Early identification of STEMI patients with emergency chest pain using lipidomics combined with machine learning
Zhi Shang1, Yang Liu2, Yu-Yao Yuan2
1Department of Cardiology, Peking University Third Hospital, NHC Key Laboratory of Cardiovascular Molecular Biology and Regulatory Peptides, Key Laboratory of Molecular Cardiovascular Science, Ministry of Education, Beijing, China.
Insights
Early detection of ST-segment elevated myocardial infarction (STEMI) is possible using a novel lipidomic model. This predictive model accurately identifies STEMI patients, even with normal cardiac troponin levels, aiding in timely intervention.
Area of Science:
- Biochemistry
- Cardiovascular Medicine
- Biomarker Discovery
Background:
- ST-segment elevated myocardial infarction (STEMI) is a critical cardiovascular emergency.
- Early diagnosis of STEMI is crucial for effective treatment and improved patient outcomes.
- Current diagnostic methods may have limitations in very early stages.
Purpose of the Study:
- To investigate differential lipid expression in STEMI patients compared to those with chest pain and no coronary artery disease (CAD).
- To develop and validate a predictive model for early STEMI detection using lipid profiles.
Main Methods:
- A nested case-control study involving STEMI patients and controls with chest pain.
- Untargeted lipidomics to analyze a wide range of lipid molecules.
- LASSO regression and XGBoost with a greedy algorithm for feature selection of predictive lipids.
Main Results:
- 1925 lipid molecules were detected, with significant differential expression in 93 (positive ion mode) and 73 (negative ion mode) molecules.
- Key differentially expressed lipid subclasses included diacylglycerol (DG), lysophophatidylcholine (LPC), acylcarnitine (CAR), and free fatty acids (FA).
- A predictive model using three specific lipids (PC, PI, LPI) demonstrated high accuracy (AUC 0.972 derivation, 0.967 validation) and correctly identified 18 of 19 STEMI patients with normal troponin.
Conclusions:
- Specific lipid profiles are significantly altered in STEMI patients.
- A multi-lipid predictive model, derived from machine learning feature selection, offers a highly accurate and early method for STEMI prediction.
- This lipidomic approach shows promise for improving early diagnosis of STEMI, even before troponin elevation.
Objectives:
To analyze the differential expression of lipid spectrum between ST-segment elevated myocardial infarction (STEMI) and patients with emergency chest pain and excluded coronary artery disease (CAD), and establish the predictive model which could predict STEMI in the early stage.
Methods:
We conducted a single-center, nested case-control study using the emergency chest pain cohort of Peking University Third Hospital. Untargeted lipidomics were conducted while LASSO regression as well as XGBoost combined with greedy algorithm were used to select lipid molecules.
Results:
Fifty-two STEMI patients along with 52 controls were enrolled. A total of 1925 lipid molecules were detected. There were 93 lipid molecules in the positive ion mode which were differentially expressed between the STEMI and the control group, while in the negative ion mode, there were 73 differentially expressed lipid molecules. In the positive ion mode, the differentially expressed lipid subclasses were mainly diacylglycerol (DG), lysophophatidylcholine (LPC), acylcarnitine (CAR), lysophosphatidyl ethanolamine (LPE), and phosphatidylcholine (PC), while in the negative ion mode, significantly expressed lipid subclasses were mainly free fatty acid (FA), LPE, PC, phosphatidylethanolamine (PE), and phosphatidylinositol (PI). LASSO regression selected 22 lipids while XGBoost combined with greedy algorithm selected 10 lipids. PC (15: 0/18: 2), PI (19: 4), and LPI (20: 3) were the overlapping lipid molecules selected by the two feature screening methods. Logistic model established using the three lipids had excellent performance in discrimination and calibration both in the derivation set (AUC: 0.972) and an internal validation set (AUC: 0.967). In 19 STEMI patients with normal cardiac troponin, 18 patients were correctly diagnosed using lipid model.
Conclusions:
The differentially expressed lipids were mainly DG, CAR, LPC, LPE, PC, PI, PE, and FA. Using lipid molecules selected by XGBoost combined with greedy algorithm and LASSO regression to establish model could accurately predict STEMI even in the more earlier stage.
More Related Videos
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Related Concept Videos
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:30Acute Coronary Syndrome I: Introduction
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...