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

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.

Study Overview

• Status: Active, not recruiting
• Conditions: Coronary Heart Disease; Acute Myocardial Infarction; Angina
• Intervention / Treatment: Diagnostic test: Machine learning model diagnosis

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

• Study Type: Observational
• Enrollment (Anticipated): 600

Contacts and Locations

Study Locations

• China
  • Xinjiang
    • Ürümqi, Xinjiang, China, 830000
      • The First Affiliated Hospital of Xinjiang Medical University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 100 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

CHD patients and healthy subjects who were hospitalized in the First Affiliated Hospital of Xinjiang Medical University from August 2021 to February 2022 were selected

Description

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 Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
coronary heart disease; 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	Diagnostic test: Machine learning model diagnosis; Machine learning model diagnosis
Healthy person; .A total of 300 healthy subjects from the First Affiliated Hospital of Xinjiang Medical University during the same period were selected as controls.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
make a definite diagnosis of CHD	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	2021-2023

Collaborators and Investigators

• Sponsor: Xiang Ma
• Collaborators: Shihezi University

Study record dates

Study Major Dates

• Study Start (Actual): August 22, 2021
• Primary Completion (Anticipated): December 31, 2023
• Study Completion (Anticipated): December 31, 2023

Study Registration Dates

• First Submitted: August 22, 2021
• First Submitted That Met QC Criteria: August 22, 2021
• First Posted (Actual): August 24, 2021

Study Record Updates

• Last Update Posted (Actual): September 2, 2021
• Last Update Submitted That Met QC Criteria: September 1, 2021
• Last Verified: September 1, 2021

More Information

Terms related to this study

• Keywords: machine learning; artificial intelligence; Deep learning; auscultation; electronic patient record
• Additional Relevant MeSH Terms: Ischemia; Pathologic Processes; Necrosis; Cardiovascular Diseases; Vascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Myocardial Infarction; Infarction; Heart Diseases; Coronary Artery Disease; Myocardial Ischemia; Coronary Disease
• Other Study ID Numbers: XMa0001

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: No

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: Yes