Evolving classification of intensive care patients from event data |
| |
| Institution: | 1. Department of Information Systems Engineering, Ben-Gurion University of the Negev, Marcus Family Campus, Rager St., Beer-Sheva 84105, Israel;2. Department of Infectious Diseases, Guy’s and St. Thomas’ NHS foundation Trust, Westminster Bridge Road, London SE1 7EH, United Kingdom;3. The Farr Institute of Health Informatics Research, University College London, 222 Euston Road, London NW1 2DA, United Kingdom;1. VARPA Group, Department of Computer Science, University of A Coruna, Campus de Elviña s/n, 15071 A Coruña, Spain;2. LIDIA, Department of Computer Science, University of A Coruna, Campus de Elviña s/n, 15071 A Coruña, Spain;3. Artificial Vision Group, Department of Electronics and Computer Science, University of Santiago de Compostela, C/ Joaquín Díaz de Rábago s/n (Campus Sur), 15782 Santiago de Compostela, Spain;4. Optometry Group, Department of Applied Physics, University of Santiago de Compostela, Edificio Monte da Condesa s/n (Campus Sur), 15782 Santiago de Compostela, Spain;1. Biological Structure, University of Washington Structural Informatics Group, 1959 NE Pacific Street, Box 357420, Seattle, Washington 98195, USA;2. Computer Science and Engineering, University of Washington, Seattle, Washington 98195, USA;3. Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington 98195, USA;1. Faculty of Campo Limpo Paulista, Rua Guatemala, 167, 13231-230 Campo Limpo Paulista, SP, Brazil;2. Luxembourg Institute of Science and Technology, 29 Avenue John F. Kennedy, L-1855 Luxembourg, Luxembourg;3. Laboratoire de Recherche en Informatique, University of Paris-Sud, Bâtiment 650 (Ada Lovelace), 91405 Orsay, France;1. InSyBio Ltd, 109 Uxbridge Road, W5 5TL London, UK;2. Department of Computer Engineering and Informatics, University of Patras, Building B University Campus, Rio, 26500, Greece;3. Department of Social Work, School of Sciences of Health and Care, Technological Educational Institute of Western Greece, Megalou Aleksandrou 1, Koukouli, 26334 Patra, Greece;1. Department of Biomedical Informatics, University of Utah, 421 Wakara Way, Salt Lake City, UT 84108, USA;2. Homer Warner Research Center, Intermountain Healthcare, 5121 South Cottonwood Street, Murray, UT 84107, USA;3. Department of Internal Medicine, University of Utah, 30 North 1900 East, Salt Lake City, UT 84132, USA |
| |
| Abstract: | ObjectiveThis 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 methodsAn 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.ResultsRetrospective 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).ConclusionsOur 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. |
| |
| Keywords: | Evolving classification Decision trees Logistic regression Event data streams Intensive care |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
