Frontiers in cardiovascular medicine · 2026
Development and validation of a predictive model for postoperative delirium in patients undergoing cardiac surgery.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Cui Lin, Zhang Jinhong, Sun Xiaoling, Xia Jiangling, Xu Hongyu
Аннотация
BACKGROUND: This study aimed to identify risk factors for postoperative delirium (POD) following adult cardiac surgery and to develop and validate a predictive nomogram for clinical application.
METHODS: Data from 724 cardiac surgery patients were randomly split into training (70%) and validation (30%) cohorts. Predictors selected through LASSO and multivariate logistic regression were used to build the nomogram. Model performance was examined using area under the receiver operating characteristic curve (AUROC), calibration plots, decision curve analysis (DCA), and clinical impact curve (CIC).
RESULTS: POD occurred in 285 patients (39.4%). Predictors included emergency surgery, age, Sequential Organ Failure Assessment score, postoperative shock, and postoperative blood lactate and glucose levels. The nomogram displayed excellent discriminative ability (high AUROC) and strong calibration agreement in both datasets. The model demonstrated strong clinical utility, as evidenced by the DCA and CIC results.
CONCLUSION: This study identifies key risk factors for POD and presents a validated nomogram as an effective, clinically valuable tool to predict POD among patients undergoing cardiac surgery.
METHODS: Data from 724 cardiac surgery patients were randomly split into training (70%) and validation (30%) cohorts. Predictors selected through LASSO and multivariate logistic regression were used to build the nomogram. Model performance was examined using area under the receiver operating characteristic curve (AUROC), calibration plots, decision curve analysis (DCA), and clinical impact curve (CIC).
RESULTS: POD occurred in 285 patients (39.4%). Predictors included emergency surgery, age, Sequential Organ Failure Assessment score, postoperative shock, and postoperative blood lactate and glucose levels. The nomogram displayed excellent discriminative ability (high AUROC) and strong calibration agreement in both datasets. The model demonstrated strong clinical utility, as evidenced by the DCA and CIC results.
CONCLUSION: This study identifies key risk factors for POD and presents a validated nomogram as an effective, clinically valuable tool to predict POD among patients undergoing cardiac surgery.