Big Data and ICU scoring systems

James Todd, Brent Richards, Bruce J Vanstone, Adrian Gepp

Research output: Contribution to conferencePosterResearch

Abstract

Severity scoring systems are used in intensive care units for stratifying patients in clinical research and benchmarking ICU performance. A variant of the Acute Physiology and Chronic Health Evaluation (APACHE) system is used in Australia for benchmarking purposes – the APACHE III-j. This and other major scoring systems have been developed under an old paradigm of minimum data collection, while the current paradigm is to use all useful data. The APACHE III-j system uses the worst observations in the first 24-hours of a patient’s ICU stay, ignoring the rest of the distributional information. We hypothesise that scoring system performance can be improved by adding variables that capture this ignored distributional information. To test this hypothesis, the APACHE III-j system will be replicated and compared to a modified version that adds metrics describing the distribution of an underlying physiology variable utilising high frequency data.
Original languageEnglish
Publication statusPublished - 21 Jul 2017
EventAI in Intensive Care Research Day - Gold Coast University Hospital
Duration: 21 Jul 2017 → …
http://www.intellihq.com.au/july21st-2017-ai-research-day/

Workshop

WorkshopAI in Intensive Care Research Day
Period21/07/17 → …
Internet address

Fingerprint

APACHE
Benchmarking
Intensive Care Units
Research

Cite this

Todd, J., Richards, B., Vanstone, B. J., & Gepp, A. (2017). Big Data and ICU scoring systems. Poster session presented at AI in Intensive Care Research Day, .
Todd, James ; Richards, Brent ; Vanstone, Bruce J ; Gepp, Adrian. / Big Data and ICU scoring systems. Poster session presented at AI in Intensive Care Research Day, .
@conference{29f3cee8224947dfbb00341f39ff2dbd,
title = "Big Data and ICU scoring systems",
abstract = "Severity scoring systems are used in intensive care units for stratifying patients in clinical research and benchmarking ICU performance. A variant of the Acute Physiology and Chronic Health Evaluation (APACHE) system is used in Australia for benchmarking purposes – the APACHE III-j. This and other major scoring systems have been developed under an old paradigm of minimum data collection, while the current paradigm is to use all useful data. The APACHE III-j system uses the worst observations in the first 24-hours of a patient’s ICU stay, ignoring the rest of the distributional information. We hypothesise that scoring system performance can be improved by adding variables that capture this ignored distributional information. To test this hypothesis, the APACHE III-j system will be replicated and compared to a modified version that adds metrics describing the distribution of an underlying physiology variable utilising high frequency data.",
author = "James Todd and Brent Richards and Vanstone, {Bruce J} and Adrian Gepp",
year = "2017",
month = "7",
day = "21",
language = "English",
note = "AI in Intensive Care Research Day ; Conference date: 21-07-2017",
url = "http://www.intellihq.com.au/july21st-2017-ai-research-day/",

}

Todd, J, Richards, B, Vanstone, BJ & Gepp, A 2017, 'Big Data and ICU scoring systems' AI in Intensive Care Research Day, 21/07/17, .

Big Data and ICU scoring systems. / Todd, James; Richards, Brent; Vanstone, Bruce J; Gepp, Adrian.

2017. Poster session presented at AI in Intensive Care Research Day, .

Research output: Contribution to conferencePosterResearch

TY - CONF

T1 - Big Data and ICU scoring systems

AU - Todd, James

AU - Richards, Brent

AU - Vanstone, Bruce J

AU - Gepp, Adrian

PY - 2017/7/21

Y1 - 2017/7/21

N2 - Severity scoring systems are used in intensive care units for stratifying patients in clinical research and benchmarking ICU performance. A variant of the Acute Physiology and Chronic Health Evaluation (APACHE) system is used in Australia for benchmarking purposes – the APACHE III-j. This and other major scoring systems have been developed under an old paradigm of minimum data collection, while the current paradigm is to use all useful data. The APACHE III-j system uses the worst observations in the first 24-hours of a patient’s ICU stay, ignoring the rest of the distributional information. We hypothesise that scoring system performance can be improved by adding variables that capture this ignored distributional information. To test this hypothesis, the APACHE III-j system will be replicated and compared to a modified version that adds metrics describing the distribution of an underlying physiology variable utilising high frequency data.

AB - Severity scoring systems are used in intensive care units for stratifying patients in clinical research and benchmarking ICU performance. A variant of the Acute Physiology and Chronic Health Evaluation (APACHE) system is used in Australia for benchmarking purposes – the APACHE III-j. This and other major scoring systems have been developed under an old paradigm of minimum data collection, while the current paradigm is to use all useful data. The APACHE III-j system uses the worst observations in the first 24-hours of a patient’s ICU stay, ignoring the rest of the distributional information. We hypothesise that scoring system performance can be improved by adding variables that capture this ignored distributional information. To test this hypothesis, the APACHE III-j system will be replicated and compared to a modified version that adds metrics describing the distribution of an underlying physiology variable utilising high frequency data.

M3 - Poster

ER -

Todd J, Richards B, Vanstone BJ, Gepp A. Big Data and ICU scoring systems. 2017. Poster session presented at AI in Intensive Care Research Day, .