The goal of this clinical trial is to learn if an AI-enabled stratified management system (SMART-CHD) can improve post-discharge outcomes in adults aged 18-45 with premature coronary artery disease. The main questions it aims to answer are:

1. Does SMART-CHD reduce the combined rate of all-cause death, myocardial infarction, stroke and rehospitalization within 12 months?
2. Does SMART-CHD achieve better control of modifiable risk factors compared with usual care?

Researchers will compare SMART-CHD to standard discharge management (verbal and printed instructions on medications, follow-up timelines and lifestyle advice) to see if the AI-driven platform leads to fewer adverse events and improved risk-factor profiles.

Participants will:

1. Install and use the SMART-CHD mobile app after a 10-minute structured orientation session with supervised simulations.
2. Complete regular in-app surveys on lifestyle behaviors, laboratory/imaging results and clinical events (with OCR-powered LLM assistance).
3. Wear paired sensors for continuous monitoring of blood pressure, heart rate and other physiologic metrics.
4. Receive automated EHR data harvesting, AI-driven voice-call reminders, and real-time CRC support via a dedicated WeChat group.
5. Follow personalized, guideline-based risk-factor recommendations (diet, exercise, sleep, weight, smoking, alcohol, hypertension, dyslipidemia, diabetes).

Inclusion Criteria

1. Patients with coronary heart disease aged 18-45 years;
2. The patient or a close family member is capable of using a smartphone and mobile application (App);
3. Willing to participate in the study and able to provide written informed consent.

Exclusion Criteria

1. Severe cognitive impairment;
2. Advanced-stage malignancy;
3. Life expectancy less than 12 months;
4. Severe multi-organ failure;
5. Refusal to provide written informed consent.

Individual participant data (IPD) that underlie the results reported in publications will be shared, including all collected de-identified IPD.

Data will be available beginning 6 months after publication of the primary results and will remain available for at least 5 years thereafter.

De-identified IPD and supporting documents will be made available upon reasonable request to the Principal Investigator (PI). Requests must include a methodologically sound proposal and intended use. Access will be granted at the discretion of the PI after review of the request.