Artificial Intelligence Uncovered Clinical Factors for Cardiovascular Events in Myocardial Infarction Patients with...

Area of Science:

• Cardiology
• Endocrinology
• Artificial Intelligence in Medicine

Background:

• Glucose intolerance (GI), encompassing prediabetes and diabetes, significantly increases cardiovascular event risk in patients with myocardial infarction (MI).
• Identifying specific clinical risk factors for cardiovascular events in this high-risk population is crucial for targeted interventions.

Purpose of the Study:

• To identify clinical risk factors associated with cardiovascular events in patients who have experienced myocardial infarction (MI) and have glucose intolerance (GI).

Main Methods:

• Utilized a limitless-arity multiple testing procedure, an AI-driven data mining approach.
• Analyzed over 415,000 combinations of clinical parameters in pooled data from the ABC and PPAR trials.
• Included 1476 patients with MI and GI.

Main Results:

• Identified 242 combinations predicting hospitalization for percutaneous coronary intervention, non-fatal MI, worsening heart failure, or all-cause mortality.
• Proton pump inhibitor (PPI) use and plasma glucose > 200 mg/dL after oral glucose tolerance test were linked to coronary events.
• Elevated plasma BNP levels (> 200 pg/dL) predicted coronary, cardiac, and heart failure events.
• Diuretic use, advanced age, and lack of anti-dyslipidemia drugs were associated with cardiovascular events.
• All identified factors correlated with all-cause mortality.

Conclusions:

• Progression of GI, PPI use, and high plasma BNP levels are significant predictors of coronary events or recurrent MI in MI patients with GI.
• Artificial intelligence (AI) offers a powerful method for uncovering previously unrecognized risk factors for cardiovascular events.