Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
This work addresses personalized medical services like diagnosis and treatment for patients, but it is incremental as it builds on existing deep learning and GP methods.
The paper tackles personalized healthcare prediction from time-series EHR data by combining a deep neural network for global trends and Gaussian Processes for individual variability, showing practical advantages over standard RNN models.
We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention. Our proposed framework targets at making personalized and reliable predictions from time-series data, such as Electronic Health Records (EHR), by modeling two complementary components: i) a shared component that captures global trend across diverse patients and ii) a patient-specific component that models idiosyncratic variability for each patient. To this end, we propose a composite model of a deep neural network to learn complex global trends from the large number of patients, and Gaussian Processes (GP) to probabilistically model individual time-series given relatively small number of visits per patient. We evaluate our model on diverse and heterogeneous tasks from EHR datasets and show practical advantages over standard time-series deep models such as pure Recurrent Neural Network (RNN).