Establishment of Disease Characteristics and a Chinese Medicine Prognosis Risk Model Based on a Large-Scale Database After Coronary Revascularization

This study aims to develop a risk prediction model for patients who have undergone coronary revascularization (such as stent placement or bypass surgery). After these procedures, some patients still experience heart-related problems like chest pain, heart attack, or rehospitalization. This study will enroll 600 patients from multiple hospitals in China and follow them for 12 months. At enrollment and at 12, 24, 36, and 48 weeks after surgery, researchers will collect clinical information (including traditional Chinese medicine symptoms, blood tests, heart imaging) and biological samples (blood and tongue coating). Using artificial intelligence, the study will build a predictive model that combines Western medical data with traditional Chinese medicine characteristics. The goal is to better identify patients at higher risk of future heart events, so that personalized prevention and management can be provided. The study does not involve any experimental treatment or intervention - it is purely observational.

Study Overview

• Status: Not yet recruiting
• Conditions: Coronary Artery Disease; Myocardial Revascularization; Postoperative Period

Detailed Description

This is a multicenter, prospective cohort study conducted at five sites in China. The study aims to develop and validate a prognostic risk model for major adverse cardiovascular events (MACE) in patients after coronary revascularization (percutaneous coronary intervention or coronary artery bypass grafting).

Study population: A total of 600 eligible patients aged ≥18 years who have undergone coronary revascularization will be enrolled consecutively. Key exclusion criteria include severe heart failure, malignant arrhythmias, severe pulmonary or liver/kidney dysfunction, pregnancy, psychiatric disorders, and poor compliance.

Data collection: At baseline (enrollment), the following data are collected: demographics, medical history, surgical characteristics (e.g., access route, number of stents, target vessels), vital signs, laboratory tests (complete blood count, cardiac enzymes, liver/kidney function, lipids, glucose), echocardiography, 24-hour ambulatory electrocardiography, and a standardized Traditional Chinese Medicine (TCM) case report form covering symptom scores, tongue/pulse findings, and pattern elements. In addition, biological samples (blood and tongue coating) are obtained for proteomics, metabolomics, and tongue-coating microbiomics.

Follow-up: Participants are followed at 12, 24, 36, and 48 weeks post-enrollment. At each follow-up, the TCM case report form is reassessed, MACE (including all-cause death, subacute stent thrombosis, perioperative myocardial infarction, recurrent myocardial infarction, recurrent unstable angina, repeat revascularization, and rehospitalization for angina or heart failure) are recorded, and NYHA functional class and current medications are updated.

Statistical analysis: Missing data will be handled by mean imputation or K-nearest neighbors imputation. Continuous variables will be standardized using Z-scores, and categorical variables will be one-hot encoded. Feature selection will be performed using LASSO regression. Three nested prediction models will be built:

• Model_Base: Cox proportional hazards model based on routine clinical and imaging variables.
• Model_TCM: adding TCM syndrome features using machine learning algorithms (random forest, support vector machine).
• Model_Full: further integrating multi-omics biomarkers using deep learning methods (convolutional neural network, transformer).

Model performance will be assessed by discrimination (area under the ROC curve), calibration, and decision curve analysis. Internal validation will use k-fold cross-validation, and external validation will be conducted in at least three independent hospitals. The targeted predictive accuracy (area under the curve) is above 85%. All analyses will be performed using SPSS 26.0, Python, and R.

Ethics: The study protocol has been approved by the ethics committee of the lead site (The Third Affiliated Hospital of Zhejiang Chinese Medical University) and will be approved by participating centers. Written informed consent will be obtained from all participants.

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

Contacts and Locations

• Study Contact: Name: Liu Qiang; Phone Number: 13588121905; Email: 19981011@zcmu.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Adult patients (≥18 years) who have undergone coronary revascularization (percutaneous coronary intervention or coronary artery bypass grafting) for coronary artery disease. Participants are recruited consecutively from the cardiology wards and outpatient clinics of three tertiary hospitals in China, including The Third Affiliated Hospital of Zhejiang Chinese Medical University (lead site), Zhejiang Provincial People's Hospital, The First Affiliated Hospital of Zhejiang Chinese Medical University.

Description

Inclusion Criteria:

• Diagnosis of coronary artery disease with prior coronary revascularization (PCI or CABG)
• Age ≥ 18 years
• Signed informed consent

Exclusion Criteria:

• Malignant arrhythmias, severe heart failure, myocardial disease, or structural heart disease
• Severe pulmonary insufficiency, severe liver or kidney dysfunction, severe electrolyte disturbances
• Pregnancy or breastfeeding
• Severe psychiatric disorders, malignant tumors, hematologic diseases, rheumatic immune diseases, or severe infection
• Poor compliance or any other reason making the participant unsuitable for the study

