Rapid prediction of deterioration risk among non-high-risk patients with acute pulmonary embolism at admission: An imaging tool

Right ventricular area predicts short-term mortality in acute pulmonary embolism based on CT pulmonary angiography: A retrospective study

We performed this cohort study to assess the prognostic value of right ventricular size, including diameter, area, and volume, in short-term mortality of acute pulmonary embolism (APE) based on 256-slice computed tomography compared with D-dimer, creatine kinase muscle and brain isoenzyme, and Wells scores. A total of 225 patients with APE, who were followed up for 30 days were enrolled in this cohort study. Clinical data, laboratory indices (creatine kinase, creatine kinase muscle and brain isoenzyme, and D-dimer), and Wells scores were collected. The 256-slice computed tomography was used to quantify cardiac parameters (RVV/LVV, RVD/LVD-ax, RVA/LVA-ax, RVD/LVD-4ch, RVA/LVA-4ch) and the diameter of the coronary sinus. Participants were divided into non-death and death groups. The values mentioned above were compared between the 2 groups. The RVD/LVD-ax, RVA/LVA-ax, RVA/LVA-4ch, RVV/LVV, D-dimer, and creatine kinase levels were significantly higher in the death group than in the non-death group (P < .05). The active period of the malignant tumor, heart rate ≥ 100 beats/minutes, and RVA/LVA-ax were positively correlated with early death from APE (P < .05). Active stage of malignant tumor (OR:9.247, 95%CI:2.682-31.888, P < .001) and RVA/LVA-ax (OR:3.073, 95%CI:1.447-6.528, P = .003) were independent predictors of early death due to APE. According to the receiver operating characteristic curve, the cutoff point of RVA/LVA-ax was 1.68 with a sensitivity of 46.7% and specificity of 84.8%. The measurement of ventricular size in the short-axis plane is more convenient and reliable than that in the 4-chamber cardiac plane. RVA/LVA-ax is an independent predictor of early death from APE, and when RVA/LVA-ax > 1.68, the risk of early death from APE increases.

A new machine learning model for predicting severity prognosis in patients with pulmonary embolism: Study protocol from Wenzhou, China

Introduction

Pulmonary embolism (PE) is a common thrombotic disease and potentially deadly cardiovascular disorder. The ratio of clinical misdiagnosis and missed diagnosis of PE is very large because patients with PE are asymptomatic or non-specific.

Methods

Using the clinical data from the First Affiliated Hospital of Wenzhou Medical University (Wenzhou, China), we proposed a swarm intelligence algorithm-based kernel extreme learning machine model (SSACS-KELM) to recognize and discriminate the severity of the PE by patient's basic information and serum biomarkers. First, an enhanced method (SSACS) is presented by combining the salp swarm algorithm (SSA) with the cuckoo search (CS). Then, the SSACS algorithm is introduced into the KELM classifier to propose the SSACS-KELM model to improve the accuracy and stability of the traditional classifier.

Results

In the experiments, the benchmark optimization performance of SSACS is confirmed by comparing SSACS with five original classical methods and five high-performance improved algorithms through benchmark function experiments. Then, the overall adaptability and accuracy of the SSACS-KELM model are tested using eight public data sets. Further, to highlight the superiority of SSACS-KELM on PE datasets, this paper conducts comparison experiments with other classical classifiers, swarm intelligence algorithms, and feature selection approaches.

Discussion

The experimental results show that high D-dimer concentration, hypoalbuminemia, and other indicators are important for the diagnosis of PE. The classification results showed that the accuracy of the prediction model was 99.33%. It is expected to be a new and accurate method to distinguish the severity of PE.