.803957

3. Ma, Q. (2007). Development of oral anticoagulants. British Journal of Clinical Pharmacology, 64(3), 263–265. https://doi.org/10.1111/J.1365-2125.2007.02898.X

4. Umashankar, N., & Oommen, B. M. (2024). The role of warfarin in anticoagulation therapy: Current insight’s and clinical perspectives. Indian Journal of Pharmacy and Pharmacology, 11(4), 178–184. https://doi.org/10.18231/j.ijpp.2024.031

5. Kuang, Y., Liu, Y., Pei, Q., Ning, X., Zou, Y., Liu, L., Song, L., Guo, C., Sun, Y., Deng, K., Zou, C., Cao, D., Cui, Y., Wu, C., & Yang, G. (2022). Long Short-Term Memory Network for Development and Simulation of Warfarin Dosing Model Based on Time Series Anticoagulant Data. Frontiers in Cardiovascular Medicine, 9. https://doi.org/10.3389/fcvm.2022.881111

6. Parwati, F. A., Wiharja, K. R. S., & Kurniawan, I. (2024). Application of Graph Neural Network to Predict Drug-Drug Interactions on Warfarin based on Molecular Properties and Molecular Mechanism. 311–316. https://doi.org/10.1109/icodsa62899.2024.10652104

7. Shin, E., Yu, Y., Bies, R. R., & Ramanathan, M. (2024). Evaluation of ChatGPT and Gemini Large Language Models for Pharmacometrics with NONMEM. https://doi.org/10.21203/rs.3.rs-4189234/v1

8. Zhang, X., Gao, Y., Shao, Y., Wang, J., Li, Y., Li, S., & Han, M. (2024). Exploring the reform of pharmacology curriculum based on ChatGPT. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns-2024-2636

9. Zhang, X., Gao, Y., Shao, Y., Wang, J., Li, Y., Li, S., & Han, M. (2024). Exploring the reform of pharmacology curriculum based on ChatGPT. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns-2024-2636

10. Krumborg, J. R., Damkier, P., Ennis, Z. N., Henriksen, D. P., Lillevang-Johansen, M., Pedersen, S. A., & Bergmann, T. K. (2023). ChatGPT: First glance from a perspective of clinical pharmacology. Basic & Clinical Pharmacology & Toxicology, 133(1), 3–5. https://doi.org/10.1111/bcpt.13879

11. Patel, C. R., Pandya, S. K., & Sojitra, B. (2023). Perspectives of ChatGPT in Pharmacology Education, and Research in Health Care: A Narrative Review. Journal of Pharmacology and Pharmacotherapeutics. https://doi.org/10.1177/0976500x231210427

12. Alhur, A. (2024). Redefining Healthcare With Artificial Intelligence (AI): The Contributions of ChatGPT, Gemini, and Co-pilot. Cureus. https://doi.org/10.7759/cureus.57795

13. Umashankar, N., & Oommen, B. M. (2024). The role of warfarin in anticoagulation therapy: Current insight’s and clinical perspectives. Indian Journal of Pharmacy and Pharmacology, 11(4), 178–184. https://doi.org/10.18231/j.ijpp.2024.031

14. Umashankar, N., & Oommen, B. M. (2024). The role of warfarin in anticoagulation therapy: Current insight’s and clinical perspectives. Indian Journal of Pharmacy and Pharmacology, 11(4), 178–184. https://doi.org/10.18231/j.ijpp.2024.031

15. Izmozherova, N., Shambatov, M. A., Popov, A. A., Zhuk, D. E., & Solodchenko, V. A. (2024). Pharmacogenetics of warfarin: A literature review. https://doi.org/10.17816/cs631885

16. Shiferaw, M. S., Zheng, T., Winter, A., Mike, L. A., & Chan, L. (2024). Assessing the accuracy and quality of artificial intelligence (AI) chatbot-generated responses in making patient-specific drug-therapy and healthcare-related decisions. BMC Medical Informatics and Decision Making, 24(1). https://doi.org/10.1186/s12911-024-02824-5

17. Chowdhury, M. T., Khaled, F. I., Sultana, S., Rahman, M. W., Mandal, M., Ahmed, K., & Hoque, H. (2019). Validation of Pharmacogenetic Testing Before Initiation of Warfarin Therapy. University Heart Journal, 15(2), 74–78. https://doi.org/10.3329/UHJ.V15I2.42665

18. Parwati, F. A., Wiharja, K. R. S., & Kurniawan, I. (2024). Application of Graph Neural Network to Predict Drug-Drug Interactions on Warfarin based on Molecular Properties and Molecular Mechanism. 311–316. https://doi.org/10.1109/icodsa62899.2024.10652104

19. Armstrong, D. L., Paul, C., McGlaughlin, B., & Hill, D. M. (2024). Can artificial intelligence (AI) educate your patient? A study to assess overall readability and pharmacists’ perception of AI‐generated patient education materials. JACCP: Journal of the American College of Clinical Pharmacy. https://doi.org/10.1002/jac5.2006

20. (Nasra, M., Jaffri, R., Pavlin‐Premrl, D., Kok, H. K., Khabaza, A., Barras, C., Slater, L., Yazdabadi, A., Moore, J. M., Russell, J., Smith, P., Chandra, R. V., Brooks, M., Jhamb, A., Chong, W., Maingard, J., & Asadi, H. (2024). Can artificial intelligence improve patient educational material readability? A systematic review and narrative synthesis. Internal Medicine Journal. https://doi.org/10.1111/imj.16607

21. Adithya, S., Aggarwal, S., Sridhar, J., VS, K., John, V., & Singh, C. (2024). An Observational Study to Evaluate Readability and Reliability of AI-Generated Brochures for Emergency Medical Conditions. Cureus. https://doi.org/10.7759/cureus.68307

22. Tuan, A. W., Foley, D. J., Gupta, N., Chester-Paul, K., Bhasker, J., Pearson, C., Amarnani, A., Kraschnewski, J. L., & Shah, R. (2023). Using machine learning to improve the readability of hospital discharge instructions for heart failure. medRxiv. https://doi.org/10.1101/2023.06.18.23291568

23. Rashid, M. M., Atılgan, N., Dobres, J., Day, S., Penkova, V., Küçük, M., Clapp, S. R., & Sawyer, B. D. (2024). Humanizing AI in Education: A Readability Comparison of LLM and Human-Created Educational Content. Proceedings of the Human Factors and Ergonomics Society ... Annual Meeting. https://doi.org/10.1177/10711813241261689

24. Patel, N., Nagpal, P., Shah, T., Sharma, A., Malvi, S., & Lomas, D. (2023). Improving mathematics assessment readability: Do large language models help? Journal of Computer Assisted Learning, 39(3), 804–822. https://doi.org/10.1111/jcal.12776

Warfarin Use: A Readability Comparison of Gemini and ChatGPT