Imagine an older loved one with heart disease going in for a routine surgery, only to emerge confused, agitated, and not themselves. This condition, called postoperative delirium, is a serious and common risk for this group, affecting about 1 in 6 patients in this study. Until now, doctors haven't had a reliable way to predict who it will happen to. This research aimed to build that prediction tool. Using data from 861 elderly patients with coronary heart disease who had non-heart surgeries, scientists developed several computer models to forecast the risk of delirium. The best-performing model was highly accurate at spotting who was likely to develop this complication. It did this by analyzing seven key factors about a patient. The most important predictors were a person's level of physical frailty, their score on a simple memory test, and how severe their insomnia was. The researchers created an easy-to-use calculator based on this model. While the tool looks promising, the study notes it needs to be tested in other hospitals before it can be widely used to help doctors plan safer care for at-risk seniors.
Can a computer model predict post-surgery confusion in older heart patients? A new tool shows promise.
Plain Language Summary
What this means for you:
A new computer model uses frailty, memory, and sleep scores to predict post-surgery confusion in older heart patients. What this means for you:
A new computer model uses frailty, memory, and sleep scores to predict post-surgery confusion in older heart patients. View Original Abstract ↓
BackgroundPatients with advanced age and coronary heart disease (CHD) are at significantly increased risk for postoperative delirium (POD). However, there is no method to predict POD in elderly patients with CHD.MethodsDate from elderly patients with CHD who underwent non-cardiac surgery was collected. The dataset is subdivided into training and validation sets at a ratio of 7:3. Boruta algorithm, least absolute shrinkage and selection operator (LASSO) regression and multiple logistic regression analysis were used to select features. Machine learning method was used to construct a model for predicting the occurrence of POD. Receiver operating characteristic (ROC) curve, decision curve, calibration curve, specificity, sensitivity, accuracy, F1 score and Brier score were used to compare the predictive performance of these machine learning models, and the interpretability of the models was evaluated by Shapley additive interpretation (SHAP).ResultsA total of 861 patients were included in the study. The incidence of POD was 16.6% (143/861). Seven key features were identified. Ten machine learning models were constructed. Among the models, gradient boosting model (GBM) performed better. The area under the ROC curve (AUC) is 0.856 (95% confidence interval [CI]: 0.796-0.916). The decision curve, calibration curve, specificity, sensitivity, accuracy, F1 score and Brier score were also relatively good. SHAP plots of GBM showed that Clinical Frailty Scale (CFS) grade, Mini-mental State Examination (MMSE) score, and Athens Insomnia Scale (AIS) score were significant predictors of POD in elderly CHD patients, and an easy-to-use calculator for predicting the risk of POD was developed based on the GBM model.ConclusionThis study developed a reliable GBM model for predicting the occurrence of POD in elderly patients with CHD. Higher CFS grade, lower MMSE score and higher AIS score significantly enhanced the predictive ability of the model. External validation of our model is needed before it can be applied in a clinical setting.Trial registrationRegistration number of the Chinese Clinical Trial Registry: ChiCTR2500097325, Registration Date: 17/02/2025.