Latest YouTube Video

Monday, February 8, 2016

Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks. (arXiv:1602.02685v1 [cs.LG])

In clinical data sets we often find static information (e.g. gender of the patients, 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 that is specifically designed for the clinical domain and that combines static and dynamic information in order to predict future events. We work with a database collected in the Charit\'{e} Hospital in Berlin that contains all the 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, given 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, 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 performed an additional experiment using these models to predict next actions and found that for such use case 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.

Donate to arXiv



from cs.AI updates on arXiv.org http://ift.tt/1ScrW0p
via IFTTT

No comments: