Development of a Nomogram for Predicting ICU Readmission

Cureus. 2024 Oct 15;16(10):e71555. doi: 10.7759/cureus.71555. eCollection 2024 Oct.

Abstract

Background This study aims to develop and validate a comprehensive prediction model for ICU readmissions. Readmission following ICU discharge is associated with adverse outcomes such as increased mortality, prolonged hospital stays, and elevated healthcare costs. Consequently, predicting and preventing readmissions is crucial. Previous models for predicting ICU readmissions were primarily based on physiological indices; however, these indices fail to capture the complete nature of treatment or patient conditions beyond physiological measures, thereby limiting the accuracy of these predictions. Methodology A total of 1,400 patients who had an unplanned ICU admission at Sapporo Medical University Hospital from January 2015 to October 2022 were included; a single regression analysis was performed using unplanned ICU readmission as the dependent variable. After performing a single regression analysis, logistic regression analysis using the stepwise method was performed using variables with significant differences, and a predictive nomogram was created using the variables that remained in the final model. To internally validate the predictive nomogram model, nonparametric bootstrapping (1,000 replications) was performed on the original model. Results Of the 1,400 patients who had an unplanned admission to the ICU, 114 (8.1%) were readmitted to the ICU unplanned. Seven main variables (Sequential Organ Failure Assessment score, respiratory rate, Glasgow Coma Scale, sleep disturbance, Continuous Kidney Replacement Therapy, presence of tracheal suctioning, and Oxygen Saturation) were selected to be associated with ICU readmission. The evaluation of the models showed excellent discrimination with an area under the receiver operating characteristic of 0.805 (original model) and 0.796 (bootstrap model). Calibration plots also confirmed good agreement between observed and predicted reentry. Conclusions This new predictive model is more accurate than previous models because it includes physiological indicators as well as other patient conditions and procedures needed and is expected to be used in clinical practice. In particular, the inclusion of new factors, such as sleep disturbance and the need for tracheal suctioning, enabled a more comprehensive patient assessment. The use of this predictive nomogram as a criterion for discharging ICU patients may prevent unplanned ICU readmission.

Keywords: icu readmission; intensive care unit; nomogram; prediction model; sleep disturbance.