Predicting Adverse Events

Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients

Derek Sleeman, Laura Elizabeth Moss, Malcolm Sim, John Kinsella

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Myocardial damage is known to occur relatively frequently, and
although it is not often fatal it results in the patient staying in the
ICU for significantly longer. Thus it is important for clinicians to
detect these events. Confirmation of myocardial damage is by a
biomarker (troponin), but these tests are only done at fixed timepoints.
Consequently it is desirable for doctors, and support systems,
to detect myocardial damage from the standard parameters
collected for ICU patients. We have undertaken a study with several
ICU consultants to determine the conditions which generally
precede a myocardial-damaging event. In fact, these knowledge
acquisition sessions produced a complex model which we have
realized as 2 interacting modules. Subsequently, we compared
this model’s predictions against the original datasets; the model
when run against the test dataset resulted in a relatively high True
Positive (TP) rate (75.8%). The implications of these analyses are
discussed, as are a number of planned follow-up studies.
Original languageEnglish
Title of host publicationKCAP 2011 Conference Proceedings
Place of PublicationNew York
PublisherACM Press
Pages73-79
Number of pages7
ISBN (Electronic)978-1-4503-0396-5
Publication statusPublished - 2011

Fingerprint

Intensive Care Units
Troponin
Consultants
Datasets

Keywords

  • Knowledge Acquisition
  • Modelling of Expertize
  • Event Prediction
  • Intensive Care Unit
  • Myocardial Damage.

Cite this

Sleeman, D., Moss, L. E., Sim, M., & Kinsella, J. (2011). Predicting Adverse Events: Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients. In KCAP 2011 Conference Proceedings (pp. 73-79). New York: ACM Press.

Predicting Adverse Events : Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients. / Sleeman, Derek; Moss, Laura Elizabeth; Sim, Malcolm; Kinsella, John.

KCAP 2011 Conference Proceedings. New York : ACM Press, 2011. p. 73-79.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sleeman, D, Moss, LE, Sim, M & Kinsella, J 2011, Predicting Adverse Events: Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients. in KCAP 2011 Conference Proceedings. ACM Press, New York, pp. 73-79.
Sleeman D, Moss LE, Sim M, Kinsella J. Predicting Adverse Events: Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients. In KCAP 2011 Conference Proceedings. New York: ACM Press. 2011. p. 73-79
Sleeman, Derek ; Moss, Laura Elizabeth ; Sim, Malcolm ; Kinsella, John. / Predicting Adverse Events : Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients. KCAP 2011 Conference Proceedings. New York : ACM Press, 2011. pp. 73-79
@inproceedings{a0f48084c34a4cada5d574c74a0df351,
title = "Predicting Adverse Events: Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients",
abstract = "Myocardial damage is known to occur relatively frequently, and although it is not often fatal it results in the patient staying in the ICU for significantly longer. Thus it is important for clinicians to detect these events. Confirmation of myocardial damage is by a biomarker (troponin), but these tests are only done at fixed timepoints. Consequently it is desirable for doctors, and support systems, to detect myocardial damage from the standard parameters collected for ICU patients. We have undertaken a study with several ICU consultants to determine the conditions which generally precede a myocardial-damaging event. In fact, these knowledge acquisition sessions produced a complex model which we have realized as 2 interacting modules. Subsequently, we compared this model’s predictions against the original datasets; the model when run against the test dataset resulted in a relatively high True Positive (TP) rate (75.8{\%}). The implications of these analyses are discussed, as are a number of planned follow-up studies.",
keywords = "Knowledge Acquisition, Modelling of Expertize, Event Prediction, Intensive Care Unit, Myocardial Damage.",
author = "Derek Sleeman and Moss, {Laura Elizabeth} and Malcolm Sim and John Kinsella",
year = "2011",
language = "English",
pages = "73--79",
booktitle = "KCAP 2011 Conference Proceedings",
publisher = "ACM Press",

}

TY - GEN

T1 - Predicting Adverse Events

T2 - Detecting Myocardial Damage in Intensive Care Unit (ICU) Patients

AU - Sleeman, Derek

AU - Moss, Laura Elizabeth

AU - Sim, Malcolm

AU - Kinsella, John

PY - 2011

Y1 - 2011

N2 - Myocardial damage is known to occur relatively frequently, and although it is not often fatal it results in the patient staying in the ICU for significantly longer. Thus it is important for clinicians to detect these events. Confirmation of myocardial damage is by a biomarker (troponin), but these tests are only done at fixed timepoints. Consequently it is desirable for doctors, and support systems, to detect myocardial damage from the standard parameters collected for ICU patients. We have undertaken a study with several ICU consultants to determine the conditions which generally precede a myocardial-damaging event. In fact, these knowledge acquisition sessions produced a complex model which we have realized as 2 interacting modules. Subsequently, we compared this model’s predictions against the original datasets; the model when run against the test dataset resulted in a relatively high True Positive (TP) rate (75.8%). The implications of these analyses are discussed, as are a number of planned follow-up studies.

AB - Myocardial damage is known to occur relatively frequently, and although it is not often fatal it results in the patient staying in the ICU for significantly longer. Thus it is important for clinicians to detect these events. Confirmation of myocardial damage is by a biomarker (troponin), but these tests are only done at fixed timepoints. Consequently it is desirable for doctors, and support systems, to detect myocardial damage from the standard parameters collected for ICU patients. We have undertaken a study with several ICU consultants to determine the conditions which generally precede a myocardial-damaging event. In fact, these knowledge acquisition sessions produced a complex model which we have realized as 2 interacting modules. Subsequently, we compared this model’s predictions against the original datasets; the model when run against the test dataset resulted in a relatively high True Positive (TP) rate (75.8%). The implications of these analyses are discussed, as are a number of planned follow-up studies.

KW - Knowledge Acquisition

KW - Modelling of Expertize

KW - Event Prediction

KW - Intensive Care Unit

KW - Myocardial Damage.

M3 - Conference contribution

SP - 73

EP - 79

BT - KCAP 2011 Conference Proceedings

PB - ACM Press

CY - New York

ER -