Higher Preoperative Red Blood Cell Distribution Width Increases the Risk of Myocardial Injury After Noncardiac Surgery in Advanced-Age Patients: A Retrospective Cohort Study

Liu, Chang; Zhang, Kai; Zhang, Ting; Sha, Xiaoling; Xu, Yu-Hai; Gu, Jun; Tian, Ye; Liu, Yanhong; Cao, Jiangbei; Mi, Weidong; Li, Hao

doi:10.2147/cia.s392778

Cited by 3 publications

(1 citation statement)

References 32 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RDW was used to diagnose certain types of anemia, including but not limited to iron-deficiency anemia, thalassemia, and sickle cell anemia [6,7]. Moreover, RDW is a predictive and prognostic biomarker for cardiovascular events, metabolic syndrome, and patients on chemo and radiation therapy [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Role of Red Cell Distribution Width in Late-onset Preeclampsia: A Single-Center Experience

Nori

Helmi

Salman

et al. 2023

amj

View full text Add to dashboard Cite

Background: Red cell distribution width (RDW) is an inflammatory biomarker and a component of complete blood count that gains increased attention. Pre-eclampsia (PE) is a unique pregnancy syndrome for which inflammation was proposed for pathogenesis. Objectives: We aimed to examine RDW's role in PE and explore confounders that limit its implication in practice. Materials and methods: A case-control study recruited 120 participants matched in body mass index (BMI) and gestational age into 3 subgroups; late-onset severe PE cases (30/120), late-onset non-severe PE cases (30/120), and healthy controls (60/120). Participants' demographics (age, BMI, systolic and diastolic blood pressure (SBP, and DBP), hematological and biochemical parameters were evaluated. Results: RDW was significantly higher in PE cases (P-value < 0.01 ); In addition, RDW was positively correlated to SBP, DBP, and protein urea, r =0.5, r = 0.46, and r = 0.47 ; P-value < 0.0001, respectively. Liver enzymes, hemoglobin, and white blood cell count were all significantly linked to RDW (r = 0.27, P-value = 0.015), (r = 0.32, P-value = 0.005), (r = -0.27, P-value = 0.02) and (r = 0.39; P-value = 0.0004) respectively. Applying ROC Curve analysis showed that RDW cut-off value of > 14.4% discriminated PE cases from healthy controls (P-value < 0.001). At a cut-off value > 15.6% RDW distinguished severe from non-severe PE cases (P-value < 0.001). Conclusion: RDW was significantly correlated to PE predictors and severity markers independent of gestational age and BMI. The ROC curve showed that RDW distinguished PE from healthy controls in addition to non-severe from severe PE cases with high sensitivity and specificity. Being an inexpensive, reliable test with good predictive and prognostic value warrants further studies for RDW's role in PE screening and follow-up.

show abstract

Section: Introductionmentioning

confidence: 99%

Role of Red Cell Distribution Width in Late-onset Preeclampsia: A Single-Center Experience

Nori

Helmi

Salman

et al. 2023

amj

View full text Add to dashboard Cite

show abstract

Development and Validation of an Explainable Machine Learning Model for Predicting Myocardial Injury After Noncardiac Surgery in Two Centers in China: Retrospective Study

