UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Evolving classification of intensive care patients from event data

Last, M; Tosas, O; Cassarino, TG; Kozlakidis, Z; Edgeworth, J; (2016) Evolving classification of intensive care patients from event data. Artificial Intelligence in Medicine , 69 pp. 22-32. 10.1016/j.artmed.2016.04.001. Green open access

[img]
Preview
Text
Last et al Evolving classification of intensive care patients from event data AAM.pdf

Download (263kB) | Preview

Abstract

Objective: This work aims at predicting the patient discharge outcome on each hospitalization day by introducing a new paradigm—evolving classification of event data streams. Most classification algorithms implicitly assume the values of all predictive features to be available at the time of making the prediction. This assumption does not necessarily hold in the evolving classification setting (such as intensive care patient monitoring), where we may be interested in classifying the monitored entities as early as possible, based on the attributes initially available to the classifier, and then keep refining our classification model at each time step (e.g., on daily basis) with the arrival of additional attributes. / Materials and methods: An oblivious read-once decision-tree algorithm, called information network (IN), is extended to deal with evolving classification. The new algorithm, named incremental information network (IIN), restricts the order of selected features by the temporal order of feature arrival. The IIN algorithm is compared to six other evolving classification approaches on an 8-year dataset of adult patients admitted to two Intensive Care Units (ICUs) in the United Kingdom. / Results: Retrospective study of 3452 episodes of adult patients (≥ 16 years of age) admitted to the ICUs of Guy’s and St. Thomas’ hospitals in London between 2002 and 2009. Random partition (66:34) into a development (training) set n = 2287 and validation set n = 1165. Episode-related time steps: Day 0—time of ICU admission, Day x—end of the x-th day at ICU. The most accurate decision-tree models, based on the area under curve (AUC): Day 0: IN (AUC = 0.652), Day 1: IIN (AUC = 0.660), Day 2: J48 decision-tree algorithm (AUC = 0.678), Days 3–7: regenerative IN (AUC = 0.717–0.772). Logistic regression AUC: 0.582 (Day 0)—0.827 (Day 7). / Conclusions: Our experimental results have not identified a single optimal approach for evolving classification of ICU episodes. On Days 0 and 1, the IIN algorithm has produced the simplest and the most accurate models, which incorporate the temporal order of feature arrival. However, starting with Day 2, regenerative approaches have reached better performance in terms of predictive accuracy.

Type: Article
Title: Evolving classification of intensive care patients from event data
Open access status: An open access version is available from UCL Discovery
DOI: 10.1016/j.artmed.2016.04.001
Publisher version: http://dx.doi.org/10.1016/j.artmed.2016.04.001
Language: English
Additional information: Copyright © 2016 Elsevier B.V. All rights reserved. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
Keywords: Evolving classification; Decision trees; Logistic regression; Event data streams; Intensive care
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources
URI: https://discovery.ucl.ac.uk/id/eprint/1495931
Downloads since deposit
71Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item