Font Size: a A A

Prognostic Model Of Traditional Chinese And Western Medicine For Patients With Chronic Heart Failure Based On Decision Tree

Posted on:2021-09-25Degree:MasterType:Thesis
Country:ChinaCandidate:C SunFull Text:PDF
GTID:2504306302499874Subject:Chinese medical science
Abstract/Summary:PDF Full Text Request
ObjectiveObserve the occurrence of endpoint events and prognostic factors of TCM and Western medicine in patients with chronic heart failure in TCM hospitals,screen for the prognostic factors of TCM and Western medicine related to the occurrence of endpoint events,and use decision tree algorithms to build a prognostic model of TCM and Western medicine for chronic heart failure patients Prognostic evaluation and management of heart failure patients provide reference.MethodUsing the retrospective cohort study and relying on the case management system of the Affiliated Hospital of Shandong University of Traditional Chinese Medicine,patients with chronic heart failure who were admitted from January 1,2013 to December 31,2017 and met the inclusion criteria were used as the cohort.The "Cohort Study Questionnaire for Patients with Chronic Heart Failure in Traditional Chinese Medicine Hospital" was prepared to collect general information,laboratory test results,TCM syndrome types,and Chinese and Western medicine treatment data.Patients were followed up to obtain the prognostic information,and cardiac death,worsening heart failure,cardiogenic shock and severe arrhythmia were regarded as the adverse end events.Epidate 3.1 software was used to enter prognostic factors and endpoint event information to build a database.Logistic single factor analysis was used to screen the prognostic factors of TCM and Western medicine related to poor prognosis,and co-linear diagnosis was used to determine the final modeling variables in combination with medical theories.The included cases were randomly divided into the training set and the test set according to the ratio of 9:4.The Chinese and western medicine modeling variables based on the training set were used to establish the prognosis model of patients with chronic heart failure using decision tree algorithm,and the predictive performance of the model was evaluated through the test set data.ResultA total of 383 cases of chronic heart failure were included in this study.The average follow-up time was 1.5 years,of which 56 cases had composite endpoint events.Logistic single factor analysis suggest age,systolic pressure,diastolic blood pressure,heart rate,Cardiac function grade,history of coronary heart disease,history of hypertensive heart disease,history of diabetes,history of alcohol consumption,family history of heart disease,complicated arrhythmia,complicated respiratory diseases,LVEF,NT-pro BNP,alanine transaminase,total cholesterol,high-density lipoprotein cholesterol,low density lipoprotein cholesterol,hemoglobin,D-dimer,qi deficiency and and blood stasis syndrome,Qi Yin deficiency and blood stasis syndrome,Yang Qi deficiency and blood stasis syndrome,application ARB drugs,beta blockers,application Qi-invigorating traditional Chinese medicine injections,nvigorating blood circulation and removing blood stasis traditional Chinese medicine injections in patients with a total of 27 indicators are associated with poor prognosis.Collinearity diagnosis was combined with professional medical knowledge,total cholesterol and LDL were excluded,and finally 25 indexes were determined as modeling variables.The 383 included cases were randomly divided into the training set and the test set,263 cases were in the training set and 120 cases in the test set.Based on the training set data,a decision tree algorithm was used to construct the model,which included four indexes: history of hypertensive heart disease,systolic blood pressure,NT-pro BNP and blood stasis syndrome of deficiency of Yang qi.The test set data was used to evaluate the performance of the model,and the mixed matrix was established.The classification accuracy of the model was 85.0%,the sensitivity was 12/(12+4)=75.0%,and the specificity was 90/(90+14)=86.5%.Conclusionthe prognosis of patients with chronic heart failure factors include age,systolic pressure,diastolic blood pressure,heart rate,Cardiac function grade,history of coronary heart disease,history of hypertensive heart disease,history of diabetes,history of alcohol consumption,family history of heart disease,complicated arrhythmia,complicated respiratory diseases,LVEF,NT-pro BNP,alanine transaminase,high-density lipoprotein cholesterol,hemoglobin,D-dimer,qi deficiency and blood stasis syndrome,Qi Yin deficiency and blood stasis syndrome,Yang Qi deficiency and blood stasis syndrome,application ARB drugs,beta blockers,application Qi-invigorating traditional Chinese medicine injections,nvigorating blood circulation and removing blood stasis traditional Chinese medicine injections.2.Based on the prognostic factors of Chinese and western medicine,decision tree algorithm can be used to construct the prognostic evaluation model of patients with chronic heart failure,with high prediction accuracy and strong generalization ability,which can provide reference for the prognostic evaluation of patients with chronic heart failure in traditional Chinese medicine hospital.
Keywords/Search Tags:prognosis model, decision tree algorithm, chronic heart failure, Prognostic factors
PDF Full Text Request
Related items