A Deep Learning Approach to Predicting Diagnosis Code from Electronic Health Records

Electronic Health Record (EHR) is an umbrella term encompassing demographics and health information of a patient from many different sources in a digital format. Deep learning has been used on EHRs in many successful studies and there is great potential in future implementations. In this study, diagnosis classification of EHRs with Multi-layer Perceptron models are studied. Two MLPs with different architectures are constructed and run on both a modified version of the EHR dataset and the raw data. A Random Forest is used as baseline for comparison. The MLPs are not successful in beating the baseline, with the best-performing MLP having a classification accuracy of 48.1%, which is 13.7 percentage points lower than that of the baseline. The results indicate that when the dataset is small, this approach should not be chosen. However, the dataset is growing over time and thus there is potential for continued research in the future.