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Adults post-coronary revascularization.; Patients aged ≥18 years who underwent coronary revascularization (PCI or CABG). Consecutive enrollment from 5 Chinese hospitals. Prospective follow-up at 12, 24, 36, and 48 weeks post-enrollment. Assessments include MACE (all-cause death, stent thrombosis, myocardial infarction, unstable angina, repeat revascularization, rehospitalization), TCM syndrome score, NYHA class, echocardiography, ambulatory ECG, and biospecimens (blood and tongue coating for proteomics, metabolomics, microbiomics). No intervention is assigned.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Major Adverse Cardiovascular Events (MACE)	Composite of all-cause death, subacute stent thrombosis, perioperative myocardial infarction, recurrent myocardial infarction, recurrent unstable angina, repeat revascularization (PCI or CABG), and rehospitalization due to angina or heart failure. Events are ascertained by medical records, clinical diagnosis, coronary angiography, ECG, and cardiac enzyme/troponin measurements.	12, 24, 36, and 48 weeks post-enrollment

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Traditional Chinese Medicine (TCM) Syndrome Score	Total score of TCM symptoms and signs (chest pain, palpitations, fatigue, tongue/pulse, etc.). Each item scored 0-3 (none to severe). Sum of all items. Higher score indicates more severe symptoms. Unit of Measure: points on a scale	Baseline, 12, 24, 36, 48 weeks post-enrollment
NYHA Functional Class	Classification of heart failure symptoms based on physical activity limitation. Class I (no limitation) to IV (symptoms at rest). Unit of Measure: relative abundance / qualitative	12, 24, 36, 48 weeks post-enrollment
Multi-omics Biomarkers (exploratory)	Proteomics, metabolomics (LC-MS/MS, LC-MS/GC-MS) from blood, and 16S rRNA microbiome from tongue coating. Used to identify biomarkers associated with TCM patterns. Results reported as relative abundance or presence/absence. Unit of Measure: relative abundance / qualitative	Baseline
Left Ventricular End-Diastolic Diameter (LVEDD)	Diameter of the left ventricle at end-diastole, measured by echocardiography. Unit of Measure: mm.	Baseline
Left Ventricular End-Systolic Diameter (LVESD)	Diameter of the left ventricle at end-systole, measured by echocardiography. Unit of Measure: mm	Baseline
Left Ventricular Posterior Wall Thickness (LVPW)	Thickness of the left ventricular posterior wall in diastole, measured by echocardiography. Unit of Measure: mm.	Baseline
Interventricular Septal Thickness (IVS)	Thickness of the interventricular septum in diastole, measured by echocardiography. Unit of Measure: mm	Baseline
Left Ventricular Ejection Fraction (LVEF)	Percentage of blood ejected from the left ventricle per contraction, measured by echocardiography. Unit of Measure: %.	Baseline
Left Ventricular Fractional Shortening (FS)	Percentage change in left ventricular diameter between diastole and systole, measured by echocardiography. Unit of Measure: %	Baseline
E/A Ratio	Ratio of early (E) to late (A) ventricular filling velocities, measured by pulsed-wave Doppler echocardiography. Unit of Measure: ratio	Baseline
Mean Heart Rate (24-hour)	Average heart rate over 24 hours derived from ambulatory electrocardiography (Holter). Unit of Measure: beats per minute (bpm)	Baseline
Minimum Heart Rate (24-hour)	Lowest heart rate recorded during 24-hour ambulatory ECG, with timestamp. Unit of Measure: bpm.	Baseline
Maximum Heart Rate (24-hour)	Highest heart rate recorded during 24-hour ambulatory ECG, with timestamp. Unit of Measure: bpm.	Baseline
Total Premature Ventricular Contractions (PVCs)	Number of premature ventricular contractions recorded over 24 hours by ambulatory ECG. Unit of Measure: count per 24h	Baseline
Total Premature Atrial Contractions (PACs)	Number of premature atrial contractions recorded over 24 hours by ambulatory ECG. Unit of Measure: count per 24h	Baseline
Maximum RR Interval	Longest interval between two consecutive R waves on 24-hour ambulatory ECG, indicating cardiac pause. Unit of Measure: seconds (s)	Baseline
ST Segment Depression Maximum Amplitude	Greatest magnitude of ST segment depression during any ischemic event on 24-hour ambulatory ECG. Unit of Measure: mm (or mV)	Baseline
ST Segment Depression Longest Duration	Longest duration of a single ST segment depression event on 24-hour ambulatory ECG. Unit of Measure: minutes (min)	Baseline
SDNN (Heart Rate Variability)	Standard deviation of all normal-to-normal R-R intervals over 24 hours, a measure of heart rate variability. Unit of Measure: milliseconds (ms)	Baseline

Collaborators and Investigators

• Sponsor: Liu Qiang

Study record dates

Study Major Dates

• Study Start (Estimated): July 1, 2026
• Primary Completion (Estimated): June 30, 2028
• Study Completion (Estimated): December 31, 2028

Study Registration Dates

• First Submitted: May 15, 2026
• First Submitted That Met QC Criteria: May 21, 2026
• First Posted (Actual): May 29, 2026

Study Record Updates

• Last Update Posted (Actual): May 29, 2026
• Last Update Submitted That Met QC Criteria: May 21, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Heart Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Coronary Disease; Myocardial Ischemia; Coronary Artery Disease
• Other Study ID Numbers: ZSLL-KY-2026-027-01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data (IPD) will not be shared because the informed consent obtained from participants did not include provisions for data sharing beyond the primary study. Additionally, the data contain sensitive clinical information and biospecimen-derived multi-omics data, which may raise privacy and ethical concerns. Access to de-identified data may be considered upon reasonable request to the principal investigator, subject to institutional and ethics committee approval.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No