Development and Validation of a Delirium Prediction Model for Elderly Patients (DEEP)
Issued Date
2022-03-01
Resource Type
ISSN
01252208
Scopus ID
2-s2.0-85127459338
Journal Title
Journal of the Medical Association of Thailand
Volume
105
Issue
3
Start Page
180
End Page
187
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of the Medical Association of Thailand Vol.105 No.3 (2022) , 180-187
Suggested Citation
Lertvipapath P. Development and Validation of a Delirium Prediction Model for Elderly Patients (DEEP). Journal of the Medical Association of Thailand Vol.105 No.3 (2022) , 180-187. 187. doi:10.35755/jmedassocthai.2022.03.13274 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/86050
Title
Development and Validation of a Delirium Prediction Model for Elderly Patients (DEEP)
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
Background: Delirium is common among hospitalized elderly patients. It is associated with complications and mortality. Objective: To develop and validate a predictive model for delirium among hospitalized elderly patients. Materials and Methods: The present study was a single-center, retrospective cohort study performed in 589 patients aged 60 years or older admitted to medical or surgical units at a tertiary hospital in Bangkok, Thailand between 2011 and 2017. Results: A sample was randomly split (70:30) into the derivation set (n=412; 120 with delirium) and validation set (n=177; 56 with delirium). In the derivation set, multiple logistic regression reveled six potential risk factors, which were older than 75 years, dementia, infection, liver cirrhosis, hypokalemia, and hyponatremia. Hosmer-Lemeshow goodness-of-fit test showed that the model had a good calibration (p=0.27). The model also had a good discrimination ability based on high area under receiver operating characteristic (AUROC) curve of 0.821 (95% CI 0.784 to 0.858). Regression coefficients were used to get a risk score which varied from 0 to 15. The optimal cutoff point of 4.5 or with a higher risk of delirium, gave a sensitivity of 65.8% (95% CI 56.6 to 74.2), a specificity of 82.2% (95% CI 77.3 to 86.4), a positive predictive value of 60.3% (95% CI 53.5 to 66.7), a negative predictive value of 85.4% (95% CI 82.0 to 88.3), and an accuracy of 77.4% (95% CI 73.1 to 81.4). The risk score was then applied to the derivation set resulting in a higher AUROC of 0.855 (95% CI 0.797 to 0.914). Conclusion: The present study was a simple predictive model that demonstrated good discrimination ability, high specificity, and an excellent negative predictive value. It may permit the use of early preventive intervention to reduce the incidence, severity, and complications of delirium.