Construction and analysis of heart failure diagnosis model based on random forest and artificial neural network

Boyang, Chen; Li, Yuexing; Yiping, Yan; Haiyang, Yu; Xufei, Zhang; Guan, Lina; Chen, Yunzhi

doi:10.1097/md.0000000000031097

Cited by 4 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DEGs associated with HF identified by Boyang et al through analysis of the Omnibus database included GLUL . 23 Huang et al reported that SRGN may be a new HF target in iDCM patients, 24 and our screening results were consistent with theirs, finding that GLUL and SRGN were differentially expressed in HF, while the gene was also differentially expressed in AF. Currently, no previous studies have identified the expression and function of GLUL and SRGN in AF, which is also an innovative aspect of this study, as it reveals the relationship between GLUL , SRGN , and AF for the first time.…”

Section: Discussionsupporting

confidence: 89%

“…In this study, we found four new biomarkers highly correlated with AF and HF, namely, GLUL , NCF2 , S100A12 , and SRGN , which is different from the results of Zhuang et al Proteins encoded by GLUL belong to the glutamine synthase family and play a role in acid–base homeostasis, cell signalling, and cell proliferation. The DEGs associated with HF identified by Boyang et al through analysis of the Omnibus database included GLUL 23 . Huang et al reported that SRGN may be a new HF target in iDCM patients, 24 and our screening results were consistent with theirs, finding that GLUL and SRGN were differentially expressed in HF, while the gene was also differentially expressed in AF.…”

Section: Discussionsupporting

confidence: 84%

See 1 more Smart Citation

Identification of common mechanisms and biomarkers of atrial fibrillation and heart failure based on machine learning

Zhang,

Ding,

et al. 2024

ESC Heart Failure

View full text Add to dashboard Cite

AimsAtrial fibrillation (AF) is the most common arrhythmia. Heart failure (HF) is a disease caused by heart dysfunction. The prevalence of AF and HF were progressively increasing over time. The co‐existence of AF and HF presents a significant therapeutic challenge. In order to provide new ideas for the diagnosis of AF and HF, it is necessary to carry out biomarker related studies.Methods and resultsThe training set and validation set data of AF and HF patient samples were downloaded from the GEO database, ‘limma’ was used to compare the differences in gene expression levels between the disease group and the normal group to screen for differentially expressed genes (DEGs). Weighted correlation network analysis (WGCNA) identified the modules with the highest positive correlation with AF and HF. Functional enrichment and PPI network construction of key genes were carried out. Biomarkers were screened by machine learning. The infiltration of immune cells in AF and HF groups was evaluated by R‐packet ‘CIBERSORT’. The miRNA network was constructed and potential therapeutic agents for biomarker genes were predicted through the drugbank database. Through WGCNA analysis, it was found that the modules most positively correlated with AF and HF were MEturquoise (r = 0.21, P value = 0.09) and MEbrown (r = 0.62, P value = 8e‐12), respectively. We screened 25 genes that were highly correlated with both AF and HF. Lasso regression analysis results showed 7 and 20 core genes in AF and HF groups, respectively. The top 20 important genes in AF and HF groups were obtained as core genes by RF model analysis. Four biomarkers were obtained after the intersection of core genes in four groups, namely, GLUL, NCF2, S100A12, and SRGN. The diagnostic efficacy of four genes in AF validation sets was good (AUC: GLUL 0.76, NCF2 0.64, S100A12 0.68, and SRGN 0.76), as well as in the HF validation set (AUC: GLUL 0.76, NCF2 0.84, S100A12 0.92, and SRGN 0.68). The highest correlation with neutrophils was observed for GLUL, NCF2, and S100A12, while SRGN exhibited the strongest correlation with T cells CD4 memory resting in the AF group. GLUL, NCF2, S100A12, and SRGN were most associated with neutrophils in the HF group. A total of 101 miRNAs were predicted by four genes, and GLUL, NCF2, and S100A12 predicted a total of 10 potential therapeutic agents.ConclusionsWe identified four biological markers that are highly correlated with AF and HF, namely, GLUL, NCF2, S100A12, and SRGN. Our findings provide theoretical basis for the clinical diagnosis and treatment of AF and HF.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Discussionsupporting

confidence: 84%

Identification of common mechanisms and biomarkers of atrial fibrillation and heart failure based on machine learning

Zhang,

Ding,

et al. 2024

ESC Heart Failure

View full text Add to dashboard Cite

show abstract

“…SERPINA3 is a circulating acute-phase protein and endogenous inhibitor of serine proteases [57]. There is growing evidence that it could be a prognostic marker in cardiovascular disease [58][59][60][61][62]. Yet, its (patho)physiological role is poorly understood, and literature is often contradictory, stressing the need for further research.…”

Section: Serpina3 An Enigmatic Protein With Association To Ctr-cvtmentioning

confidence: 99%

Characterization of systolic and diastolic function, alongside proteomic profiling, in doxorubicin-induced cardiovascular toxicity in mice

