Machine Learning-Based Multi-Class Disease Prediction for Cattle and Livestock Health Management

This paper focused on developing an automated cattle and livestock disease prediction system using machine learning. A dataset of 6,950 augmented veterinary records spanning 8 animal types, 120 breeds, and 139 disease classes was preprocessed using One-Hot Encoding and StandardScaler, and four classifiers were trained and compared. Random Forest achieved the highest accuracy of 98.42% and the highest precision, and was therefore selected as the production model. The trained model was deployed through a Flask web application supporting both single-animal diagnosis and bulk herd screening, with sub-second response times and a bulk throughput of roughly 44 animals per second. The field impact of the system lies in empowering handlers with ranked disease probabilities, confidence scores, and precise medication protocols — reducing mortality while curbing unnecessary antibiotic use through targeted alerts. Bulk prediction scales to thousand-head herds and produces audit-ready records for veterinary oversight, while role-based access preserves professional control alongside farmer autonomy. Future work will extend manual symptom entry into continuous vital-stream monitoring through low-cost wearable sensors on collars or ear tags, transmitting temperature, rumen pH, and activity data to live herd dashboards with anomaly alerts, potentially cutting time-to-detection from roughly 24 hours to under 6 hours. Packaging the prediction engine as an installable Progressive Web App with offline-capable service workers would improve reliability on the intermittent connections common in rural areas, and camera-based symptom capture could feed a lightweight image feature extractor alongside the existing Random Forest model. Containerising the Flask services, migrating from CSV to a centralised database with per-farm data sovereignty, and sharing anonymised aggregate disease trends would further support regional surveillance.

[1] L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. Available: https://doi.org/10.1023/A:1010933404324 [2] S. Narayanan, A. Ramachandran, S. N. Aakur, and A. Bagavathi, "Genome Sequence Classification for Animal Diagnostics with Graph Representations and Deep Neural Networks," arXiv preprint arXiv:2007.12791, 2020. Available: https://arxiv.org/abs/2007.12791 [3] C. Jewell and R. Brown, "Bayesian Data Assimilation Provides Rapid Decision Support for Vector-Borne Diseases," 2015. [4] K. J. Patra and C. Panda, "Lumpy Skin Disease Diagnosis in Animals: A Deep Learning Approach Using MobileNetV2," 2024. [5] E. Casella, M. C. Cantor, M. M. Woodrum Setser, S. Silvestri, and J. H. C. Costa, "A Machine Learning and Optimization Framework for the Early Diagnosis of Bovine Respiratory Disease," IEEE Access, vol. 11, pp. 71164–71179, 2023. doi: https://doi.org/10.1109/ACCESS.2023.3291348 [6] P. Cihan, Z. Aydin, and T. Yildirim, "AI-Aided Cardiovascular Disease Diagnosis in Cattle from Retinal Images: Machine Learning vs. Deep Learning Models," Computers and Electronics in Agriculture, vol. 226, Art. no. 109391, 2024. doi: https://doi.org/10.1016/j.compag.2024.109391 [7] S. Mehta and A. Bhalla, "Harnessing the Power of CNN and SVM for Robust Cattle Disease Classification," in Proc. 15th IEEE Int. Conf. Computing, Communication and Networking Technologies (ICCCNT), 2024. doi: https://doi.org/10.1109/ICCCNT61001.2024.10726198 [8] D. Karthikevan and V. Mekala, "Lumpy Skin Disease Prediction Using Machine Learning," in Proc. 2nd IEEE Int. Conf. Intelligent Data Communication Technologies and Internet of Things (IDCIoT), 2024, pp. 887–895. doi: https://doi.org/10.1109/IDCIoT59759.2024.10467939 [9] H. M. Prosser, E. M. Bortoluzzi, R. J. Valeris-Chacin, E. C. Baker, and M. A. Scott, "Application of Artificial Intelligence and Machine Learning in Bovine Respiratory Disease Prevention, Diagnosis, and Classification," American Journal of Veterinary Research, vol. 86, no. S1, 2025. doi: https://doi.org/10.2460/AJVR.24.10.0327 [10] L. Heinen, R. L. Larson, and B. J. White, "Disease Prediction in Cattle: A Mixed-Methods Review of Predictive Modeling Studies," Animals, vol. 15, no. 17, Art. no. 2481, 2025. doi: https://doi.org/10.3390/ani15172481