Artificial Intelligence Tools for Aquatic Animal Disease Courses

Project: Research

Project Details

Description

This project aims to develop an AI-powered Chat Bot, tailored for aquatic animal veterinary medicine, which addresses the limitations of generic AI tools in specialized domains like aquaculture. Using large language models (LLMs) and a Retrieval-Augmented Generation (RAG) framework, we will design a Chat Bot which provides precise, reliable responses to aquatic animal diseases and their treatments based on verified, peer-reviewed resources. Equipped with aquaculture-specific terminology, clinical treatment calculators, and case-based reasoning, it will enable students to diagnose diseases, calculate drug dosages, and design actionable treatment plans for finfish, shrimp, and ornamental species. The development process will emphasize accuracy through a multi-stage validation process, including beta testing with domain experts and iterative feedback using Reinforcement Learning from Human Feedback (RLHF). A curated reference database from authoritative sources—scientific publications, government guidelines, textbooks, and topic specific course notes—will ensure content reliability. Collaborators, such as aquaculture specialists from CityUHK and the University of Malaysia Sabah, will test the tool to ensure applicability, including diverse regional practices. The tool will be integrated into several courses, including VM2106, VM4202, and VM4301, to act as a virtual tutor, enhancing student engagement with complex case studies through interactive, realtimefeedback. It will also permit students to learn how to integrate AI tools into everyday veterinary practice. Expected outcomes from this project include quantifiable improvements in clinical skills for 60+ undergraduate students in the first year of launching the tool, reduced medical errors via built-in calculators, and training for graduate students in AI development. The project will foster interdisciplinary collaboration through publications, conferences, and open-access deployment on CityUHK’s veterinary website and phone app. By merging the proposed AI innovation with veterinary education, this initiative will equip future practitioners with cutting-edge tools and thetraining to use them efficiently in practice, ensuring they enter the workforce prepared to address aquatic animal health challenges with technological proficiency.
Project number6000914
Grant typeTDG(CityU)
StatusActive
Effective start/end date16/06/25 → …

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.