Predictive value of the Wells score combined with D-dimer level in identifying acute pulmonary embolism in patients with coronary heart disease with chest pain

Machine-learning-based models assist the prediction of pulmonary embolism in autoimmune diseases: A retrospective, multicenter study

BACKGROUND

Pulmonary embolism (PE) is a severe and acute cardiovascular syndrome with high mortality among patients with autoimmune inflammatory rheumatic diseases (AIIRDs). Accurate prediction and timely intervention play a pivotal role in enhancing survival rates. However, there is a notable scarcity of practical early prediction and risk assessment systems of PE in patients with AIIRD.

METHODS

In the training cohort, 60 AIIRD with PE cases and 180 age-, gender-, and disease-matched AIIRD non-PE cases were identified from 7254 AIIRD cases in Tongji Hospital from 2014 to 2022. Univariable logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) were used to select the clinical features for further training with machine learning (ML) methods, including random forest (RF), support vector machines (SVM), neural network (NN), logistic regression (LR), gradient boosted decision tree (GBDT), classification and regression trees (CART), and C5.0 models. The performances of these models were subsequently validated using a multicenter validation cohort.

RESULTS

In the training cohort, 24 and 13 clinical features were selected by univariable LR and LASSO strategies, respectively. The five ML models (RF, SVM, NN, LR, and GBDT) showed promising performances, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.962-1.000 in the training cohort and 0.969-0.999 in the validation cohort. CART and C5.0 models achieved AUCs of 0.850 and 0.932, respectively, in the training cohort. Using D-dimer as a pre-screening index, the refined C5.0 model achieved an AUC exceeding 0.948 in the training cohort and an AUC above 0.925 in the validation cohort. These results markedly outperformed the use of D-dimer levels alone.

CONCLUSION

ML-based models are proven to be precise for predicting the onset of PE in patients with AIIRD exhibiting clinical suspicion of PE.

TRIAL REGISTRATION

Chictr.org.cn : ChiCTR2200059599.

The relationship between pesi score and pulmonary venous flow parameters in patients with acute pulmonary embolism

BACKGROUND

Acute pulmonary embolism (APE) is an important cause of cardiovascular morbidity and mortality. PESI scoring is used in risk classification. This study was designed to determine the relationship between echocardiographic pulmonary vein measurements and PESI score, which is an important tool in diagnosis and treatment.

METHODS

A total of 210 patients were evaluated. Pulmonary vein measurements and PESI scores of the patients at the time of diagnosis were calculated. Correlation analysis was performed to determine the relationship between the two parameters.

RESULTS

Total PESI scores were 112.9 ± 33.9. The pulmonary vein S wave .39 ± .14, the D wave .48 ± .18, and the S/D ratio was found to be .86 ± .35. It was determined that there was a significant correlation between pulmonary S/D ratio and PESI score. (Pearson correlation coefficient = -.693, R2 Linear:.484; p < .001) The AUC of S/D for mortality prediction was .729 (95% CI = .653-.804; p < .001), the cutoff value was .63, the sensitivity and specificity were 55.6% and 55.7%, respectively.

CONCLUSION

Pulmonary vein measurements were found to be correlated with the PESI score and were found to be a parameter that could predict mortality.

The impact of COVID-19 on the sensitivity of D-dimer for pulmonary embolism

Objective

This study seeks to evaluate the test characteristics of D‐dimer for pulmonary embolism (PE) in patients with a concurrent diagnosis of COVID‐19. We hypothesized that the sensitivity of D‐dimer for PE at current institutional cut points would be similar to those without COVID‐19.

Methods

This is a multicenter retrospective observational cohort study across five urban and suburban EDs in the same health care system. The electronic health record was queried for all computed tomography pulmonary angiography (CTPA) studies from December 1, 2019, to October 22, 2020. All ED patients who underwent CTPA had D‐dimer and COVID‐19 testing completed in a single encounter were included in the study. Baseline demographics were obtained. Test characteristics of D‐dimer for PE were calculated for patients with and without COVID‐19. Additionally, receiver operator characteristics (ROC) curves were constructed for two different D‐dimer assays.

Results

There were 1158 patient encounters that met criteria for analysis. Performance of D‐dimer testing for PE was similar between COVID‐19–positive and –negative patients. In COVID‐19–positive patients, the sensitivity was 100% (95% confidence interval [CI] = 87.6%–100%), specificity was 11.9% (95% CI = 7.9%–17.1%), and negative predictive value (NPV) was 100%. In COVID‐19–negative patients the sensitivity was 97.6% (95% CI = 91.5%–99.7%), specificity was 14.4% (95% CI = 12.1%–17%), and NPV was 98.3% (95% CI = 93.8%–99.6%). For assay 1 the area under the curve (AUC) for COVID‐19–positive patients was 0.76 (95% CI = 0.68–0.83), and for COVID‐19–negative patients, 0.73 (95% CI = 0.69–0.77). For assay 2, AUC for COVID‐19–positive patients was 0.85 (95% CI = 0.77–0.92), and for COVID‐19–negative patients, 0.80 (95% CI = 0.77–0.84). Inspection of the ROC curve for assay 1 revealed that 100% sensitivity was maintained up to a threshold of 0.67 FEU (fibrinogen equivalent units; from 0.50 FEU) with an increase in specificity to 29% (from 18.7%), and for assay 2, 100% sensitivity was maintained up to a threshold of 662 D‐dimer units (DDU; from 230 DDU) with an increased specificity to 59% (from 6.1%).

Conclusion

Results from this multicenter retrospective study did not find a significant difference in sensitivity of D‐dimer for PE due to concomitant COVID‐19 infection. Further study is required to determine if PE can safely be excluded based on D‐dimer results alone in patients with suspected or proven COVID‐19 or if adjusted D‐dimer levels could have a role in management.

The plasma D-dimer trends and their value in acute lower limb ischemia patients treated by catheter directed thrombolysis

To investigate the change trends of plasma D-dimer during catheter-directed thrombolysis (CDT) in acute lower limb ischemia (ALI) patients and their clinical value. A retrospective review of patients with ALI who received CDT was carried out. The repeated measurements of plasma D-dimer were analyzed by generalized estimating equations (GEEs) and the change trends of D-dimer were analyzed by spline regression approach. A total of 150 patients were included. Among them, 3 days of CDT was ineffective in 41 cases, effective in 33 cases and markedly effective in 76 cases. The results of GEEs analysis showed that serum D-dimer changed significantly with time (time effect, P < 0.001). Serum D-dimer levels of patients with different treatment outcomes were different after treatment (group effect, P < 0.001), and serum D-dimer levels in these three groups showed different trends over time (group*time effect, P < 0.001). The different trends in serum D-dimer level with time after treatment in the three groups could be directly seen in the spline regression curve (P < 0.001). The plasma D-dimer changes regularly during CDT for ALI. We can predict the efficacy of CDT and guide adjustments of the therapeutic regimen according to the trend of D-dimer changes during thrombolysis.