Search Results (5)

Background: Pulmonary embolism (PE) is a significant cause of cardiovascular mortality, and emergency department (ED) management requires early risk assessment to guide monitoring and disposition. Because key decisions are often needed while diagnostic evaluation is ongoing, the simplified Pulmonary Embolism Severity Index (sPESI) may provide limited discrimination for in-hospital outcomes. We evaluated whether explainable machine-learning (ML) models integrating routine ED variables with validated risk scores can predict in-hospital mortality in adults evaluated for suspected acute PE. Methods: A retrospective single-center cohort study was performed, including 220 consecutive adults evaluated for suspected acute PE in the ED between January 2021 and March 2025, comprising both PE-confirmed and PE-excluded cases. Predictors included demographics, vital signs, arterial blood gas indices, available imaging/echocardiographic findings, and Wells, Revised Geneva, and sPESI scores. Seven ML algorithms were trained and internally evaluated using the area under the receiver operating characteristic curve (AUC) and complementary metrics. Model interpretability was assessed using SHAP (SHAPley Additive exPlanations), and a sensitivity analysis was conducted in the PE-confirmed subgroup. Results: Tree-based ensemble models demonstrated higher discrimination for in-hospital all-cause mortality than simpler classifiers. SHAP analyses consistently highlighted sPESI, oxygenation/arterial blood gas indices, and malignancy as key contributors to mortality risk. Findings were similar in the PE-confirmed sensitivity analysis. Conclusions: Explainable ML models combining established risk scores with routinely collected ED variables may complement risk stratification along the suspected-PE pathway. External multicenter validation and prospective impact studies are warranted before clinical implementation. Full article

Background: Pulmonary thromboembolism (PTE) is a preventable yet potentially fatal condition with significant morbidity and mortality. Several clinical scoring systems, including the Wells and modified Geneva scores, have been developed to assess the likelihood of PTE and guide further diagnostic evaluation. The Padua prediction score, primarily used to assess venous thromboembolism (VTE) risk in hospitalized patients, has also been considered for its potential utility in suspected PTE cases. Methods: This retrospective study included 257 patients with suspected acute PTE. Diagnosis was confirmed by computed tomography pulmonary angiography (CTPA) in 140 patients (patient group), while 117 patients without radiologic evidence of PTE served as controls. All participants were evaluated using Wells, modified Geneva, and Padua scores. Sensitivity, specificity, predictive values, and the effect of combining scores with age-adjusted D-dimer levels were analyzed. Results: The Wells score demonstrated a sensitivity of 60% and specificity of 91%, with a positive predictive value of 88%. Modified Geneva and Padua scores showed lower diagnostic accuracy. Negative predictive values increased significantly when combined with age adjusted D-dimer levels. Conclusions: The Wells score was the most reliable tool among the three for predicting PTE. Combining clinical scoring with D-dimer testing enhances diagnostic accuracy and may reduce unnecessary imaging in patients with low to moderate risk. Full article

Introduction: A significant increase in the use of computed tomography with pulmonary angiography (CTPA) for the diagnosis of pulmonary embolism (PE) has been observed in the past twenty years. We aimed to investigate whether the validated diagnostic predictive tools and D-dimers were adequately utilized in a large public hospital in New York City. Methods: We conducted a retrospective review of patients who underwent CTPA for the specific indication of ruling out PE over a period of one year. Two independent reviewers, blinded to each other and to the CTPA and D-dimer results, estimated the clinical probability (CP) of PE using Well’s score, the YEARS algorithm, and the revised Geneva score. Patients were classified based on the presence or absence of PE in the CTPA. Results: A total of 917 patients were included in the analysis (median age: 57 years, female: 59%). The clinical probability of PE was considered low by both independent reviewers in 563 (61.4%), 487 (55%), and 184 (20.1%) patients based on Well’s score, the YEARS algorithm, and the revised Geneva score, respectively. D-dimer testing was conducted in less than half of the patients who were deemed to have low CP for PE by both independent reviewers. Using a D-dimer cut-off of <500 ng/mL or the age-adjusted cut-off in patients with a low CP of PE would have missed only a small number of mainly subsegmental PE. All three tools, when combined with D-dimer < 500 ng/mL or <age-adjusted cut-off, yielded a NPV of > 95%. Conclusion: All three validated diagnostic predictive tools were found to have significant diagnostic value in ruling out PE when combined with a D-dimer cut-off of <500 ng/mL or the age-adjusted cut-off. Excessive use of CTPA was likely secondary to suboptimal use of diagnostic predictive tools. Full article

Background: Elderly COVID-19 patients have a high risk of pulmonary embolism (PE), but factors that predict PE are unknown in this population. This study assessed the Wells and revised Geneva scoring systems as predictors of PE and their relationships with D-dimer (DD) in this population. Methods: This was a longitudinal, observational study that included patients ≥75 years old with COVID-19 and suspected PE. The performances of the Wells score, revised Geneva score and DD levels were assessed. The combinations of the DD level and the clinical scales were evaluated using positive rules for higher specificity. Results: Among 305 patients included in the OCTA-COVID study cohort, 50 had suspected PE based on computed tomography pulmonary arteriography (CTPA), and the prevalence was 5.6%. The frequencies of PE in the low-, intermediate- and high-probability categories were 5.9%, 88.2% and 5.9% for the Geneva model and 35.3%, 58.8% and 5.9% for the Wells model, respectively. The DD median was higher in the PE group (4.33 mg/L; interquartile range (IQR) 2.40–7.17) than in the no PE group (1.39 mg/L; IQR 1.01–2.75) (p < 0.001). The area under the curve (AUC) for DD was 0.789 (0.652–0.927). After changing the cutoff point for DD to 4.33 mg/L, the specificity increased from 42.5% to 93.9%. Conclusions: The cutoff point DD > 4.33 mg/L has an increased specificity, which can discriminate false positives. The addition of the DD and the clinical probability scales increases the specificity and negative predictive value, which helps to avoid unnecessary invasive tests in this population. Full article

Introduction: The diagnostic algorithm of non-high risk pulmonary embolism (PE) is based on probability scoring systems and plasma D-dimer (DD) assessment. The aim of the present study was to investigate the efficacy of Revised Geneva Scoring (RGS) and DD testing for the excluding of non-high risk PE, in the patients admitted to the hospital due to acute respiratory diseases. Materials and Methods: The consecutive patients, above 18 years of age, referred to the department of lung diseases, entered the study. The exclusion criteria were: the pregnancy and the suspicion of high risk PE. Plasma DD was measured with quick ELISA test, VIDAS D-dimer New, bioMerieux, France. Multislice computed tomography angiography was performed in all of the patients. Results: 153 patients, median age 65 (19−88) years entered the study. The probability of PE was: low—in 58 patients (38%), intermediate—in 90 (59%), high—in 5 (3%). DD < 500 ng/mL was found in 12% of patients with low and intermediate probability of PE. PE was recognized in 10 out of 153 patients (7%). None of the patients with DD < 500 ng/mL was diagnosed with PE (NPV 100%). Median DD value was significantly higher in PE patients comparing to non-PE (4500 ng/mL and 1356 ng/mL respectively, p = 0.006). Conclusion: In the group of the patients with acute respiratory symptoms, low or intermediate clinical probability scoring combined with normal DD had a high NPV in excluding PE. Nevertheless, such approach was not very effective, as the increased DD was noted in 88% of the examined population. Full article