With the development of healthcare 4.0, there has been an explosion in the amount of data such as image, medical text, physiological signals, lab tests, etc. Among them, medical records provide a complete picture of the associated clinical events. However, the processing of medical texts is difficult because they are structurally free, diverse in style, and have subjective factors. Assigning metadata codes from the International Classification of Diseases (ICD) presents a standardized way of indicating diagnoses and procedures, so it becomes a mandatory process for understanding medical records to make better clinical and financial decisions. Such a manual encoding task is time-consuming, error-prone and expensive. In this paper, we proposed a deep learning approach and a medical topic mining method to automatically predict ICD codes from text-free medical records. The result of the F1 score on Medical Information Mart for Intensive Care (MIMIC-III) dataset increases by 5% over the state of art. It also suitable for multiple ICD versions and languages. For the specific disease, atrial fibrillation, the F1 score is up to 96% and 93.3% using in-house ICD-10 datasets and MIMIC-III datasets, respectively. We developed an Artificial Intelligence based coding system, which can greatly improve the efficiency and accuracy of human coders, and meanwhile accelerate the secondary use for clinical informatics.