An Evaluation of Artificial Intelligence Chatbots as Alternatives to Specialized Software in Teaching Bayesian Pharmacokinetic Analysis

Authors

• Reza Mehvar, Chapman UniversityFollow

Document Type

Article

Publication Date

5-15-2026

Abstract

Objective

To investigate the accuracy and reliability of artificial intelligence chatbots in estimating pharmacokinetic parameters from limited patient samples and population data for potential application in teaching Bayesian concepts.

Methods

Two plasma concentration–time data sets after a single intravenous dose, along with population values for volume of distribution (V) and elimination rate constant (k), were entered into free versions of ChatGPT and Gemini. Three prompts were engineered to assess and improve the accuracy and consistency of patient-only (based on plasma concentrations) and Bayesian (based on plasma concentrations and population data) estimates of V and k. To assess consistency, each prompt was analyzed 7 times on 3 separate occasions, resulting in 21 replicates per chatbot. The optimized prompt was then used to create a simulation assignment comprising 3 scenarios with varying levels of assay and/or population parameter variability.

Results

Initially, both chatbots produced inconsistent and sometimes inaccurate responses for patient-only and Bayesian estimates of V and k. Prompt engineering improved the estimates of the pharmacokinetic parameters for both chatbots. However, ChatGPT produced more accurate and consistent results for patient-only and Bayesian estimates with the optimized prompt. The simulation assignment with the optimized prompt revealed that the simulation scenarios accurately and reliably predicted the effects of changing the levels of assay and/or population variability on the Bayesian estimates of V and k.

Conclusion

Free versions of chatbots can serve as alternatives to specialized pharmacokinetic software, making advanced pharmacokinetic simulation tools, including those for Bayesian analysis, more accessible to pharmacy educators and students.

Comments

This article was originally published in American Journal of Pharmaceutical Education, volume 90, issue 7, in 2026. https://doi.org/10.1016/j.ajpe.2026.102003

Recommended Citation

Mehvar R. An evaluation of artificial intelligence chatbots as alternatives to specialized software in teaching Bayesian pharmacokinetic analysis. Am. J. Pharm. Educ. 2026;90(7):102003. https://doi.org/10.1016/j.ajpe.2026.102003

Copyright

The authors

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.