A Hybrid Machine Learning Framework for Poultry Disease Prediction and Sustainable Organic Control in Precision Poultry Farming

The researchers created a hybrid machine learning method to predict poultry diseases based on farm management and environmental factors along with organic disease control methods that are sustainable. The researchers compared four machine learning techniques —Decision Trees, Naive Bayes, K-Nearest Neighbor and Random Forest —to see which technique would be best at making predictions regarding poultry disease. The experimental results indicated that the Random Forest approach was able to produce the most accurate predictions with an accuracy rate of 94% and an AUC (Area Under Curve) of .96. Results from cross-validation also showed the Random Forest approach was the most reliable in terms of consistency across different validations and the ability to produce stable results over the multiple validation tests. Environmental factors (temperature, humidity and moisture levels from litter) and vaccination status were found to be primary drivers for the incidence of poultry diseases through feature importance. This finding emphasizes the need for appropriate environmental management and bio-security methods to effectively manage poultry farms. The hybrid predictive framework model includes using predictive analytics with organic methods of managing disease; therefore it represents an integrated and data-based sustainable method of managing poultry health. Additionally, by decreasing dependence on antibiotics, and increasing use of disease prevention measures, this model supports the creation of long-term sustainable poultry production systems. The inclusion of machine learning models in combination with precision livestock technology may also enable poultry producers to develop an "intelligent" poultry health monitoring system that will be able to detect disease risk(s) in poultry in real time. The future research direction should be to expand the dataset utilized in this study by including additional data source(s), such as computer vision and/or sensor based monitoring systems, and development of mobile or cloud based decision support platform(s) that will provide poultry farmers with real-time disease prediction and management recommendations. In summary, the integration of machine learning prediction model(s) into poultry health management practices utilizing sustainable approaches is a promising method to improve poultry disease control, enhance poultry farm productivity, and ensure global food security.

Abubakar, A. A., Zira, R. A., Yahaya, A., & Dantata, S. A. (2025). Poultry disease detection using machine learning: A review. Journal of Scientific Development Research. https://doi.org/10.70382/hujsdr.v8i9.005 Benos, L., Tagarakis, A., Dolias, G., Berruto, R., Kateris, D., & Bochtis, D. (2021). Machine learning in agriculture: A comprehensive updated review. Sensors, 21(11), 3758. https://doi.org/10.3390/s21113758 Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. https://doi.org/10.1109/TIT.1967.1053964 Curti, P. D. F., Selli, A., Pinto, D. L., Merlos-Ruiz, A., Balieiro, J. C. C., & Ventura, R. V. (2023). Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: An overview. Animal Reproduction, 20(2), e20230077. https://doi.org/10.1590/1984-3143-AR2023-0077 Dunlop, M. W., Blackall, P. J., & Stuetz, R. M. (2016). Water activity of poultry litter: Relationship to moisture content during a grow-out. Journal of Environmental Management. https://doi.org/10.1016/j.jenvman.2016.02.036 Food and Agriculture Organization. (2013). Good practices for biosecurity in the pig sector (also applicable to poultry systems). FAO. Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90. https://doi.org/10.1016/j.compag.2018.02.016 Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674. https://doi.org/10.3390/s18082674 Liu, Y., Johar, M. G. M., & Haja Mydeen, A. I. (2023). Poultry disease early detection methods using deep learning technology. Indonesian Journal of Electrical Engineering and Computer Science, 32(3), 1712–1723. https://doi.org/10.11591/ijeecs.v32.i3.pp1712-1723