AUTHOR=Su Hang , Shou Yeqi , Fu Yujie , Zhao Dong , Heidari Ali Asghar , Han Zhengyuan , Wu Peiliang , Chen Huiling , Chen Yanfan 

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

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2022.1052868

DOI=10.3389/fninf.2022.1052868

ISSN=1662-5196

ABSTRACT=Pulmonary embolism (PE) is a common thrombotic disease and potentially fatal cardiovascular disorder. The rate of clinical misdiagnosis and missed diagnosis of PE is very high because patients with PE are asymptomatic or non-specific. 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, in this paper, an improved algorithm (SSACS) is proposed 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. In the experimental part, this paper verifies the optimization performance of SSACS by benchmark function experiments. Then, the overall adaptability and accuracy of the SSACS-KELM model are tested using 8 public data sets. Further, to verify the performance of SSACS-KELM on PE datasets, this paper conducts comparison experiments with other classical classifiers, swarm intelligence algorithms, and feature selection methods. The experimental results show that the selected metrics, such as high D-dimer concentration, hypoalbuminemia, history of tumor, systolic blood pressure and syncope, are essential for the feature selection method proposed in this study to determine the severity 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.