Customized static orthoses in rehabilitation clinics often cause side effects, such as discomfort and skin damage due to excessive local contact pressure. Currently, clinicians adjust orthoses to reduce high contact pressure based on subjective feedback from patients. However, the adjustment is inefficient and prone to variability due to the unknown contact pressure distribution as well as differences in discomfort due to pressure across patients. This paper proposed a new method to predict a threshold of contact pressure (pressure limit) associated with moderate discomfort at each critical spot under hand orthoses. A new pressure sensor skin with 13 sensing units was configured from FEA results of pressure distribution simulated with hand geometry data of six healthy participants. It was used to measure contact pressure under two types of customized orthoses for 40 patients with bone fractures. Their subjective perception of discomfort was also measured using a 6 scores discomfort scale. Based on these data, five critical spots were identified that correspond to high discomfort scores (>1) or high pressure magnitudes (>0.024 MPa). An artificial neural network was trained to predict contact pressure at each critical spot with orthosis type, gender, height, weight, discomfort scores and pressure measurements as input variables. The neural networks show satisfactory prediction accuracy with R2 values over 0.81 of regression between network outputs and measurements. This new method predicts a set of pressure limits at critical locations under the orthosis that the clinicians can use to make orthosis adjustment decisions.