Stabilizing High-Dimensional Prediction Models Using Feature Graphs

被引：4

作者：

Gopakumar, Shivapratap ^{[1
]}

Truyen Tran ^{[1
]}

Tu Dinh Nguyen ^{[1
]}

Dinh Phung ^{[1
]}

Venkatesh, Svetha ^{[1
]}

机构：

[1] Deakin Univ, Ctr Pattern Recognit & Data Analyt, Geelong, Vic 3216, Australia

来源：

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS | 2015年 / 19卷 / 03期

关键词：

Biomedical computing; electronic medical records; stability; predictive models; VARIABLE SELECTION; HEART-FAILURE; READMISSION; RISK; HOSPITALIZATION; REGULARIZATION; DEATH;

D O I：

10.1109/JBHI.2014.2353031

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We investigate feature stability in the context of clinical prognosis derived from high-dimensional electronic medical records. To reduce variance in the selected features that are predictive, we introduce Laplacian-based regularization into a regression model. The Laplacian is derived on a feature graph that captures both the temporal and hierarchic relations between hospital events, diseases, and interventions. Using a cohort of patients with heart failure, we demonstrate better feature stability and goodness-of-fit through feature graph stabilization.

引用

页码：1044 / 1052

页数：9

共 35 条

[1] Prognosis and prognostic research: validating a prognostic model
Altman, Douglas G.
Vergouwe, Yvonne
Royston, Patrick
Moons, Karel G. M.
[J]. BMJ-BRITISH MEDICAL JOURNAL, 2009, 338 : 1432 - 1435
[2] An Automated Model to Identify Heart Failure Patients at Risk for 30-Day Readmission or Death Using Electronic Medical Record Data
Amarasingham, Ruben
Moore, Billy J.
Tabak, Ying P.
Drazner, Mark H.
Clark, Christopher A.
Zhang, Song
Reed, W. Gary
Swanson, Timothy S.
Ma, Ying
Halm, Ethan A.
[J]. MEDICAL CARE, 2010, 48 (11) : 981 - 988
[3] [Anonymous], 2007, ARTIFICIAL INTELLIGE
[4] Automated variable selection methods for logistic regression produced unstable models for predicting acute myocardial infarction mortality
Austin, PC
Tu, JV
[J]. JOURNAL OF CLINICAL EPIDEMIOLOGY, 2004, 57 (11) : 1138 - 1146
[5] Awada W, 2012, 2012 IEEE 13TH INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION (IRI), P356, DOI 10.1109/IRI.2012.6303031
[6] What are the factors in risk prediction models for rehospitalisation for adults with chronic heart failure?
Betihavas, Vasiliki
Davidson, Patricia M.
Newton, Phillip J.
Frost, Steven A.
Macdonald, Peter S.
Stewart, Simon
[J]. AUSTRALIAN CRITICAL CARE, 2012, 25 (01) : 31 - 40
[7] Birnbaum Z., 1955, USE MANN WHITNEY STA
[8] Correlates of early hospital readmission or death in patients with congestive heart failure
Chin, MH
Goldman, L
[J]. AMERICAN JOURNAL OF CARDIOLOGY, 1997, 79 (12) : 1640 - 1644
[9] Chung F.R.K., 1997, AM MATH SOC, V92, DOI DOI 10.1090/CBMS/092
[10] Network and Data Integration for Biomarker Signature Discovery via Network Smoothed T-Statistics
Cun, Yupeng
Froehlich, Holger
[J]. PLOS ONE, 2013, 8 (09):

← 1 2 3 4 →