MedPath

Research on the Diagnostic Value of Machine Learning Model Based on Clinical Data in Patients With Coronary Heart Disease

Conditions
Coronary Heart Disease
Acute Myocardial Infarction
Angina
Interventions
Diagnostic Test: Machine learning model diagnosis
Registration Number
NCT05018715
Lead Sponsor
Xiang Ma
Brief Summary

Based on the clinical data of patients, a machine learning model for coronary heart disease diagnosis was established to evaluate whether the model could improve the accuracy of coronary heart disease diagnosis, and to evaluate its authenticity, reliability and benefits.

Detailed Description

A total of 300 patients with CHD WHO were hospitalized in the First Affiliated Hospital of Xinjiang Medical University from August 2021 to February 2022 were selected, all of whom met the DIAGNOSTIC criteria of CHD formulated by the World Health Organization (WHO) and excluded diseases such as highly severe valvular disease and congenital heart disease.A total of 300 healthy subjects from the First Affiliated Hospital of Xinjiang Medical University during the same period were selected as controls.Observation indicators included: Clinical indicators collected included: General conditions: gender, age, medical history;Blood biochemical indexes, such as blood routine, liver function, kidney function, blood lipid, blood glucose, myocardial markers, electrolyte, serum creatinine concentration, body mass index, BNP and other indicators;Related tests such as ELECTROcardiogram, holter electrocardiogram, cardiac ultrasound (left atrial diameter, ascending aorta, ventricular septal thickness, left posterior wall thickness, right ventricular diameter, ejection fraction, abnormal ventricular wall motion, evidence of infarction or ischemia, valve abnormality, congenital heart disease, etc.);Signs include: audio data of heart sounds in nine parts of precardiac area;Medication status.All blood biochemical indexes and examinations were completed in the laboratory department and ultrasound department of our hospital, and the physical signs were completed in the ward.The results of coronary angiography, pre-hospital and post-hospital echocardiography and other related data were recorded.Machine learning model was constructed based on clinical data to assist diagnosis of patients with coronary heart disease

Recruitment & Eligibility

Status
UNKNOWN
Sex
All
Target Recruitment
600
Inclusion Criteria
  • Patients who meet the diagnostic criteria for CHD set by the World Health Organization
Exclusion Criteria
  • Exclude serious valvular disease, congenital heart disease, respiratory system and other diseases.

Study & Design

Study Type
OBSERVATIONAL
Study Design
Not specified
Arm && Interventions
GroupInterventionDescription
coronary heart diseaseMachine learning model diagnosisA total of 300 patients with CHD WHO were hospitalized in the First Affiliated Hospital of Xinjiang Medical University from August 2021 to February 2022 were selected, all of whom met the DIAGNOSTIC criteria of CHD formulated by the World Health Organization (WHO) and excluded diseases such as highly severe valvular disease and congenital heart disease
Primary Outcome Measures
NameTimeMethod
make a definite diagnosis of CHD2021-2023

Based on the patient's typical angina pectoris symptoms, combined with the patient's age and coronary heart disease risk factors, and excluding other causes of angina pectoris, a preliminary diagnosis can be established. Coronary CTA, coronary angiography and other examinations find direct evidence of coronary artery stenosis, which can confirm the diagnosis

Secondary Outcome Measures
NameTimeMethod

Trial Locations

Locations (1)

The first affiliated Hospital of Xinjiang Medical University

🇨🇳

Ürümqi, Xinjiang, China

© Copyright 2025. All Rights Reserved by MedPath