Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Multiple signal integration by decision tree induction to detect artifactsin the neonatal intensive care unit
Autore:
Tsien, CL; Kohane, IS; McIntosh, N;
Indirizzi:
MIT, Comp Sci Lab, Cambridge, MA 02139 USA MIT Cambridge MA USA 02139MIT, Comp Sci Lab, Cambridge, MA 02139 USA Harvard Univ, Sch Med, Boston, MA 02115 USA Harvard Univ Boston MA USA 02115 vard Univ, Sch Med, Boston, MA 02115 USA Childrens Hosp, Informat Program, Boston, MA 02115 USA Childrens Hosp Boston MA USA 02115 Informat Program, Boston, MA 02115 USA Royal Infirm, Neonatal Unit, Edinburgh EH1, Midlothian, Scotland Royal Infirm Edinburgh Midlothian Scotland EH1 EH1, Midlothian, Scotland
Titolo Testata:
ARTIFICIAL INTELLIGENCE IN MEDICINE
fascicolo: 3, volume: 19, anno: 2000,
pagine: 189 - 202
SICI:
0933-3657(200007)19:3<189:MSIBDT>2.0.ZU;2-U
Fonte:
ISI
Lingua:
ENG
Soggetto:
CARDIAC OPERATED PATIENTS; ALARM SYSTEM; NEURAL NETWORKS; PULSE OXIMETER; FUZZY-LOGIC; MEDICINE;
Keywords:
false alarms; artifact detection; decision trees; intensive care monitoring; patient monitoring; machine learning;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Clinical Medicine
Citazioni:
48
Recensione:
Indirizzi per estratti:
Indirizzo: Tsien, CL 450 Mem Dr,G121, Cambridge, MA 02139 USA 450 Mem Dr,G121 Cambridge MA USA 02139 Cambridge, MA 02139 USA
Citazione:
C.L. Tsien et al., "Multiple signal integration by decision tree induction to detect artifactsin the neonatal intensive care unit", ARTIF INT M, 19(3), 2000, pp. 189-202

Abstract

The high incidence of false alarms in the intensive care unit (ICU) necessitates the development of improved alarming techniques. This study aimed todetect artifact patterns across multiple physiologic data signals from a neonatal ICU using decision tree induction. Approximately 200 h of bedside data were analyzed. Artifacts in the data streams were visually located and annotated retrospectively by an experienced clinician. Derived values were calculated for successively overlapping time intervals of raw values, and then used as feature attributes for the induction of models trying to classify 'artifact' versus 'not artifact' cases. The results are very promising, indicating that integration of multiple signals by applying a classification system to sets of values derived from physiologic data streams may be a viable approach to detecting artifacts in neonatal ICU data. (C) 2000 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 01/10/20 alle ore 14:37:17