The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The other is a structured dataset on primary hypertension. One is a plain text data set indexed by medical experts. There are two data sets used in the experiments. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM.Ī two-step model is applied in our study. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities.
0 kommentar(er)
