Poultry production is very essential across the world and helps to provide high nutrients and proteins to human beings through meat and eggs. Though the farmers can save money from the poultry as it needs only a limited amount of resources to feed the chicken, a heavy loss occurs in the poultry due to the fast spread of disease among the chicken that may not be controlled by humans. Recently many technologies have been developed to detect chicken disease, but the technologies faced certain issues such as increased time consumption, inefficient detection, and so on. To defeat the mentioned challenges, a proposed method named Grey wolf optimized Deep Convolutional Neural Network (GWO-Deep CNN) is designed to enrich the performance of research by detecting the disease accurately and further helps veterinarians to diagnose the disease properly, which reduces the death rate among the chickens in the poultry. The Deep CNN is utilized effectively to detect the disease accurately and classify the detected disease. Performance metrics utilized to analyze the performance of the GWO-Deep CNN are accuracy, sensitivity, and specificity, which attain 0.973, 0.983, and 0.965 respectively.