The International journal of neuroscience · 2026
A predictive model for postoperative delirium in patients admitted to the intensive care unit after cardiac valve 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.
Shi Zhizhen, Yuan Zhen, Cheng Jiwei, Zhao Yanxin
Аннотация
INTRODUCTION: Postoperative delirium (POD) frequently occurs in patients following cardiac valve surgery in the intensive care unit (ICU), and is linked to adverse outcomes and extended hospitalization. The purpose of this study was to establish and validate a model for predicting high-risk individuals.
METHODS: This retrospective analysis enrolled adult patients who had cardiac valve surgery and subsequent ICU admission. Potential predictors were screened using LASSO logistic regression with cross-validation, followed by multivariable logistic regression, and a nomogram was developed from the final model. Model performance was assessed by receiver operating characteristic (ROC) curve analysis, calibration plots and decision curve analysis (DCA), and was benchmarked against the Sequential Organ Failure Assessment (SOFA) score.
RESULTS: In total, 3249 patients were analyzed, of whom 535 (16.5%) developed POD. Significant predictors identified were oxygen saturation, respiratory rate, urea nitrogen, INR, white blood cell (WBC) count, hemoglobin, SOFA score, myocardial infarction, diabetes and hyperlipidemia. The nomogram yielded AUCs of 0.766 (95% CI: 0.738-0.794) in the training cohort and 0.789 (95% CI: 0.750-0.828) in the validation cohort, showing significantly better predictive accuracy than the SOFA score (p < 0.05).
CONCLUSIONS: The proposed model demonstrates strong predictive ability for POD in cardiac valve surgery patients and may aid clinicians in early risk stratification and targeted intervention. Further prospective validation is needed.
METHODS: This retrospective analysis enrolled adult patients who had cardiac valve surgery and subsequent ICU admission. Potential predictors were screened using LASSO logistic regression with cross-validation, followed by multivariable logistic regression, and a nomogram was developed from the final model. Model performance was assessed by receiver operating characteristic (ROC) curve analysis, calibration plots and decision curve analysis (DCA), and was benchmarked against the Sequential Organ Failure Assessment (SOFA) score.
RESULTS: In total, 3249 patients were analyzed, of whom 535 (16.5%) developed POD. Significant predictors identified were oxygen saturation, respiratory rate, urea nitrogen, INR, white blood cell (WBC) count, hemoglobin, SOFA score, myocardial infarction, diabetes and hyperlipidemia. The nomogram yielded AUCs of 0.766 (95% CI: 0.738-0.794) in the training cohort and 0.789 (95% CI: 0.750-0.828) in the validation cohort, showing significantly better predictive accuracy than the SOFA score (p < 0.05).
CONCLUSIONS: The proposed model demonstrates strong predictive ability for POD in cardiac valve surgery patients and may aid clinicians in early risk stratification and targeted intervention. Further prospective validation is needed.