Identification of risk genes associated with myocardial infarction based on the recursive feature elimination algorithm and support vector machine classifier

Identification of Risk Genes Associated with Myocardial Infarction-Big Data Analysis and Literature Review

Acute myocardial infarction occurs when blood supply to a particular coronary artery is cut off, causing ischemia or hypoxia and subsequent heart muscle destruction in the vascularized area. With a mortality rate of 17% per year, myocardial infarction (MI) is still one of the top causes of death globally. Numerous studies have been done to identify the genetic risk factors for myocardial infarction, as a positive family history of heart disease is one of the most potent cardiovascular risk factors. The goal of this review is to compile all the information currently accessible in the literature on the genes associated with AMI. We performed a big data analysis of genes associated with acute myocardial infarction, using the following keywords: "myocardial infarction", "genes", "involvement", "association", and "risk". The analysis was done using PubMed, Scopus, and Web of Science. Data from the title, abstract, and keywords were exported as text files and imported into an Excel spreadsheet. Its analysis was carried out using the VOSviewer v. 1.6.18 software. Our analysis found 28 genes which are mostly likely associated with an increased risk for AMI, including: PAI-1, CX37, IL18, and others. Also, a correlation was made between the results obtained in the big data analysis and the results of the review. The most important genes increasing the risk for AMI are lymphotoxin-a gene (LTA), LGALS2, LDLR, and APOA5. A deeper understanding of the underlying functional genomic circuits may present new opportunities for research in the future.

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach

Background

Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific.

Objective

Apply machine learning for the prediction and identification of factors associated with short and long-term mortality in Asian STEMI patients and compare with a conventional risk score.

Methods

The National Cardiovascular Disease Database for Malaysia registry, of a multi-ethnic, heterogeneous Asian population was used for in-hospital (6299 patients), 30-days (3130 patients), and 1-year (2939 patients) model development. 50 variables were considered. Mortality prediction was analysed using feature selection methods with machine learning algorithms and compared to Thrombolysis in Myocardial Infarction (TIMI) score. Invasive management of varying degrees was selected as important variables that improved mortality prediction.

Results

Model performance using a complete and reduced variable produced an area under the receiver operating characteristic curve (AUC) from 0.73 to 0.90. The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.846–0.910; vs AUC = 0.81, 95% CI:0.772–0.845, AUC = 0.90, 95% CI: 0.870–0.935; vs AUC = 0.80, 95% CI: 0.746–0.838, AUC = 0.84, 95% CI: 0.798–0.872; vs AUC = 0.76, 95% CI: 0.715–0.802, p < 0.0001 for all). TIMI score underestimates patients’ risk of mortality. 90% of non-survival patients are classified as high risk (>50%) by machine learning algorithm compared to 10–30% non-survival patients by TIMI. Common predictors identified for short- and long-term mortality were age, heart rate, Killip class, fasting blood glucose, prior primary PCI or pharmaco-invasive therapy and diuretics. The final algorithm was converted into an online tool with a database for continuous data archiving for algorithm validation.

Conclusions

In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. Ongoing continuous testing and validation will allow for better risk stratification and potentially alter management and outcomes in the future.

In Silico Analysis of Differential Gene Expression in Three Common Rat Models of Diastolic Dysfunction

Standard therapies for heart failure with preserved ejection fraction (HFpEF) have been unsuccessful, demonstrating that the contribution of the underlying diastolic dysfunction pathophysiology differs from that of systolic dysfunction in heart failure and currently is far from being understood. Complicating the investigation of HFpEF is the contribution of several comorbidities. Here, we selected three established rat models of diastolic dysfunction defined by three major risk factors associated with HFpEF and researched their commonalities and differences. The top differentially expressed genes in the left ventricle of Dahl salt sensitive (Dahl/SS), spontaneous hypertensive heart failure (SHHF), and diabetes 1 induced HFpEF models were derived from published data in Gene Expression Omnibus and used for a comprehensive interpretation of the underlying pathophysiological context of each model. The diversity of the underlying transcriptomic of the heart of each model is clearly observed by the different panel of top regulated genes: the diabetic model has 20 genes in common with the Dahl/SS and 15 with the SHHF models. Advanced analytics performed in Ingenuity Pathway Analysis (IPA^®) revealed that Dahl/SS heart tissue transcripts triggered by upstream regulators lead to dilated cardiomyopathy, hypertrophy of heart, arrhythmia, and failure of heart. In the heart of SHHF, a total of 26 genes were closely linked to cardiovascular disease including cardiotoxicity, pericarditis, ST-elevated myocardial infarction, and dilated cardiomyopathy. IPA Upstream Regulator analyses revealed that protection of cardiomyocytes is hampered by inhibition of the ERBB2 plasma membrane-bound receptor tyrosine kinases. Cardioprotective markers such as natriuretic peptide A (NPPA), heat shock 27 kDa protein 1 (HSPB1), and angiogenin (ANG) were upregulated in the diabetes 1 induced model; however, the model showed a different underlying mechanism with a majority of the regulated genes involved in metabolic disorders. In conclusion, our findings suggest that multiple mechanisms may contribute to diastolic dysfunction and HFpEF, and thus drug therapies may need to be guided more by phenotypic characteristics of the cardiac remodeling events than by the underlying molecular processes.