Authors : Vasireddy Surya; Rooma Tyagi; Vineel Sai Kumar Rampally; Deepthi Gonala; Shirish Kumar Gonala

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/3s7yvnpt

Scribd : https://tinyurl.com/4wrckjdw

DOI : https://doi.org/10.38124/ijisrt/25apr1781

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : The pharmaceutical industry uses traditional training and evaluation approaches that often lack personalized learning, interactive training, and immediate performance assessment thus restricting their effectiveness in today’s fast- paced educational environments. The Solution implements an AI-based chatbot system that supports pharmaceutical training along with evaluation needs. The chatbot functions as an interactive learning assistant which enables students and trainees to participate in real-time dialogues while accessing pharma-related assignments along with quizzes that deliver instant personalized feedback for each user. It leverages a fine-tuned large language model LLaMA 2 which delivers context- specific accurate results for pharmaceutical inquiries including both unstructured questions and structured learning content. The system features three operational modes which enable users to interact through domain-specific questions i.e. Interactive Question & Answers (1), complete multiple-choice quizzes with automatic evaluation and scoring i.e. Quiz Mode (2) and generate questions for deeper learning and assessment. i.e. Assignment & Training Questionnaire Generator (3). To evaluate the solution effectiveness, Available open-source datasets used to fine-tune LLaMA model. The chatbot's performance was assessed through qualitative assessment and its ability to accurately interpret input and generate output. The AI solution delivers simplified knowledge distribution and assessment during remote training sessions while simultaneously reducing time requirements for evaluation tasks. Future improvements to this system might include support for multiple languages as well as real-time analytics integration and learning paths. The chatbot system provides users with assessment tools and evaluation criteria allowing users to monitor their learning growth at any time from any location. The system includes interactive training tools such as quizzes together with questionnaires and assignment prompts to get continuous user participation while reinforcing their knowledge acquisition. Through this intelligent system, the model not only delivers informative responses but also encourages self-assessment, making it a valuable tool for modern pharmaceutical training and education.

Keywords : Pharmaceutical Training, AI-Based Chatbot, Personalized Feedback, Interactive Learning, LLaMA 2 (Large Language Model Meta AI), Real-Time Assessment, Knowledge Distribution, Questionnaire Generator.

References :

1. Vasireddy Surya; Rooma Tyagi; Vineel Sai Kumar Rampally; Shirish Kumar Gonala. “Next-Gen Pharma Communication: Revolutionizing Doctor-Pharma Relationships Using AI-Driven Messaging & Insights.” Volume. 10 Issue.4, April-2025 International Journal of Innovative Science and Research Technology (IJISRT), 328-338, https://doi.org/10.38124/ijisrt/25apr027
2. L. Chen, P. Chen and Z. Lin, "Artificial Intelligence in Education: A Review," in IEEE Access, vol. 8, pp. 75264-75278, 2020, doi: 10.1109/ACCESS.2020.2988510.
3. Winkler, Rainer & Söllner, Matthias. (2018). Unleashing the Potential of Chatbots in Education: A State-Of-The-Art Analysis. Academy of Management Proceedings. 2018. 15903. 10.5465/AMBPP.2018.15903abstract.
4. Mithun Shivakoti and Narsaiah Shivakoti. Role of Artificial Intelligence in Personalized Learning at Higher Education Institutions. International Journal of Contemporary Research in Multidisciplinary. 2023: 2(6):89-92
5. Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). BLEU: a Method for Automatic Evaluation of Machine Translation. Proceedings of the 40th Annual Meeting on ACL, 311–318. https://doi.org/10.3115/1073083.1073135
6. Salvatore Giorgi, Kelsey Isman, Tingting Liu, Zachary Fried, João Sedoc, Brenda Curtis. (2024). Evaluating generative AI responses to real-world drug-related questions. https://doi.org/10.1016/j.psychres.2024.116058
7. Ghorashi, Nima & Ismail, Ahmed & Ghosh, Pritha & Sidawy, Anton & Javan, Ramin. (2023). AI-Powered Chatbots in Medical Education: Potential Applications and Implications. Cureus. 15. 10.7759/cureus.43271.
8. Chan Kai Siang & Zary Nabil. (2019). Applications and Challenges of Implementing Artificial Intelligence in Medical and Healthcare Education: An Integrative Review (Preprint). JMIR Medical Education. 5. 10.2196/13930.
9. Masters, K. (2019). Artificial intelligence in medical education. Medical Teacher, 41(9), 976–980. https://doi.org/10.1080/0142159X.2019.1595557
10. Kumar, Jeya Amantha. (2021). Educational chatbots for project-based learning: investigating learning outcomes for a team-based design course. RUSC. Universities and Knowledge Society Journal. 18. 10.1186/s41239-021-00302-w.
11. Cevasco, K.E., Morrison Brown, R.E., Woldeselassie, R. et al. Patient Engagement with Conversational Agents in Health Applications 2016–2022: A Systematic Review and Meta-Analysis. J Med Syst 48, 40 (2024). https://doi.org/10.1007/s10916-024-02059-x
12. Milne-Ives, Madison & de Cock, Caroline & Lim, Ernest & Shehadeh, Melissa & Pennington, Nick & Mole, Guy & Meinert, Edward. (2020). The effectiveness of artificial intelligence conversational agents in healthcare: a systematic review (Preprint). Journal of Medical Internet Research. 22. 10.2196/20346.