File(s) under permanent embargo
DeepCare: a deep dynamic memory model for predictive medicine
chapter
posted on 2016-04-12, 00:00 authored by Trang Thi Minh Pham, Truyen TranTruyen Tran, Quoc-Dinh Phung, Svetha VenkateshSvetha VenkateshPersonalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes. At the data level, DeepCare represents care episodes as vectors in space, models patient health state trajectories through explicit memory of historical records. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timed events by moderating the forgetting and consolidation of memory cells. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling, intervention recommendation, and future risk prediction. On two important cohorts with heavy social and economic burden -- diabetes and mental health -- the results show improved modeling and risk prediction accuracy.
History
Event
The 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD) 2016Title of book
Advances in knowledge discovery and data mining : 19th Pacific-Asia Conference, PAKDD 2015, Ho Chi Minh City, Vietnam, May 19-22, 2015, proceedingsVolume
9652Series
Lecture Notes in Computer ScienceChapter number
3Pagination
30 - 41Publisher
SpringerLocation
Auckland, New ZealandPlace of publication
New York, N.Y.Publisher DOI
Start date
2016-04-22End date
2016-04-19ISSN
0302-9743ISBN-13
9783319317533Language
engPublication classification
B Book chapter; B1 Book chapterCopyright notice
2016, Springer International Publishing SwitzerlandExtent
44Editor/Contributor(s)
J Bailey, L Khan, T Washio, G Dobbie, J Huang, R WangUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC