Predicting high-risk prognosis from diagnostic histories of adult disease patients via deep recurrent neural networks

It is a critical issue to predict the prognosis of adult disease patients due to the possibility of spreading to high-risk symptoms in medical fields. Most studies for predicting prognosis have used complex data from patients such as biomedical images, biomarkers, and pathological measurements. We demonstrate a language model-like method for predicting high-risk prognosis from diagnosis histories of patients using deep recurrent neural networks (RNNs), i.e., prognosis prediction using RNN (PP-RNN). The proposed PP-RNN uses multiple RNNs for learning from diagnosis code sequences of patients in order to predict occurrences of high-risk diseases. The use of RNNs allows the model to learn the status changes of patients considering time, thus enhancing prediction accuracy. We evaluate our method on real-world diagnosis data of over 67,000 adult disease patients recorded for 14 years. Experimental results show the proposed PP-RNN outperforms other standard classification models. In particular, our method provides competitive performance with respect to recall and F1-score on high-risk diseases compared to other models. Furthermore, we investigate the effects of the parameters on the performances.