Mixed reality systems are often reported to cause user discomfort. Therefore, it is important to estimate the timing at which discomfort occurs and to consider ways to reduce or avoid it. The purpose of this study is to estimate the discomfort of the user while using the MR system. Psychological and physiological indicators during task were measured using the MR system, and a deep learning model was constructed to estimate psychological indicators from physiological indicators. As a result of 4-fold cross-validation, the average F1 value of each discomfort score was 0.602 for 1, 0.555 for 2, and 0.290 for 3. This result suggests that mild discomfort can be detected with a certain degree of accuracy.