Four-point bending tests have been used to investigate the flexural strength of orthopedic bone plates. This flexural strength can also be predicted by using the finite element method. However, calculating various metal bone plate designs’ flexural strength is time-consuming. This issue would become worse for the design optimization of bone plates. Thus, this study aimed to develop a fast-computing method that integrated finite element analysis and deep learning techniques to evaluate the plate's flexural strength. Three-dimensional parametric finite element models of a metal bone plate under a four-point bending load were developed using ANSYS Workbench. Six design variables of the bone plate were considered. The bone plate's implant stress was calculated and used as learning and verification data for developing the deep-learning model. The convolutional neural network (CNN) was used in this study. The finite element study showed that the implant stress of the bone plates could be evaluated. The CNN-based deep learning model could be successfully developed to predict implant stress quickly. The CNN-based deep learning model could promptly predict the mechanical performances of the bone plate designs. This deep learning model was expected to reduce the cost and time needed to design and optimize bone plates. Integrating finite element analysis with deep learning technique was a feasible and effective tool for predicting the flexural strength of the metal bone plate designs under a four-point bending load.