Method for predicting GO disease risk in GD patient based on time sequence data

The invention provides a method for predicting a GO disease risk in a GD patient based on time sequence data. The method comprises the following steps: acquiring baseline data, a treatment prescription, clinical examination data and a face image of a target GD patient at a current time point; the baseline data, the treatment prescriptions, the clinical examination data and the face images are classified according to the numerical data, the category data and the picture data and are preprocessed respectively, and three sets of feature data are obtained; performing feature fusion on the three groups of feature data to obtain a feature vector of the current time point; the feature vector of the current time point and the feature vectors of all previous time points form sequence data according to a time sequence; and inputting the sequence data into a pre-trained GO disease risk prediction model, so as to determine the risk level of the target GD patient from the GO disease in the future according to the predicti