A generative framework for prediction and informative risk factor selection of bone diseases

With the rapid development of healthcare industry, the overwhelming amounts of electronic health records (EHRs) have been well documented and shared by healthcare institutions and practitioners. It is important to take advantage of EHR data to develop an effective disease risk management model that not only predicts the progression of the disease, but also provides a candidate list of informative risk factors (RFs) in order to prevent the disease. Although EHRs are valuable sources due to the comprehensive patient information, it is difficult to pinpoint the underlying causes of the disease in order to assess the risk of a patient in developing a target disease. Because of the entangled EHR data, it is also challenging to discriminate between patients suffering from the disease and without the disease for the purpose of selecting RFs that cause the disease. To tackle these challenges, we propose a disease memory (DM) framework which can extract the integrated features by modeling the relationships among RFs and more importantly between RFs and the target disease by establishing a deep graphical model with two types of labels. The variants of DM can model characteristics for patients with disease and without disease respectively via training deep networks with different samples. Experiments on a real bone disease data set show that the proposed framework can successfully predict the bone disease and select the informative RFs that are beneficial and useful to aid clinical decision support. Most of the selected RFs are validated by medical literature and some new RFs will attract interests in medical research. The stable and promising performance on evaluation metrics confirms the effectiveness of our model.