Large amount of Electronic Health Record (EHR) data have been collected over millions of patients over multiple years. The rich longitudinal EHR data documented the collective experiences of physicians including diagnosis, medication prescription and procedures. We argue it is possible now to leverage the EHR data to model how physicians behave, and we call our model Doctor AI. Towards this direction of modeling clinical bahavior of physicians, we develop a successful application of Recurrent Neural Networks (RNN) to jointly forecast the future disease diagnosis and medication prescription along with their timing. Unlike a traditional classification model where a single target is of interest, our model can assess entire history of patients and make continuous and multilabel prediction based on patients' historical data. We evaluate the performance of the proposed method on a large real-world EHR data over 250K patients over 8 years. We observe Doctor AI achieves up to 79% recall@30, significantly higher than several baselines.
View on arXiv