Derivation and validation of a prediction score for postoperative delirium in geriatric patients undergoing hip fracture surgery or hip arthroplasty

Abstract

IntroductionPostoperative delirium is a common complication of patients undergoing hip fracture surgery or arthroplasty and is related to decreased survival time and physical function. In this study, we aim to build and validate a prediction score of postoperative delirium in geriatric patients undergoing hip fracture surgery or hip arthroplasty.MethodsA retrospective cohort of geriatric patients undergoing hip fracture surgery or hip arthroplasty was established. Variables of included patients were collected as candidate predictors of postoperative delirium. The least absolute shrinkage and selection operator (LASSO) regression and logistic regression were used to derive a predictive score for postoperative delirium. The accuracy of the score was evaluated by the area under the curve (AUC) of the receiver operating curve (ROC). We used bootstrapping resamples for model calibration. The prediction score was validated in an extra cohort.ResultsThere were 1,312 patients in the derivation cohort, and the incidence of postoperative delirium was 14.33%. Of 40 variables, 9 were identified as predictors, including preoperative delirium, cerebrovascular accident (CVA) with the modified Rankin scale, diabetes with a random glucose level, Charlson comorbidity index (CCI), age, application of benzodiazepines in surgery, surgical delay ≥2 days, creatine ≥90 μmol/L, and active smoker. The prediction score achieved a mean AUC of 0.848 in the derivation cohort. In the validation cohort, the mean AUC was 0.833. The prediction model was well-calibrated in the two cohorts.ConclusionBased on retrospective data, a prediction score for postoperative delirium in geriatric patients undergoing hip fracture surgery or hip arthroplasty was derived and validated. The performance of the scoring system outperformed the models from previous studies. Although the generalization ability of the score needs to be tested in similar populations, the scoring system will enable delirium risk stratification for hip fracture patients and facilitate the development of strategies for delirium prevention.

Postoperative delirium in geriatric patients with hip fractures

“…Clinicians should be vigilant for POD in patients who present with these features during the perioperative period. In recent years, a variety of risk prediction models have been developed to predict POD risk in geriatric patients with hip fractures ( Kim et al, 2020 ; Oberai et al, 2021 ; Shen et al, 2022 ; Table 2 ), which enable delirium risk stratification for hip fracture patients and facilitate the development of strategies for POD. Adapted from the AWOL (Age, WORLD backward, Orientation, illness severity) delirium prediction tool for medical inpatients Douglas et al (2013) , Whitlock et al (2020) developed a perioperative delirium risk stratification tool called AWOL-S (Age, WORLD backward, Orientation, illness severity, Surgery-specific risk) for elective surgical patients.…”

Validation of the Charlson Comorbidity Index for the prediction of 30-day and 1-year mortality among patients who underwent hip fracture surgery

“…The mean of the original CCI in this cohort was 5.1 (SD ± 2.0) and 4.6 (SD ± 1.9) for the adjusted CCI. A previous study of a hip fracture population reported a similar CCI value of 5 (SD ± 2) (Shen et al 2022 ). The observed 30-day and 1-year mortality rates in this study were 8.6% and 25.9%, respectively.…”

Prediction models for postoperative delirium in elderly patients with machine-learning algorithms and SHapley Additive exPlanations

“…Interestingly, the random forest model also performed best in our previous study on POD prediction [ 10 ]. Shen J. et al developed a risk score for predicting POD in hip fracture patients, using nine variables, and achieving an AUC of 0.833 [ 25 ]. Yang Y. et al constructed a nomogram for POD prediction using only three variables and achieved an AUC of 0.84.…”