Skip to main content
. 2013 Jul 9;13:269. doi: 10.1186/1472-6963-13-269

Table 4.

Area under the receiver operating characteristics (ROC) curve of the case-mix based logistic regression models to identify patients located above the 95th percentile of health spending

 
Demographic variables only
ACG-PM
CRG
DCG-HCC
Out of the box AUC 95% CI AUC 95% CI AUC 95% CI AUC 95% CI
Variables:
 
 
 
 
 
 
 
 
A&S + dx + rx + cost percentiles (age < 65)
 
 
0,816
(0.813 - 0.818)
 
 
 
 
A&S + dx + rx + cost percentiles (age 65+)
 
 
0,761
(0.760 - 0.764)
 
 
 
 
A&S + dx
 
 
 
 
0,787
(0.786 - 0.789)
0,824
(0.822 - 0.825)
A&S + dx + rx + cost
 
 
 
 
 
 
0,852
(0.851 - 0.853)
Recalibration
 
 
 
 
 
 
 
 
Variables:
 
 
 
 
 
 
 
 
A&S (Age and sex)
0,774
(0.773 - 0.776)
 
 
 
 
 
 
A&S + Only Dx
 
 
0,845
(0.844 - 0.847)
0,797
(0.795 - 0.798)
0,846
(0.845 - 0.848)
A&S + Only Rx
 
 
0,833
(0.831 - 0.834)
 
 
0,837
(0.836 - 0.838)
A&S + Dx + Rx
 
 
0,847
(0.853 - 0.856)
 
 
0,858
(0.857 - 0.859)
A&S + Dx + Rx + cost percentile
 
 
0,868
(0.866- 0.869)
0.848*
(0.847 - 0.849)
0,868
(0.867 - 0.869)
A&S + Dx + Rx + cost percentile + DI     0,868 (0.867 - 0.869) 0.848* (0.847 - 0.850) 0,868  

*The CRG models do not include prescriptions.

Age groups: 14–17; 18–34; 35–44; 45–54; 55–64; 65–69; 70–74; 75–79; 80–84; 85 + .

Cost groups in percentiles: 0–1; 2–10; 11–25; 26–50; 51–75; 76–90; 91–93; 94–95; 96–97; 98 + .

Dx diagnoses, Rx Prescriptions, DI Deprivation index.