Liu,

Zhang,

Yang

et al. 2024

JMIR Aging

Self Cite

View full text Add to dashboard Cite

Background: Myocardial injury after non-cardiac surgery (MINS) is an easily overlooked complication but closely related to postoperative cardiovascular adverse outcomes, so the improved risk prediction tools are critically needed.Objective: To develop and validate an explainable machine learning model for predicting MINS in older patients undergoing non-cardiac surgery. Methods:The retrospective cohort study assessed operations performed on non-cardiac surgical older patients at center 1 in the training set. The least absolute shrinkage and selection operator (LASSO) method and recursive feature elimination (RFE) methods were used to select key features. Prediction performance was measured by the area under the receiver operating characteristic curve (AUC) as the main evaluation metric to select the best algorithms. Validation data from the two datasets were explored to validate the performance of the model and the developed model was compared with the RCRI model. The SHapley Additive exPlanations (SHAP) method was applied to calculate values for each feature, representing the contribution to the predicted risk of complication, and generate personalized explanations.Results: A total of 12424 patients were included in training set, 4754 in center 1, 2245 in center 2 were included as validating sets. The best-performing model for prediction was CatBoost algorithm, achieving an AUC of 0.805 (95% confidence interval, 0.778-0.831) in the training set, and validating with an AUC of 0.780 in center 1, 0.70 in center 2, with superior performance compared to RCRI (AUC:0.636, P<0.01). The SHAP values indicated the ranking of the level of importance of each variable, and preoperative serum creatinine concentration, red blood cell distribution width, and age accounted for the top three. The results from SHAP method can make predictions towards event with a positive values or non-event with negative value and an explicit explanation of individualized risk prediction. Conclusions:The Catboost model demonstrated superior capability of predicting individual-level risk of MINS, and the explainable perspective can allow identification of potentially modifiable sources of risk on patient level.

show abstract

Development and validation of an explainable machine learning model for predicting myocardial injury after non-cardiac surgery: multicenter, retrospective study (Preprint)

Liu,

Zhang,

Yang

et al. 2023

Preprint

View full text Add to dashboard Cite

BACKGROUND Myocardial injury after non-cardiac surgery (MINS) is an easily overlooked complication but closely related to postoperative cardiovascular adverse outcomes, so the improved risk prediction tools are critically needed. OBJECTIVE To develop and validate an explainable machine learning model for predicting MINS in older patients undergoing non-cardiac surgery. METHODS The retrospective cohort study assessed operations performed on non-cardiac surgical older patients at center 1 in the training set. The least absolute shrinkage and selection operator (LASSO) method and recursive feature elimination (RFE) methods were used to select key features. Prediction performance was measured by the area under the receiver operating characteristic curve (AUC) as the main evaluation metric to select the best algorithms. Validation data from the two datasets were explored to validate the performance of the model and the developed model was compared with the RCRI model. The SHapley Additive exPlanations (SHAP) method was applied to calculate values for each feature, representing the contribution to the predicted risk of complication, and generate personalized explanations. RESULTS A total of 12424 patients were included in training set, 4754 in center 1, 2245 in center 2 were included as validating sets. The best-performing model for prediction was CatBoost algorithm, achieving an AUC of 0.805 (95% confidence interval, 0.778–0.831) in the training set, and validating with an AUC of 0.780 in center 1, 0.70 in center 2, with superior performance compared to RCRI (AUC:0.636, P<0.01). The SHAP values indicated the ranking of the level of importance of each variable, and preoperative serum creatinine concentration, red blood cell distribution width, and age accounted for the top three. The results from SHAP method can make predictions towards event with a positive values or non-event with negative value and an explicit explanation of individualized risk prediction. CONCLUSIONS The Catboost model demonstrated superior capability of predicting individual-level risk of MINS, and the explainable perspective can allow identification of potentially modifiable sources of risk on patient level.

show abstract

Higher Preoperative Red Blood Cell Distribution Width Increases the Risk of Myocardial Injury After Noncardiac Surgery in Advanced-Age Patients: A Retrospective Cohort Study

Cited by 3 publications

References 32 publications

Role of Red Cell Distribution Width in Late-onset Preeclampsia: A Single-Center Experience

Role of Red Cell Distribution Width in Late-onset Preeclampsia: A Single-Center Experience

Development and Validation of an Explainable Machine Learning Model for Predicting Myocardial Injury After Noncardiac Surgery in Two Centers in China: Retrospective Study

Development and validation of an explainable machine learning model for predicting myocardial injury after non-cardiac surgery: multicenter, retrospective study (Preprint)

Contact Info

Product

Resources

About