Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

When Pigs Get Sick: Multi-Agent AI for Swine Disease Detection

Tittaya Mairittha, Tanakon Sawanglok, Panuwit Raden, Sorrawit Treesuk

TL;DR

The paper addresses the challenge of limited veterinary resources hindering rapid swine disease surveillance. It proposes an AI-powered, multi-agent diagnostic platform that combines Retrieval-Augmented Generation (RAG), adaptive stage-wise symptom collection, and confidence-weighted fusion to produce accurate disease predictions and actionable guidance. The authors formalize an end-to-end framework with query classification, stage-wise inference, and an integrated recommendations pipeline, and validate it across ASF, PRRS, PED, and FMD, showing high classification accuracy and strong knowledge retrieval performance. The approach offers scalable, evidence-based decision support for veterinarians and animal health professionals, improving surveillance, animal welfare, and global food security.”

Abstract

Swine disease surveillance is critical to the sustainability of global agriculture, yet its effectiveness is frequently undermined by limited veterinary resources, delayed identification of cases, and variability in diagnostic accuracy. To overcome these barriers, we introduce a novel AI-powered, multi-agent diagnostic system that leverages Retrieval-Augmented Generation (RAG) to deliver timely, evidence-based disease detection and clinical guidance. By automatically classifying user inputs into either Knowledge Retrieval Queries or Symptom-Based Diagnostic Queries, the system ensures targeted information retrieval and facilitates precise diagnostic reasoning. An adaptive questioning protocol systematically collects relevant clinical signs, while a confidence-weighted decision fusion mechanism integrates multiple diagnostic hypotheses to generate robust disease predictions and treatment recommendations. Comprehensive evaluations encompassing query classification, disease diagnosis, and knowledge retrieval demonstrate that the system achieves high accuracy, rapid response times, and consistent reliability. By providing a scalable, AI-driven diagnostic framework, this approach enhances veterinary decision-making, advances sustainable livestock management practices, and contributes substantively to the realization of global food security.

When Pigs Get Sick: Multi-Agent AI for Swine Disease Detection

TL;DR

The paper addresses the challenge of limited veterinary resources hindering rapid swine disease surveillance. It proposes an AI-powered, multi-agent diagnostic platform that combines Retrieval-Augmented Generation (RAG), adaptive stage-wise symptom collection, and confidence-weighted fusion to produce accurate disease predictions and actionable guidance. The authors formalize an end-to-end framework with query classification, stage-wise inference, and an integrated recommendations pipeline, and validate it across ASF, PRRS, PED, and FMD, showing high classification accuracy and strong knowledge retrieval performance. The approach offers scalable, evidence-based decision support for veterinarians and animal health professionals, improving surveillance, animal welfare, and global food security.”

Abstract

Swine disease surveillance is critical to the sustainability of global agriculture, yet its effectiveness is frequently undermined by limited veterinary resources, delayed identification of cases, and variability in diagnostic accuracy. To overcome these barriers, we introduce a novel AI-powered, multi-agent diagnostic system that leverages Retrieval-Augmented Generation (RAG) to deliver timely, evidence-based disease detection and clinical guidance. By automatically classifying user inputs into either Knowledge Retrieval Queries or Symptom-Based Diagnostic Queries, the system ensures targeted information retrieval and facilitates precise diagnostic reasoning. An adaptive questioning protocol systematically collects relevant clinical signs, while a confidence-weighted decision fusion mechanism integrates multiple diagnostic hypotheses to generate robust disease predictions and treatment recommendations. Comprehensive evaluations encompassing query classification, disease diagnosis, and knowledge retrieval demonstrate that the system achieves high accuracy, rapid response times, and consistent reliability. By providing a scalable, AI-driven diagnostic framework, this approach enhances veterinary decision-making, advances sustainable livestock management practices, and contributes substantively to the realization of global food security.

Paper Structure

This paper contains 27 sections, 7 equations, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Query Classification
  5. Multi-Agent Disease Prediction
  6. Stage-Wise Symptom Collection
  7. State Transitions
  8. Confidence-Based Disease Prediction
  9. Recommendations
  10. Algorithmic Framework
  11. Integrated Recommendation Pipeline
  12. Experimental Setup
  13. Data Collection
  14. Evaluation Methodology
  15. Evaluation Metrics for Query Classification and Routing
  16. ...and 12 more sections

Figures (2)

  • Figure 1: Schematic representation of the multi-turn diagnostic conversation flow. This diagram illustrates how user queries transition from initial query classification to subsequent processing by specialized modules— including multi-agent disease prediction and RAG—ultimately leading to actionable veterinary recommendations.
  • Figure 2: Subfigure (a) illustrates the distribution of model confidence scores specifically for correct predictions, offering insights into the relative certainty of outputs across different models. Subfigure (b) presents the performance ratings distribution across key evaluation metrics, highlighting the model’s consistent and strong performance in accuracy, relevance, correctness, coherence, and expansiveness.