Risk stratification of ST-segment elevation myocardial infarction (STEMI) patients using machine learning based on lipid profiles

Abstract

Background Numerous studies have revealed the relationship between lipid expression and increased cardiovascular risk in ST-segment elevation myocardial infarction (STEMI) patients. Nevertheless, few investigations have focused on the risk stratification of STEMI patients using machine learning algorithms. Methods A total of 1355 STEMI patients who underwent percutaneous coronary intervention were enrolled in this study during 2015–2018. Unsupervised machine learning (consensus clustering) was applied to the present cohort to classify patients into different lipid expression phenogroups, without the guidance of clinical outcomes. Kaplan-Meier curves were implemented to show prognosis during a 904-day median follow-up (interquartile range: 587–1316). In the adjusted Cox model, the association of cluster membership with all adverse events including all-cause mortality, all-cause rehospitalization, and cardiac rehospitalization was evaluated. Results All patients were classified into three phenogroups, 1, 2, and 3. Patients in phenogroup 1 with the highest Lp(a) and the lowest HDL-C and apoA1 were recognized as the statin-modified cardiovascular risk group. Patients in phenogroup 2 had the highest HDL-C and apoA1 and the lowest TG, TC, LDL-C and apoB. Conversely, patients in phenogroup 3 had the highest TG, TC, LDL-C and apoB and the lowest Lp(a). Additionally, phenogroup 1 had the worst prognosis. Furthermore, a multivariate Cox analysis revealed that patients in phenogroup 1 were at significantly higher risk for all adverse outcomes. Conclusion Machine learning-based cluster analysis indicated that STEMI patients with increased concentrations of Lp(a) and decreased concentrations of HDL-C and apoA1 are likely to have adverse clinical outcomes due to statin-modified cardiovascular risks. Trial registration ChiCTR1900028516 (http://www.chictr.org.cn/index.aspx).

Main differences between two highly effective lipid-lowering therapies in subclasses of lipoproteins in patients with acute myocardial infarction

“…Recently, a machine learning-based clustering study among patients with STEMI under statin therapy evaluated a lipid panel composed of apo A1, Apo B, HDL-C, triglycerides, LDL-C, total cholesterol and lipoprotein (a) [Lp (a)]. The study revealed that the cluster with high levels of Lp (a) and low levels of apoA1 and HDL-C identified those patients with the highest recurrent events and mortality [ 36 ].…”

Clinically Distinct Subtypes of Acute Kidney Injury on Hospital Admission Identified by Machine Learning Consensus Clustering

“…It can search for similarities and heterogeneities among large categories of data variables and isolate them into clinically meaningful clusters [8,[15][16][17]. Recent studies have shown that disease subtypes determined by ML clustering methods can forecast different clinical outcomes [18,19].…”

Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia

“…Consensus clustering is an unsupervised ML approach utilized to identify distinct phenotypes in heterogeneous patient populations. It can be used to assess similarities and differences in large datasets with many variables, and subsequently distinguish patients into novel clusters with distinct phenotypes [12,15,16]. Recent studies have demonstrated that ML consensus clustering can identify disease subtypes that carry different clinical outcomes [17,18].…”