Usefulness of admission red blood cell distribution width as a predictor of severity of acute pulmonary embolism

Is Red Cell Distribution Width a Reliable Marker for Cardiovascular Diseases? A Narrative Review

Red cell distribution width (RDW) is an easy-to-access marker which is routinely measured in complete blood count (CBC) test. Besides the classic use of RDW as a marker for discriminating different types of anemia, recent studies had indicated the relationship between high RDW and cardiovascular diseases. High RDW is not only useful in the diagnosis and prognostication of various cardiovascular conditions but also could be used as a valuable tool for predicting the incidence of cardiovascular diseases. population-based studies have indicated that higher RDW could effectively predict the incidence of heart failure (HF), atherosclerotic diseases, and atrial fibrillation (AF). It has been also demonstrated that higher RDW is associated with worse outcomes in these diseases. Recent studies have shown that high RDW is also associated with other cardiovascular conditions including cardiomyopathies, and pulmonary hypertension. The predictive role of RDW in endovascular interventions has also been demonstrated by many recent studies. Here in this review, we attempt to compile the most recent findings with older reports regarding the relation between high RDW and HF, cardiomyopathies, pulmonary hypertension, AF, atherosclerotic disorders, primary hypertension, and the outcomes of endovascular interventions. we also discussed the role of RDW in the prognostication of different cardiovascular conditions when combined with classic classification criteria.

Construction and validation of risk prediction models for pulmonary embolism in hospitalized patients based on different machine learning methods

Objective

This study aims to apply different machine learning (ML) methods to construct risk prediction models for pulmonary embolism (PE) in hospitalized patients, and to evaluate and compare the predictive efficacy and clinical benefit of each model.

Methods

We conducted a retrospective study involving 332 participants (172 PE positive cases and 160 PE negative cases) recruited from Guangdong Medical University. Participants were randomly divided into a training group (70%) and a validation group (30%). Baseline data were analyzed using univariate analysis, and potential independent risk factors associated with PE were further identified through univariate and multivariate logistic regression analysis. Six ML models, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost were developed. The predictive efficacy of each model was compared using the receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). Clinical benefit was assessed using decision curve analysis (DCA).

Results

Logistic regression analysis identified lower extremity deep venous thrombosis, elevated D-dimer, shortened activated partial prothrombin time, and increased red blood cell distribution width as potential independent risk factors for PE. Among the six ML models, the RF model achieved the highest AUC of 0.778. Additionally, DCA consistently indicated that the RF model offered the greatest clinical benefit.

Conclusion

This study developed six ML models, with the RF model exhibiting the highest predictive efficacy and clinical benefit in the identification and prediction of PE occurrence in hospitalized patients.

Prognostic value of red blood cell distribution width in patients with acute pulmonary embolism: A protocol for systematic review and meta-analysis

BACKGROUND

Prior reports have suggested that the red blood cell distribution width (RDW) parameter could be measured as a prognostic indicator in pulmonary embolism (PE) patients, thereby helping to guide their care. However, no systematic analyses on this topic have been completed to date, and the exact relationship between RDW and PE remains to be fully clarified. We will therefore conduct a systematic literature review with the goal of defining the correlation between RDW and mortality in acute PE cases.

METHODS

The EMBASE, Web of Knowledge, PubMed, ClinicalTrials.gov, and Cochrane Library databases will be searched for all relevant studies published from inception through March 2021 using the following search strategy: ("red blood cell distribution width") AND ("pulmonary embolism"). Two authors will independently identify eligible studies and extract data. The Q and I2 statistics will be used to judge heterogeneity among studies.

RESULTS

This study will establish the relative efficacy of RDW as a metric for predicting PE patient mortality.

CONCLUSIONS

This study will offer a reliable, evidence-based foundation for the clinical utilization of RDW as a tool for gauging mortality risk in acute PE patients.

ETHICS AND DISSEMINATION

As this is a protocol for a systematic review of previously published data, no ethical approval is required. Electronic dissemination of study results will be done through a peer-review publication or represented at a related conference.

A narrative review of red blood cell distribution width as a marker for pulmonary embolism

Red blood cell distribution width (RDW) is a marker of variability in red blood cell size, and is routinely reported as part of a patient's complete blood count. RDW has been shown to be associated with the prediction, severity and prognosis of pulmonary embolism (PE) in recent studies. The underlying biomolecular mechanism of the relationship of RDW to PE is largely unknown, but is thought to be due to the relationship of RDW with acute inflammatory markers and variations in blood viscosity. This review substantiates that a high RDW level, defined using either an arbitrary number or according to receiver operator curve statistics, is associated with a higher risk of acute PE, increased severity (massive vs. submassive) of PE and increased mortality in patients with PE. Nevertheless, the comparison of current studies is limited due to the definition of high RDW (each study uses a different RDW cutoff level), the broad range of exclusion criteria and the inclusion of differing modalities used to diagnose a PE (computed tomography angiogram, ventilation-perfusion study, or clinical diagnosis). Despite the above limitations, these studies provide a promising future clinical use for RDW as a marker of PE.