The rapid development of deep learning technology provides new methods and ideas for achieving the goal of assisting doctors in high-precision diagnosis. In this paper, we summarized the principles and characteristics of deep learning models that are commonly used in disease diagnosis, including convolutional neural networks, deep belief network, restricted Boltzmann machine and circulation neural network model. Then we introduced the application of deep learning technology in disease diagnosis of several typical diseases, such as lung cancer, breast cancer, and diabetic retinopathy. Finally, we proposed the future of deep learning considering the limitations of deep learning technology in disease diagnosis.