Are the Charlson and Elixhauser Comorbidity Indices Reliable Predictors of Postoperative Delirium in Abdominal Surgery?
Chorney, W.; Lisi, M.
Show abstract
BackgroundPostoperative delirium (POD) is a common complication of surgery. It is associated with a number of detrimental effects, including mortality and healthcare costs. We sought to determine whether common comorbidity indices are predictors of POD. MethodsUsing the Medical Information Mart for Intensive Care (MIMIC)-IV database, we identified 8022 abdominal surgery procedures across 7212 adult patients. We calculated both the Charlson comorbidity index (CCI) and the Elixhauser comorbidity index (ECI) for each procedure and used logistic regression to predict postoperative delirium, which was defined as delirium within 30 days following the procedure. ResultsModels based on either the CCI and ECI were predictive of postoperative delirium (area under the receiver-operator characteristic curve (AUC-ROC) of 0.622 and 0.652, respectively). However, the addition of other factors known to be associated with delirium improved model performance (AUC-ROC of 0.680). ConclusionsBoth the CCI and ECI are predictors of postoperative delirium in patients undergoing abdominal surgery. Addition of factors known to be associated with delirium renders additional predictive value and should be included in models that predict postoperative delirium.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluating the predictive value of frailty scores for critical care admission and hospital stay in elderly surgical patients: a comparison of the mFI-5 and CCI 96%
- Development of a Risk Prediction Model for Sepsis-Related Delirium Based on Multiple Machine Learning Approaches and an Online Calculator 94%
- Regional performance variation in external validation of four prediction models for severity of COVID-19 at hospital admission: An observational multi-centre cohort study 94%
Similar papers in this journal
- Point-of-care electroencephalography for prediction of postoperative delirium in older adults undergoing elective surgery: protocol for a prospective cohort study 94%
- A Novel Method for Handling Pre-Existing Conditions in Prediction Models for Covid-19 Death 91%
- Prediction of high-risk liver cancer patients from their mutation profile: Benchmarking of mutation calling techniques 88%
Similar papers in this journal
- Use of the first National Early Warning Score recorded within 24 hours of admission to estimate the risk of in-hospital mortality in unplanned COVID-19 patients: a retrospective cohort study 94%
- Validating the RISE UP score for predicting prognosis in patients with COVID-19 in the emergency department, a retrospective study 94%
- Development and validation of automated computer aided-risk score for predicting the risk of in-hospital mortality using first electronically recorded blood test results and vital signs for COVID-19 hospital admissions: a retrospective development and validation study 94%
Similar papers in this journal
- The impact of atypical intrahospital transfers on patient outcomes: a mixed methods study 92%
- AKI Risk Score (AKI-RiSc): Developing an Interpretable Clinical Score for Early Identification of Acute Kidney Injury for Patients Presenting to the Emergency Department 92%
- Impact of early postoperative ambulation on gait recovery after hip fracture surgery: A multicenter cohort study 92%
Similar papers in this journal
- Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning 93%
- OASIS+: leveraging machine learning to improve the prognostic accuracy of OASIS severity score for predicting in-hospital mortality 93%
- On the predictability of postoperative complications for cancer patients: a Portuguese cohort study 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.