Abstract
Background: 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.
Methods: 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. Data for the study is provided by the Gold Coast
University Hospital.
Results: Results were assessed by comparing the two
models on the basis on discrimination using ROC curves
and calibration through the Hosmer-Lemeshow statistics.
Discussion: Findings suggest future use of high frequency
data to capture additional distributional information to
improve severity scoring systems for use in ICUs.
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.
Methods: 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. Data for the study is provided by the Gold Coast
University Hospital.
Results: Results were assessed by comparing the two
models on the basis on discrimination using ROC curves
and calibration through the Hosmer-Lemeshow statistics.
Discussion: Findings suggest future use of high frequency
data to capture additional distributional information to
improve severity scoring systems for use in ICUs.
| Original language | English |
|---|---|
| Pages | 47-48 |
| Number of pages | 2 |
| Publication status | Published - 2017 |
| Event | The First Gold Coast Health Research Week Conference 2017 - Gold Coast University Hospital, Gold Coast, Australia Duration: 28 Nov 2017 → 30 Nov 2017 https://www.goldcoast.health.qld.gov.au/research/research-week |
Conference
| Conference | The First Gold Coast Health Research Week Conference 2017 |
|---|---|
| Country/Territory | Australia |
| City | Gold Coast |
| Period | 28/11/17 → 30/11/17 |
| Internet address |