Assisted reproductive technology (ART) has become the most important means to overcome infertility. Among all of the ART methods, in vitro fertilization embryo transfer (IVF-ET) is one of the most important assisted reproductive technologies, but its successful rate is only about 30 ~ 50%.Others’ success rate like ICSI is not high as well. Therefore, some important personal physique information that decide the IVF and ART outcome needs to be further explored. How to effectively improve the success rate of ART is also a research hotspot in the field of assisted reproduction.

we use machine learning algorithm to explore a new method to predict the ART outcome by using personal qhysique data, and an intelligent assisted ART system model is constructed. The model with stable prediction performance and excellent generalization performance was constructed by random forest algorithm to predict the IVF and ART outcome. The sensitivity, specificity and accuracy were 0.71, 0.77 and 0.74 respectively. To a certain extent, the individual constitution can objectively determine the ART outcome.