Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks

By Cristóbal Esteban, Oliver Staeck, Stephan Baier, Yinchong Yang, Volker Tresp. 2016

171 citations recorded by the source corpus.

In clinical data sets we often find static information (e.g. patient gender, blood type, etc.) combined with sequences of data that are recorded during multiple hospital visits (e.g. medications prescribed, tests performed, etc.). Recurrent Neural Networks (RNNs) have proven to be very successful for modelling sequences of data in many areas of Machine Learning. In this work we present an approach based on RNNs, specifically designed for the clinical domain, that combines static and dynamic information in order to predict future events. We work with a database collected in the Charité Hospital in Berlin that contains complete information concerning patients that underwent a kidney transplantation. After the transplantation three main endpoints can occur: rejection of the kidney, loss of the kidney and death of the patient. Our goal is to predict, based on information recorded in the Electronic Health Record of each patient, whether any of those endpoints will occur within the next six or twelve months after each visit to the clinic. We compared different types of RNNs that we developed for this work, with a model based on a Feedforward Neural Network and a Logistic Regression model. We found that the RNN that we developed based on Gated Recurrent Units provides the best performance for this task. We also used the same models for a second task, i.e., next event prediction, and found that here the model based on a Feedforward Neural Network outperformed the other models. Our hypothesis is that long-term dependencies are not as relevant in this task.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (2016, methodology): “Recently, recurrent neural networks (RNN) have been successfully applied in modeling sequential EHR data to predict diagnoses [30] and disease progression [11, 14].”
Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review (2018, background): “The goal of these models is to embed terminologies from different domains into the same space to discover the relations among them (eg., NA [33, 35, 98, 89, 56, 98] [34] relationships between diseases and drugs).”
Patient Subtyping via Time-Aware LSTM Networks (2017, methodology): “For instance, in [13], authors focused on patients suering from kidney failure.”
Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (2017, unknown): “[40], [47], [51], [59] [19], [34], [46]”
Explaining Therapy Predictions with Layer-Wise Relevance Propagation in Neural Networks (2018, background): “15, which represents all relevant information on patient i up to time step Ti [15].”