Krüger,

Bosman,

Van Assche

et al. 2024

Cardio-Oncology

View full text Add to dashboard Cite

Background The anthracycline doxorubicin (DOX) is a highly effective anticancer agent, especially in breast cancer and lymphoma. However, DOX can cause cancer therapy-related cardiovascular toxicity (CTR-CVT) in patients during treatment and in survivors. Current diagnostic criteria for CTR-CVT focus mainly on left ventricular systolic dysfunction, but a certain level of damage is required before it can be detected. As diastolic dysfunction often precedes systolic dysfunction, the current study aimed to identify functional and molecular markers of DOX-induced CTR-CVT with a focus on diastolic dysfunction. Methods Male C57BL/6J mice were treated with saline or DOX (4 mg/kg, weekly i.p. injection) for 2 and 6 weeks (respectively cumulative dose of 8 and 24 mg/kg) (n = 8 per group at each time point). Cardiovascular function was longitudinally investigated using echocardiography and invasive left ventricular pressure measurements. Subsequently, at both timepoints, myocardial tissue was obtained for proteomics (liquid-chromatography with mass-spectrometry). A cohort of patients with CTR-CVT was used to complement the pre-clinical findings. Results DOX-induced a reduction in left ventricular ejection fraction from 72 ± 2% to 55 ± 1% after 2 weeks (cumulative 8 mg/kg DOX). Diastolic dysfunction was demonstrated as prolonged relaxation (increased tau) and heart failure was evident from pulmonary edema after 6 weeks (cumulative 24 mg/kg DOX). Myocardial proteomic analysis revealed an increased expression of 12 proteins at week 6, with notable upregulation of SERPINA3N in the DOX-treated animals. The human ortholog SERPINA3 has previously been suggested as a marker in CTR-CVT. Upregulation of SERPINA3N was confirmed by western blot, immunohistochemistry, and qPCR in murine hearts. Thereby, SERPINA3N was most abundant in the endothelial cells. In patients, circulating SERPINA3 was increased in plasma of CTR-CVT patients but not in cardiac biopsies. Conclusion We showed that mice develop heart failure with impaired systolic and diastolic function as result of DOX treatment. Additionally, we could identify increased SERPINA3 levels in the mice as well as patients with DOX-induced CVT and demonstrated expression of SERPINA3 in the heart itself, suggesting that SERPINA3 could serve as a novel biomarker.

show abstract

Doxorubicin-induced cardiovascular toxicity: a longitudinal evaluation of functional and molecular markers

Bosman,

Krüger,

Van Assche

et al. 2023

Cardiovascular Research

View full text Add to dashboard Cite

Aims Apart from cardiotoxicity, the chemotherapeutic doxorubicin (DOX) induces vascular toxicity, represented by arterial stiffness and endothelial dysfunction. Both parameters are of interest for cardiovascular risk stratification as they are independent predictors of future cardiovascular events in the general population. However, the time course of DOX-induced cardiovascular toxicity remains unclear. Moreover, current biomarkers for cardiovascular toxicity prove insufficient. Here, we longitudinally evaluated functional and molecular markers of DOX-induced cardiovascular toxicity in a murine model. Molecular markers were further validated in patient plasma. Methods and Results DOX (4 mg/kg) or saline (vehicle) was administered intraperitoneally to young, male mice weekly for six weeks. In vivo cardiovascular function and ex vivo arterial stiffness and vascular reactivity were evaluated at baseline, during DOX therapy (week 2 and 4) and after therapy cessation (week 6, 9 and 15). Left ventricular ejection fraction (LVEF) declined from week 4 in the DOX group. DOX increased arterial stiffness in vivo and ex vivo at week 2, which reverted thereafter. Importantly, DOX-induced arterial stiffness preceded reduced LVEF. Further, DOX impaired endothelium-dependent vasodilation at week 2 and 6, which recovered at week 9 and 15. Conversely, contraction with phenylephrine was consistently higher in the DOX-treated group. Furthermore, proteomic analysis on aortic tissue identified increased thrombospondin-1 (THBS1) and alpha-1-antichymotrypsin (SERPINA3) at week 2 and 6. Upregulated THBS1 and SERPINA3 persisted during follow-up. Finally, THBS1 and SERPINA3 were quantified in plasma of patients. Cancer survivors with anthracycline-induced cardiotoxicity (AICT; LVEF < 50%) showed elevated THBS1 and SERPINA3 levels compared to age-matched control patients (LVEF ≥ 60%). Conclusions DOX increased arterial stiffness and impaired endothelial function, which both preceded reduced LVEF. Vascular dysfunction restored after DOX therapy cessation whereas cardiac dysfunction persisted. Further, we identified SERPINA3 and THBS1 as promising biomarkers of DOX-induced cardiovascular toxicity, which were confirmed in AICT patients.

show abstract

Construction and analysis of heart failure diagnosis model based on random forest and artificial neural network

Cited by 4 publications

References 45 publications

Identification of common mechanisms and biomarkers of atrial fibrillation and heart failure based on machine learning

Identification of common mechanisms and biomarkers of atrial fibrillation and heart failure based on machine learning

Characterization of systolic and diastolic function, alongside proteomic profiling, in doxorubicin-induced cardiovascular toxicity in mice

Doxorubicin-induced cardiovascular toxicity: a longitudinal evaluation of functional and molecular markers

Contact Info

Product

Resources

About