January 11, 2023Frontiers in Cardiovascular MedicineOpen Access

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

View Full Paper

Ask AI

Bookmark

Why the study?

Single machine learning algorithms have limitations for exploring the diagnostic value in dilated cardiomyopathy.

Can a multiple-model machine learning approach identify functional genes with high diagnostic value for dilated cardiomyopathy?

Structured PICO

Can a multiple-model machine learning approach identify functional genes with high diagnostic value for dilated cardiomyopathy?

Population

386 microarray samples (207 DCM, 179 healthy controls) from 6 GEO datasets, plus a clinical validation cohort of 24 individuals (12 DCM, 12 healthy controls).

Intervention

Multiple-model machine learning (LASSO, SVM, RF, DT, GBM, NN) based on overall normalized sum weights to identify diagnostic genes.

Comparator

Healthy controls.

Outcome

Diagnostic accuracy (Area Under the Curve [AUC]) of identified candidate genes for differentiating DCM from healthy controls.surrogate

A multiple-model machine learning approach identified SERPINA3, FRZB, and FCN3 as potential diagnostic biomarkers for dilated cardiomyopathy, which was confirmed by significantly altered plasma levels in patients.

Limitations

Inadequate validation (small sample size for clinical validation)
Black box phenomenon of machine learning models (especially neural networks)
Lack of clinical features such as age or race which might trigger bias

Implication

May support multi-model ML for DCM diagnosis; leaves open prospective validation before any clinical adoption.

Abstract

Introduction Machine 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. Methods Gene 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). Results We 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. Discussion SERPINA3, FRZB, and FCN3 might be potential diagnosis targets for DCM, Further verification work could be implemented.