. Author manuscript; available in PMC: 2019 Sep 1.

Published in final edited form as: IEEE J Biomed Health Inform. 2017 Oct 27;22(5):1589–1604. doi: 10.1109/JBHI.2017.2767063

Table III.

Summary of EHR deep learning tasks.

Task	Subtasks	Input Data	Models	References
Information Extraction	(1) Single Concept Extraction	Clinical Notes	LSTM, Bi-LSTM, GRU, CNN	[15], [16], [34]
	(2) Temporal Event Extraction		RNN + Word Embedding	[35]
	(3) Relation Extraction		AE	[36]
	(4) Abbreviation Expansion		Custom Word Embedding	[37]
Representation Learning	(1) Concept Representation	Medical Codes	RBM, Skip-gram, AE, LSTM	[23], [36]
Representation Learning	(2) Patient Representation	Medical Codes	RBM, Skip-gram, GRU, CNN, AE	[14], [18]–[23], [36], [38]–[40]
Outcome Prediction	(1) Static Prediction	Mixed	AE, LSTM, RBM, DBN	[14], [18], [23], [41]–[43]
Outcome Prediction	(2) Temporal Prediction	Mixed	LSTM	[19]–[21], [38], [44]–[48]
Phenotyping	(1) New Phenotype Discovery	Mixed	AE, LSTM, RBM, DBN	[14], [40], [44], [49], [50]
Phenotyping	(2) Improving Existing Definitions	Mixed	LSTM	[45], [51]
De-identification	Clinical text de-identification	Clinical Notes	Bi-LSTM, RNN + Word Embedding	[52], [53]