Artificial Intelligence With Deep Learning and Genes on Cardiovascular Disease

Application of Artificial Intelligence Deep Learning to the Correlation Between Cardiovascular Disease and Individualized Differences

An association study with large database from electronic medical record system, images, outcome analysis and genetic single nucleotide polymorphism variations by machine learning and artificial intelligence methods in a Taiwanese and Chinese medical center based population

Study Overview

• Status: Unknown
• Conditions: Cardiovascular Diseases
• Intervention / Treatment: Other: ASCVD risk score

Detailed Description

In recent years, the analysis of big data database combined with computer deep learning has gradually played an important role in biomedical technology. For a large number of medical record data analysis, image analysis, single nucleotide polymorphism difference analysis, etc., all relevant research on the development and application of artificial intelligence can be observed extensively. For clinical indication, patients may receive a variety of cardiovascular routine examination and treatments, such as: cardiac ultrasound, multi-path ECG, cardiovascular and peripheral angiography, intravascular ultrasound and optical coherence tomography, electrical physiology, etc... The current study is for the investigative cardiovascular team to take the advantage that in addition to the examination and treatment the participants should appropriately receive, the investigators can also analyze the individual differences and using the "deep learning methodology" to analyze the difference in physical fitness, therapeutic effectiveness and the consideration in the safety of the treatment. The additional goal of this study is to improve the quality of health care, the realization of cardiovascular "precise medicine" especially with personal difference on genetic variation.

This study will analyze the differences in the individualization of cardiovascular disease between diseases and other subjects to further improve the quality of care for clinical patients. By using artificial intelligence deep learning system, the investigators hope to not only improve the diagnostic rate and also gain more accurately predict the patient's recovery, improve medical quality in the near future.

• Study Type: Observational
• Enrollment (Anticipated): 5000

Contacts and Locations

Study Locations

• Taiwan
  • Tainan, Taiwan, 704
    • Recruiting
    • Department of Internal Medicine, National Cheng Kung University Hospital
    • Contact: Pei-Tiang Hsu; Phone Number: 2389 +88662353535; Email: sz2137@yahoo.com.tw

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Pipeline for case enrollment:

1. We will enroll investigating subjects from the clinics of near 10 physicians screened by our assistant or physicians themselves, with nearly 100-120 cases/month. According to our initial experience during our previous hospital-based grant in 2018 showed feasible case number to be enrolled, nearly 1000 case within 3 months enrollment. In total, we plan to recruit 5000 subjects with cardiovascular disease or with risk factors within 3 years. (IRB approval A-ER-107-149)
2. Our study subjects will be evaluated whether they fulfill the cases criteria by an independent physician every month.
3. In comparison with disease, the risk factor only group (500 cases) will be the matching group on genetic background and outcome comparison.

Description

Inclusion Criteria:

• Patients' selection criteria and enrollment plan:

We will enroll subjects from either cardiovascular clinics or inpatients from the National Cheng Kung University Hospital from 2018 to 2021 after the signature of inform consent from patients and their families. The major enrollment criteria include one of the flowing diseases or conditions:

A. Coronary artery disease:

1. History of myocardial infarction
2. Coronary artery disease with computer tomography angiography image study with at least one vessel luminal stenosis >70%
3. Coronary artery stents implantation by hospital-based image database

4. Thallium-201 scan positive/treadmill test positive with additional 2 risk factors, including

   1. Diabetes mellitus
   2. Hypertension
   3. Dyslipidemia
   4. Family history of sudden death, coronary bypass surgery, cerebral vascular attacks (CVA), premature myocardial infarction
   5. Smoking behaviors

B. Congestive heart failure with reduced ejection fraction

1. Echocardiography left ventricular ejection fraction <40%

C. Hypertrophic cardiomyopathy:

1. Left ventricle interventricular septum（IVS) >15 mm
2. Left ventricle mass index> 200gm
3. Apical hypertrophy noted on the report with 4 chamber view

D. Atrial fibrillation

1. Recorded by Holter continuous EKG
2. Recorded by standard 12 leads complete EKG

E. Pulmonary hypertension

1. Echo with systolic pulmonary pressure (sysPAP)> 40 mmHg
2. Diagnosis of idiopathic pulmonary hypertension
3. Under pulmonary hypertension medication

F. Fabry's disease

1. α-Galactosidase (a-GAL) enzyme deficiency
2. Genetic disorder

G. Patient with only risk factors (<3 risk factors), recognized as the comparison group (>500 cases)

1. Diabetes mellitus
2. Hypertension
3. Dyslipidemia
4. Family history of sudden death, coronary bypass surgery, cerebral vascular attacks, premature myocardial infarction
5. Smoking behavior

Exclusion Criteria:

• Patients unwilling to be enrolled
• Concentration of DNA collection was inadequate after 3 times of collection

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Cardiovascular high-risk (disease) group; A. Coronary artery disease B. Congestive heart failure with reduced ejection fraction C. Hypertrophic cardiomyopathy D. Atrial fibrillation E. Pulmonary hypertension F. Fabry's disease	Other: ASCVD risk score; ASCVD score< 10% will be in the control or low-risk group
Cardiovascular Low-risk (control) group; Patient with only risk factors with ASCVD score<10% will be recognized as the comparison group	Other: ASCVD risk score; ASCVD score< 10% will be in the control or low-risk group

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Major cardiovascular events	The rate of myocardial infarction, stroke, death, cardiovascular death, heart failure with hospitalization	5 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Heart function changes	parameters and function changes from echocardiography	5 years
Lipid profiles	The percentage changes and response of lipid profile with regular lipid lowering agents	5 years
Arrhythmia events	The rate of arrhythmia associated complications and clinical events, stokes	5 years
Recurrent acute coronary events	The rate of recurrent acute coronary events with hospitalization needed or re-intervention procedures for coronary artery needed	5 years

Collaborators and Investigators

• Sponsor: National Cheng-Kung University Hospital

Study record dates

Study Major Dates

• Study Start (ACTUAL): August 28, 2018
• Primary Completion (ANTICIPATED): December 1, 2021
• Study Completion (ANTICIPATED): June 1, 2022

Study Registration Dates

• First Submitted: March 8, 2019
• First Submitted That Met QC Criteria: March 13, 2019
• First Posted (ACTUAL): March 15, 2019

Study Record Updates

• Last Update Posted (ACTUAL): March 15, 2019
• Last Update Submitted That Met QC Criteria: March 13, 2019
• Last Verified: March 1, 2019

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Cardiovascular Diseases
• Other Study ID Numbers: A-ER-107-149

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