The association between <scp>Monocyte‐to‐Lymphocyte</scp> ratio and postoperative delirium in <scp>ICU</scp> patients in cardiac surgery

Su, Xunling; Wang, Jie; Lu, Xing

doi:10.1002/jcla.24553

Cited by 7 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 A). This is consistent with previous research findings that inadequate postoperative pain management [ 61 ], prolonged anesthesia duration [ 63 ], electrolyte imbalance, metabolic abnormalities [ 64 ], abnormal liver and kidney function [ 3 ], carbon dioxide retention [ 65 ], monocyte-to-lymphocyte ratio (MLR) [ 66 ], and decreased serum albumin [ 67 ] can all contribute to the occurrence of postoperative delirium. By comparing the summary plots of the two feature sets and considering the previous outcome indicators, it can be observed that despite having only 19 features, the selected feature set still has meaningful predictive power for the outcome.…”

Section: Discussionsupporting

confidence: 91%

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

Li,

Chen

et al. 2024

BMC Cardiovasc Disord

View full text Add to dashboard Cite

Background Previous models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients. Methods The electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (Random Forest Classifier, Logistic Regression, Support Vector Machine Classifier, K-nearest Neighbors Classifier, Gaussian Naive Bayes, Gradient Boosting Decision Tree, and Perceptron.) were used to develop delirium prediction models under full (q = 31) and selected (q = 19) feature sets, respectively. Result The Random Forest classifier performs exceptionally well in both feature datasets, with an Area Under the Curve (AUC) of 0.92 for the full feature dataset and an AUC of 0.86 for the selected feature dataset. Additionally, it achieves a relatively lower Expected Calibration Error (ECE) and the highest Average Precision (AP), with an AP of 0.80 for the full feature dataset and an AP of 0.73 for the selected feature dataset. To further evaluate the best-performing Random Forest classifier, SHAP (Shapley Additive Explanations) was used, and the importance matrix plot, scatter plots, and summary plots were generated. Conclusions We established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.

show abstract

Section: Discussionsupporting

confidence: 91%

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

Li,

Chen

et al. 2024

BMC Cardiovasc Disord

View full text Add to dashboard Cite

show abstract

“…As studies mentioned, a high level of NLR has been identified as an independent risk factor for POD in acute ischemic stroke and orthopedic surgery (Guldolf et al., 2021 ; Li et al., 2022 ). Also, other inflammatory markers ratios, such as MLR and PLR, played a prominent role in predicting POD after cardiac surgery (Şaşkin et al., 2022 ; Su et al., 2022 ). Interestingly, a recent study showed the connection between higher PWR and poor clinical consequences in patients with acute ischemic stroke (Amalia & Dalimonthe, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies demonstrated that the neutrophil‐to‐lymphocyte ratio (NLR), platelet‐to‐lymphocyte ratio (PLR), as well as platelet‐to‐white blood cell ratio (PWR) have been acknowledged as potential predictors of POD in head and neck free‐flap reconstruction or abdominal surgery (Ida et al., 2020 ; Kinoshita et al., 2021 ). Also, a recent study showed that the monocyte‐to‐lymphocyte ratio (MLR) was independently correlated with POD in intensive care unit (ICU) patients after cardiac surgery (Su et al., 2022 ). Furthermore, the above inflammatory indexes were capable of predicting postoperative complications and long‐term prognosis in thoracic oncology surgery (Ginesu et al., 2022 ; Tsukioka et al., 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Thoracic delirium index for predicting postoperative delirium in elderly patients following thoracic surgery: A retrospective case‐control study

Li,

Liu,

Zhang

et al. 2024

Brain and Behavior

View full text Add to dashboard Cite

BackgroundPostoperative delirium (POD) is an acute neurological complication in the elderly undergoing thoracic surgery and can result in serious adverse consequences.AimsThis study aimed to identify the related risk factors for POD following thoracic surgery, primarily focusing on preoperative serum biomarkers, and further to establish a novel delirium index to better predict POD.MethodsA total of 279 patients aged ≥60 years who underwent elective thoracic surgery from August 2021 to August 2022 were enrolled in this observational study. The platelet‐to‐white blood cell ratio (PWR) was calculated as number the of platelets divided by the number of white blood cells. POD was defined by the confusion assessment method twice daily during the postoperative first 3 days. Multivariate regression analysis was performed to identify all potential variables for POD. Moreover, a novel thoracic delirium index (TDI) was developed based on the related risk factors. The accuracy of TDI and its component factors in predicting POD was determined by the curve of receiver operating characteristic (ROC).ResultsIn total, 25 of 279 patients developed POD (8.96%). Age, PWR, and average pain scores within the first 3 days after surgery were regarded as the independent risk factors for POD. Moreover, the ROC analysis showed the TDI, including age, PWR, and average pain scores within the first 3 days after surgery, can more accurately predict POD with the largest area under the curve of 0.790 and the optimal cutoff value of 9.072, respectively.ConclusionThe TDI can scientifically and effectively predict POD to provide optimal clinical guidance for older patients after thoracic surgery.

show abstract

“…Delirium during hospitalization was assessed using the Confusion Assessment Method by the ICU. We utilized this approach, searching all the ICD codes associated with included subjects for the following terms: (1) delirium, (2) encephalopathy, (3) altered mental status, (4) confusion, (5) mental disorder, (6) hallucination, (7) delusion, and (8) cognitive impairment/deficit [ 41 , 42 , 43 , 44 ].…”

Section: Methodsmentioning

confidence: 99%

Promising Effects of Montelukast for Critically Ill Asthma Patients via a Reduction in Delirium

Li,

Zhang,

Zhang

et al. 2024

Pharmaceuticals

View full text Add to dashboard Cite

Background: Montelukast (MTK), a potent antagonist of cysteinyl leukotriene receptor 1, has shown therapeutic promise for the treatment of neuropsychiatric disorders. Delirium, a common complication in critically ill patients, lacks effective treatment. This study aims to explore the impact of pre-intensive care unit (ICU) MTK use on in-hospital delirium incidence and, subsequent, prognosis in critically ill patients. Methods: A retrospective cohort study (n = 6344) was conducted using the MIMIC-IV database. After propensity score matching, logistic/Cox regression, E-value sensitivity analysis, and causal mediation analysis were performed to assess associations between pre-ICU MTK exposure and delirium and prognosis in critically ill patients. Results: Pre-ICU MTK use was significantly associated with reduced in-hospital delirium (OR: 0.705; 95% CI 0.497–0.999; p = 0.049) and 90-day mortality (OR: 0.554; 95% CI 0.366–0.840; p = 0.005). The association was more significant in patients without myocardial infarction (OR: 0.856; 95% CI 0.383–0.896; p = 0.014) and could be increased by extending the duration of use. Causal mediation analysis showed that the reduction in delirium partially mediated the association between MTK and 90-day mortality (ACME: −0.053; 95% CI −0.0142 to 0.0002; p = 0.020). Conclusions: In critically ill patients, MTK has shown promising therapeutic benefits by reducing the incidence of delirium and 90-day mortality. This study highlights the potential of MTK, beyond its traditional use in respiratory disease, and may contribute to the development of novel therapeutic strategies for delirium.

show abstract

The association between Monocyte‐to‐Lymphocyte ratio and postoperative delirium in ICU patients in cardiac surgery

Cited by 7 publications

References 35 publications

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

Thoracic delirium index for predicting postoperative delirium in elderly patients following thoracic surgery: A retrospective case‐control study

Promising Effects of Montelukast for Critically Ill Asthma Patients via a Reduction in Delirium

Contact Info

Product

Resources

About