Acute myocardial infarction (AMI), as the leading cause of death among cardiovascular diseases, has its diagnosis and treatment efficiency directly affecting survival. Although the current diagnosis and treatment system has significantly improved in-hospital outcomes, delays in seeking medical care due to patients' insufficient awareness and out-of-hospital deaths are common, representing the biggest bottleneck in improving diagnostic and treatment capabilities. This study takes intelligent-assisted diagnosis of AMI as the entry point and proposes a technical approach that combines a deep learning algorithm based on 12-lead electrocardiograms with wearable monitoring devices. By utilizing morphological feature extraction and deep learning models, it aims to achieve early identification and warning of AMI. The study plans to build a multi-center AMI long-term follow-up cohort covering the Beijing area based on spatiotemporal heterogeneous data. By integrating and forming a precise high-risk cohort of 3,000 acute myocardial infarction cases, it seeks to construct an AMI risk prediction model that combines deep learning with a retrieval-augmented generative expert system, breaking through bottlenecks in ECG recognition and temporal prediction, enhancing model generalization and transferability. Ultimately, it will support the application of wearable devices, shorten pre-hospital delays, achieve early warning and precise diagnosis of AMI, reduce reinfarction and cardiac-related mortality, and carry significant clinical and public health importance.
Multivessel coronary artery disease (defined as ≥50% stenosis in at least 2 coronary artery regions, including the left main coronary artery)
Previous myocardial infarction
Patients with diabetes currently undergoing glucose-lowering treatment
Chronic kidney disease (CKD) defined as an estimated glomerular filtration rate <60 mL/min/1.73 m² with a known history of chronic kidney disease or biomarkers indicating chronic kidney damage
Researchers consider diseases or conditions that are not suitable for participation in this study (such as mental illness, significant cognitive impairment, neurodegenerative diseases, advanced malignant tumors) or situations (such as inability to communicate well with researchers in the local language, unwillingness to comply with study procedures/instructions, inability to understand study-specific training, physically fragile and vulnerable subjects).
Participation in a clinical trial involving drugs or devices within 3 months prior to enrollment.
Women who are pregnant, planning to become pregnant, or breastfeeding.
Known life-threatening diseases with an expected survival of less than 12 months.
The integrated team covers preliminary cohorts with multi-dimensional data, including multi-center clinical, imaging, and sample information (total cases \>300,000). Based on cohort quality and risk factors, multi-dimensional data is collected on high-risk patients (such as those with previous myocardial infarction, multi-vessel disease, CKD, DM, etc.) to complete the data. The primary endpoint is the time to the first occurrence of acute myocardial infarction within one year after enrollment. Follow-up points are set according to myocardial reinfarction characteristics and needs, and a long-term follow-up plan is formulated (including: frequency of follow-up, follow-up methods, laboratory tests, wearable device data, etc.). Regular follow-up and supplementation of multi-modal data are conducted, ultimately completing a 3,000-case multi-dimensional AMI cohort.
Cohort
Prospective
Acute Myocardial Infarction Risk Prediction Model
Diagnostic testFor high-risk patients with myocardial infarction, screen and integrate relevant previous prospective, multicenter AMI cohorts, and establish a multicenter, multi-treatment precise high-risk acute myocardial infarction cohort in the Beijing region, with long-term follow-up and supplementation of multidimensional data. Subsequently, based on semantic knowledge-guided cross-modal and cross-timepoint data alignment, use domain adaptation methods to perform fusion modeling of spatiotemporal and modal heterogeneous AMI cohorts. Through multimodal interpretable artificial intelligence models, mine the fused models to complete the construction and validation of an AMI risk prediction model based on spatiotemporally heterogeneous data.
The time of the first occurrence of acute myocardial infarction (AMI) within 1 year after enrollment.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
