Development of a nomogram to predict in-hospital mortality of sepsis-associated encephalopathy: a retrospective cohort study
Background: Sepsis-associated encephalopathy (SAE) is related to an increased in-hospital mortality in patients with sepsis. We aim to establish a user-friendly nomogram for individual prediction of in-hospital death probability in patients with SAE.
Methods: Data were retrospectively retrieved from the Medical Information Mart for Intensive Care (MIMIC III) open source clinical database. SAE was defined by a Glasgow Coma Score (GCS) <15 at the presence of sepsis. Prediction model with a nomogram was constructed in the training set by Logistic regression analysis and then internally validated. A decision curve analysis (DCA) was performed to evaluate the net benefit of intervention with the nomogram.
Results: A total of 669 and 287 patients with SAE were randomly assigned to training set and internal validation set according to an allocation ratio of 7:3, respectively. Parameters eligible for the nomogram included age, Sequential Organ Failure Assessment (SOFA) score, red blood cell distribution width (RDW) and the mean values of heart rate, temperature and respiratory rate at first day of ICU admission. The nomogram exhibited good discrimination with an area under the receiver operating characteristic curve (AUROC) of 0.773 (95%CI: 0.729–0.818) in the training set and 0.741 (95%CI 0.673–0.809) in the validation set, respectively. Calibration of the derived model was also excellent, with Brier score of 0.136 (95%CI: 0.12–0.153) and 0.168 (95%CI: 0.144–0.192) in both sets. The DCA of the nomogram indicated greater net benefit than SOFA. X-tile analysis showed that the nomogram can clearly stratify patients into three subgroups with different risks of hospital death.
Conclusions: The nomogram presents excellent performance in predicting in-hospital mortality of SAE patients, which can guide the prevention of SAE progression and may be more beneficial once specific treatments towards SAE are developed.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
This is a list of supplementary files associated with this preprint. Click to download.
Posted 15 Jan, 2020
Development of a nomogram to predict in-hospital mortality of sepsis-associated encephalopathy: a retrospective cohort study
Posted 15 Jan, 2020
Background: Sepsis-associated encephalopathy (SAE) is related to an increased in-hospital mortality in patients with sepsis. We aim to establish a user-friendly nomogram for individual prediction of in-hospital death probability in patients with SAE.
Methods: Data were retrospectively retrieved from the Medical Information Mart for Intensive Care (MIMIC III) open source clinical database. SAE was defined by a Glasgow Coma Score (GCS) <15 at the presence of sepsis. Prediction model with a nomogram was constructed in the training set by Logistic regression analysis and then internally validated. A decision curve analysis (DCA) was performed to evaluate the net benefit of intervention with the nomogram.
Results: A total of 669 and 287 patients with SAE were randomly assigned to training set and internal validation set according to an allocation ratio of 7:3, respectively. Parameters eligible for the nomogram included age, Sequential Organ Failure Assessment (SOFA) score, red blood cell distribution width (RDW) and the mean values of heart rate, temperature and respiratory rate at first day of ICU admission. The nomogram exhibited good discrimination with an area under the receiver operating characteristic curve (AUROC) of 0.773 (95%CI: 0.729–0.818) in the training set and 0.741 (95%CI 0.673–0.809) in the validation set, respectively. Calibration of the derived model was also excellent, with Brier score of 0.136 (95%CI: 0.12–0.153) and 0.168 (95%CI: 0.144–0.192) in both sets. The DCA of the nomogram indicated greater net benefit than SOFA. X-tile analysis showed that the nomogram can clearly stratify patients into three subgroups with different risks of hospital death.
Conclusions: The nomogram presents excellent performance in predicting in-hospital mortality of SAE patients, which can guide the prevention of SAE progression and may be more beneficial once specific treatments towards SAE are developed.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5