1.Application of Improved Deep Extreme Learning Machine in the Classification of Traditional Chinese Medicine Syndromes of Lung Cancer
Xinyou ZHANG ; Huakang XU ; Xiaoling ZHOU ; Mengling LIU ; Xiuyun LI ; Yaming ZHANG ; Chunqiang ZHANG ; Liping TANG
World Science and Technology-Modernization of Traditional Chinese Medicine 2023;25(6):2132-2139
Objective To use feature selection and Likert grading method to quantify the data of lung cancer medical records,to construct a deep extreme learning machine model optimized by the sparrow search algorithm,to classify and predict the syndrome types of traditional Chinese medicine medical record data of lung cancer,and to provide scientific and effective research on syndrome type classification of traditional Chinese medicine.means.Methods The medical records of 497 cases diagnosed with lung cancer from January 2015 to December 2021 were collected from the Affiliated Hospital of Jiangxi University of Traditional Chinese Medicine,and 412 medical records were screened as the research objects.Syndromic factors of different syndromes were summarized by feature selection and feature importance ranking,and the syndrome factors were quantified by Likert grading method.Build a deep extreme learning machine optimized based on the sparrow search algorithm,and train and test the model.Finally,the model built in this paper is compared with other machine learning models according to three evaluation criteria.Results The average classification accuracy of the SSA-DELM model established in this paper was 88.44%,while the average accuracy of the support vector machine and Bayesian network was 83.39%and 84.53%,respectively.The recall rate and F1 value of the SSA-DELM model on the five syndrome types are mostly above 80%,which is also better than other traditional machine learning models.Conclusion The results of the study show that the use of feature selection combined with Likert grading method to quantify the lung cancer medical record data,compared with the 0-1 processing data,can show the characteristics of the data,improve the accuracy of the classification model,SSA-DELM new Compared with other traditional machine learning classification models,the model has better representation learning ability and learning speed.This model not only provides a scientific and technical means for the clinical treatment of lung cancer,but also provides a useful reference for the informatization and intelligent development of TCM syndrome differentiation and treatment.
2.Incidence and related factors of pericardial tamponade after left atrial appendage closure in patients with non-valvular atrial fibrillation
Binbin WANG ; Xiang XU ; Xingpeng WANG ; Huakang LI ; Qing YAO ; Haiyun HUANG ; Wenting WANG ; Chen WAN ; Feng LIU ; Yanli GUO ; Zhiyuan SONG
Journal of Army Medical University 2024;46(7):768-774
Objective To observe the incidence of pericardial tamponade(PT)after left atrial appendage closure(LAAC)in patients with non-valvular atrial fibrillation(NVAF),and to explore its related factors and outcomes.Methods NVAF patients who were hospitalized and treated with LAAC in Department of Cardiology of our hospital from August 2014 to March 2023 were selected for the study.The general clinical data,preoperative transthoracic echocardiography and transesophageal echocardiography data,results of routine preoperative laboratory tests,intraoperative data and follow-up data of the patients were collected through the hospital medical record management system.The enrolled patients were classified into the non-PT group(n=8)and the PT group(n =1184)according to whether PT occurred after LAAC or not.The incidence of PT,related risk factors and outcomes were statistically analyzed.Results This study included 639 males(53.6%)and 553 females(46.4%),with an average age of 68.1±9.65 years.The CHA2 DS2-VASc score was 4.51±1.72,and the HAS-BLED score was 3.36±1.09.PT occurred in 8 cases(0.67%),among them,6 cases occurred 1 to 33 h after LAAC,and 2 cases occurred on day 19 and day 27 after LAAC.As for the results of transesophageal echocardiography(TEE)and LAA angiography,compared with the non-PT group,the PT group had the significantly larger maximum caliber of the LAA(P=0.025,P=0.015),smaller maximum depth of the LAA(P=0.028,P=0.031),and lower success rate of one-time placement of the occluder(P=0.031);The occluder compression rate of the PT group was significantly greater than that of the non-PT group(P=0.046).Multivariate analysis showed that larger maximum diameter of LAA,smaller average effective depth of LAA and larger compression rate of occluder were the main risk factors for PT.All the 8 PT patients were cured by stopping antithrombotic drugs,pericardiocentesis or surgical drainage.During a mean follow-up of 39±27 months,there were no device-related thrombosis(DRT),ischemic stroke,systemic embolism and other complications in the PT group.Conclusion The incidence of PT after LAAC is low,which is related to the large diameter of LAA,the relatively insufficient depth of the LAA and the large compression rate of the occlude.PT can be cured by stopping antithrombotic drugs and pericardiocentesis/surgical drainage.