Abstract
In order to increase our understanding of diseases, the relationship among diseases becomes popular research nowadays. Several previous works focused on finding the relationships between diseases with genomes. However, relationships between diseases are also affected by many factors such as gender, age, and even seasons. In this work, we divide patients into several groups based on their gender and age. After that, we find the relationships between diseases in the groups from patient records. For example, in a group of middle-aged men, we find the percentage of patients who got a disease after a specified disease in a time period. Association rule mining is adopted to find the relationships. In order to improve the precision of the results, we utilize the prevalence of diseases and distributions of diseases on gender, age, and time to filter the association rules. The experiment results which are evaluated by professionals show that our filtering method is effective. The relationship between diseases we found can be applied to many fields, such as health education for people and research materials for researchers.