Machine learning and multi-omics integration: advancing cardiovascular translational research and clinical practice

Area of Science:

• Biomedical research
• Cardiovascular medicine
• Computational biology

Background:

• Cardiovascular diseases (CVDs) represent a growing global health challenge.
• Multi-omics approaches provide molecular insights into complex physiological and pathological changes in CVDs.
• Managing and interpreting large-scale omics data is a significant hurdle in biomedical research.

Purpose of the Study:

• To review methods for integrating artificial intelligence (AI), particularly machine learning, with omics data in cardiovascular research.
• To summarize AI models that utilize multi-omics data for exploring CVD mechanisms and clinical practice.
• To highlight AI's role in extracting molecular information to address knowledge gaps in cardiovascular diseases.

Main Methods:

• Review of AI and machine learning methodologies applied to omics data.
• Analysis of representative AI models in cardiovascular disease studies.
• Discussion of data integration strategies for multi-omics datasets.

Main Results:

• AI integrated with multi-omics data shows promise in cardiovascular studies.
• AI effectively extracts potential molecular information, addressing current knowledge gaps.
• AI facilitates exploration of cardiovascular diseases from underlying mechanisms to clinical practice.

Conclusions:

• AI and omics integration offers powerful tools for advancing cardiovascular disease research.
• Challenges and opportunities exist in translating these integrated approaches into routine clinical practice.
• Future AI models are anticipated for broader applications in cardiovascular medicine.