A novel approach for disease comorbidity prediction using weighted association rule mining

Abstract

Disease comorbidity prediction has gained the attention of many researchers during the past years. Bulk creation of clinical data in the form of electronic health records (EHRs) and biological data opened the door to explore disease associations and comorbidity patterns. This led to the development of analytical tools for the detection of disease comorbidities and analysis of their causal genetic source. Comorbidity prediction using statistical analyis, data mining and network analysis have made significant contributions in medical field. Combining multiscalar data proved to have enhanced performance in disease comorbidity prediction techniques. Here we present a novel approach based on weighted association rule mining for predicting disease comorbidities using clinical data and molecular data. Results demonstrated that the system outperformed existing systems in disease comorbidity prediction.