Deakin University
Browse

File(s) under permanent embargo

Stabilizing sparse Cox model using clinical structures in electronic medical records

conference contribution
posted on 2014-08-24, 00:00 authored by Truyen TranTruyen Tran, Shivapratap Gopakumar, Quoc-Dinh Phung, Svetha VenkateshSvetha Venkatesh
Stability in clinical prediction models is crucial for
transferability between studies, yet has received little
attention. The problem is paramount in highdimensional
data which invites sparse models with feature
selection capability. We introduce an effective
method to stabilize sparse Cox model of time-to-events
using clinical structures inherent in Electronic Medical
Records (EMR). Model estimation is stabilized using
a feature graph derived from two types of EMR structures:
temporal structure of disease and intervention recurrences,
and hierarchical structure of medical knowledge
and practices. We demonstrate the efficacy of the
method in predicting time-to-readmission of heart failure
patients. On two stability measures – the Jaccard
index and the Consistency index – the use of clinical
structures significantly increased feature stability without
hurting discriminative power. Our model reported
a competitive AUC of 0.64 (95% CIs: [0.58,0.69]) for 6
months prediction.

History

Event

Pattern Recognition for Healthcare Analytics. International Workshop (2nd : 2014 : Stockholm, Sweden)

Pagination

1 - 4

Publisher

International Association of Pattern Recognition

Location

Stockholm, Sweden

Place of publication

[Stockholm, Sweden]

Start date

2014-08-24

End date

2014-08-24

Language

eng

Publication classification

E Conference publication; E1.1 Full written paper - refereed

Copyright notice

[2014, The Conference]

Title of proceedings

IAPR 2014: Proceedings of 2nd International Workshop on Pattern Recognition for Healthcare Analytics

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC