Deakin University
Browse

File(s) under permanent embargo

Deepr: A Convolutional Net for Medical Records

Version 2 2024-06-04, 12:43
Version 1 2017-03-29, 07:15
journal contribution
posted on 2024-06-04, 12:43 authored by Phuoc NguyenPhuoc Nguyen, Truyen TranTruyen Tran, N Wickramasinghe, Svetha VenkateshSvetha Venkatesh
Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that learns to extract features from medical records and predicts future risk automatically. Deepr transforms a record into a sequence of discrete elements separated by coded time gaps and hospital transfers. On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk. Deepr permits transparent inspection and visualization of its inner working. We validate Deepr on hospital data to predict unplanned readmission after discharge. Deepr achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.

History

Journal

IEEE Journal of Biomedical and Health Informatics

Volume

21

Pagination

22-30

Location

United States

ISSN

2168-2194

eISSN

2168-2208

Language

English

Publication classification

C Journal article, C1 Refereed article in a scholarly journal

Copyright notice

2016, IEEE

Issue

1

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC