Deep Phenotyping and Prediction of Long-term Cardiovascular Disease: Optimized by Machine Learning

BackgroundPrediction of cardiovascular disease (CVD) is important in clinical practice. Machine learning (ML) may offer an improved alternative to current CVD risk stratification in individual patients. We aim to identify important predictors and compare ML models with traditional models according to their prediction performance in a large long-term follow-up cohort.MethodsThe Atherosclerosis Risk in Communities (ARIC) study was designed to study the progression of subclinical disease to cardiovascular events over a 25-year follow-up period. All phenotypic variables at visit 1 were obtained. All-cause death, CVD, and coronary heart disease were the outcomes for analysis. The ML framework involved variable selection using the random survival forest (RSF) method, model building, and 5-fold cross-validation. Model performance was evaluated by discrimination using the Harrell concordance index (C-index), accuracy using the Brier score (BS), and interpretability using the number of variables in the model.ResultsOf the 14,842 participants in ARIC, the average age was 54.2 years, with 45.2% male and 26.2% Black participants. Thirty-eight unique variables were selected in the RSF top 20 importance ranking of all 6 outcomes. Aging, hypertension, glucose metabolism, renal function, coagulation, adiposity, and sodium retention dominated the predictions of all outcomes. The ML models outperformed the regression models and established risk scores with a higher C-index, lower BS, and varied interpretability.ConclusionsThe ML framework is useful for identifying important predictors of CVD and for developing models with robust performance compared with existing risk models.     

Identification of key genes and pathways in discoid lupus skin via bioinformatics analysis

Discoid lupus erythematosus (DLE) is the most common skin manifestation of lupus; however, the molecular mechanisms underlying DLE remain unknown. Therefore, we aimed to identify key differentially expressed genes (DEGs) in discoid lupus skin and investigate their potential pathways.To identify candidate genes involved in the occurrence and development of the disease, we downloaded the microarray datasets {"type":"entrez-geo","attrs":{"text":"GSE52471","term_id":"52471"}}GSE52471 and {"type":"entrez-geo","attrs":{"text":"GSE72535","term_id":"72535"}}GSE72535 from the Gene Expression Database (GEO). DEGs between discoid lupus skin and normal controls were selected using the GEO2R tool and Venn diagram software (http://bioinformatics.psb.ugent.be/webtools/Venn/). The Database for Annotation, Visualization, and Integrated Discovery (DAVID), Enrichr, and Cytoscape ClueGo were used to analyze the Kyoto Encyclopedia of Gene and Genome pathways and gene ontology. Protein-protein interactions (PPIs) of these DEGs were further assessed using the Search Tool for the Retrieval Interacting Genes version 10.0.Seventy three DEGs were co-expressed in both datasets. DEGs were predominantly upregulated in receptor signaling pathways of the immune response. In the PPI network, 69 upregulated genes were selected. Furthermore, 4 genes (CXCL10, ISG15, IFIH1, and IRF7) were found to be significantly upregulated in the RIG-I-like receptor signaling pathway, from analysis of Enrichr and Cytoscape ClueGo.The results of this study may provide new insights into the potential molecular mechanisms of DLE. However, further experimentation is required to confirm these findings.