Urine proteome analysis in heart failure with reduced ejection fraction complicated by chronic kidney disease: feasibility, and clinical and pathogenetic correlates

Abstract

Aims Urine proteome analysis (UPA) has already provided accurate discriminatory patterns of urinary peptides for renal disease, coronary artery disease, and asymptomatic LV diastolic dysfunction. UPA has now been used to characterize a discriminatory peptide biomarker pattern and establish a diagnostic classifier for heart failure patients with reduced ejection fraction (HFrEF) in the presence of chronic kidney disease (CKD). Methods and results We analysed the urine proteome profiles obtained by capillary electrophoresis online coupled to micro‐TOF (time of flight) mass spectrometry of 126 individuals, 59 HFrEF patients and 67 controls matched for age, sex, and renal function. In total, 107 significant discriminatory peptides were identified and used to establish a support vector machine‐based classifier that was successfully applied to a test set of 25 HFrEF patients and 33 controls, achieving 84% sensitivity and 91% specificity. The majority of sequenced peptides were fragments of collagen type I and III. Conclusion UPA was able to identify a set of HFrEF‐specific urinary peptide biomarkers on a background of CKD that were successfully utilized to establish a syndrome's classifier.

Circulating proteins as predictors of incident heart failure in the elderly

“…Previous proteomics efforts have used antibody microarrays, mass spectrometry, or multiple ELISA assays . These studies compared circulating or urinary protein levels in patients with heart failure to individuals without heart failure, or followed heart failure patients for up to 36 months .…”

Urinary levels of novel kidney biomarkers and risk of true worsening renal function and mortality in patients with acute heart failure

“…Serum accumulation may be related to reduced filtration function (with or without overproduction), while urinary concentration is more like a marker of impaired natriuresis and diuresis . It should be emphasized that the analysis of urinary biomarkers in patients with HF is becoming an emerging and valuable field of research providing unique information . Urinary concentration is mainly an outcome of local tubular synthesis in response to injury, whereas the serum concentration seems to be a result of wide systemic production (driven by inflammation, oxidative stress, and other factors), which can be only exacerbated by worse eGFR .…”

Applications of Machine Learning Predictive Models in the Chronic Disease Diagnosis

“…From Table 2, it is evident that diabetic predictions show an accuracy of 73.1-91.6% [23]. Cardiac diseases produce a prediction accuracy of 84-91% [34], while in the prediction of liver diseases, NB, RF, KNN, SVM, and NN models produce an accuracy in a range of 78.1-82.7%. In particular, RF and NN models are found to have the highest accuracy.…”