Multiple-model machine learning identifies potential functional genes in dilated cardiomyopathy

Abstract

IntroductionMachine learning (ML) has gained intensive popularity in various fields, such as disease diagnosis in healthcare. However, it has limitation for single algorithm to explore the diagnosing value of dilated cardiomyopathy (DCM). We aim to develop a novel overall normalized sum weight of multiple-model MLs to assess the diagnosing value in DCM.MethodsGene expression data were selected from previously published databases (six sets of eligible microarrays, 386 samples) with eligible criteria. Two sets of microarrays were used as training; the others were studied in the testing sets (ratio 5:1). Totally, we identified 20 differently expressed genes (DEGs) between DCM and control individuals (7 upregulated and 13 down-regulated).ResultsWe developed six classification ML methods to identify potential candidate genes based on their overall weights. Three genes, serine proteinase inhibitor A3 (SERPINA3), frizzled-related proteins (FRPs) 3 (FRZB), and ficolin 3 (FCN3) were finally identified as the receiver operating characteristic (ROC). Interestingly, we found all three genes correlated considerably with plasma cells. Importantly, not only in training sets but also testing sets, the areas under the curve (AUCs) for SERPINA3, FRZB, and FCN3 were greater than 0.88. The ROC of SERPINA3 was significantly high (0.940 in training and 0.918 in testing sets), indicating it is a potentially functional gene in DCM. Especially, the plasma levels in DCM patients of SERPINA3, FCN, and FRZB were significant compared with healthy control.DiscussionSERPINA3, FRZB, and FCN3 might be potential diagnosis targets for DCM, Further verification work could be implemented.

Red blood cell distribution width/albumin ratio is a novel risk factor of incidence and long-term mortality in chronic heart failure patients: three large cohorts from China and America

“…Many factors (e.g., age[3] and atrial fibrillation[4]) are involved in the evolution of this process, and controlling these factors[5] can decrease or even block the development of CHF. Although many indicators had good prognoses in CHF patients, they are difficult to promote in non-CHF patients (e.g., SOFA score[6, 7], or RNA test[8]), because the relevant tests are not generally performed on non-CHF populations. Therefore, searching for clinically common and readily available predictors is essential in preventing the evolution of CHF.…”

Integration of Machine Learning to Identify Diagnostic Genes in Leukocytes for Acute Myocardial Infarction Patients

“…Still, these approaches may have missed potential genes [20]. Compared with a single ML algorithm, the integrated ML (IML) approach [21][22][23] we developed is more advantageous in variable screening and model building. IML helps identify potential genes mistakenly deleted by a single ML and find more meaningful variables [21].…”