103 5 DELIRIUM | PART THREE emergency admission, a further distinction could be made between patients that did or did not have metabolic imbalances. These patients had a delirium risk of 10 and 32.5 percent, respectively (95%-CI: 6-15%, resp. 22-44%). In the group with an unscheduled admittance combined with a metabolic imbalance (delirium risk 1:3), Figure 2. ROC curve of the prediction model for delirium. These curves show the sensitivity and specificity of the different cut-off points in the algorithm. AUC of the original model (blue line) is 0.81 and 0.65 for the cross-validated model (green line). ECOG performance status 0-2 vs. ≥3, and curative vs. palliative treatment intention were further splits. The AUC of this algorithm was .81 (Figure 2 upper line). We evaluated predictive validity of the algorithm by five-fold cross-validation. This provided a lower estimate for the AUC of .65 (Figure 2 lower line), as the original algorithm estimates do not correct for uncertainty in the selection of predisposing and/or precipitating factors. The sum of the sensitivity and specificity was maximal at a cut-off with a high specificity of 85%, and a lower sensitivity of approximately 40% in the cross-validated algorithm. This cut-off allows for identification of a subgroup of patients with a high risk at delirium. In the algorithm, the cut-off is the distinction between patients with an unscheduled admittance with or without metabolic imbalances. We evaluated whether the factors found in this algorithmwere also predictive for different admissions of the same patient by comparing the prevalence of unscheduled admittances
RkJQdWJsaXNoZXIy MjY0ODMw