Proteomic-based biomarker discovery reveals panels of diagnostic biomarkers for early identification of heart failure subtypes
Bibliographic record
Abstract
BACKGROUND: Limited access to echocardiography can delay the diagnosis of suspected heart failure (HF), which in turn postpones the initiation of optimal guideline-directed medical therapy. Although natriuretic peptides like B-type natriuretic peptide (BNP) are valuable biomarkers for diagnosing and managing HF, the utility of combining BNP with other blood-based biomarkers to predict subtypes of new-onset HF remains underexplored. OBJECTIVES: This study sought to investigate and evaluate the diagnostic significance of adding blood-based biomarkers to BNP for identifying heart failure with preserved ejection fraction (HFpEF) or reduced ejection fraction (HFrEF), with the goal of enhancing diagnostic assays beyond BNP measurements. METHODS: We identified candidate blood protein biomarkers using untargeted proteomics workflows from a cohort of individuals recruited to the STOP-HF trial who were at risk of HF and subsequently developed either HFpEF or HFrEF over time ("HF progressors"; n = 40). Candidate biomarkers were verified in an independent cohort (n = 52) from a community-based rapid access HF diagnostic clinic. The biological processes associated with these proteins were assessed, and the diagnostic values of biomarker panels were evaluated using a machine learning approach. RESULTS: Within HF progressors, we identified 3 proteins associated with HFpEF development: vascular cell adhesion protein 1 (VCAM1), insulin-like growth factor 2 (IGF2), and inter-alpha-trypsin inhibitor heavy chain 3 (ITIH3). Additionally, 4 proteins were linked to HFrEF development: C-reactive protein (CRP), interleukin-6 receptor subunit beta (IL6RB), phosphatidylinositol-glycan-specific phospholipase D (PHLD), and noelin (NOE1). These findings were verified in an independent cohort to distinguish HF subtypes from controls. Moreover, a random forest algorithm demonstrated that combining these candidate biomarkers with BNP measurement significantly improved the prediction of HF subtypes. CONCLUSIONS: We identified candidate proteins linked to HFpEF and HFrEF in a longitudinal HF progressor cohort and validated them in a community-based cohort. Adding these proteins to BNP led to a significant improvement in HF subtype prediction. Study results have clinical implications for blood-based screening of HF subtypes using panels of biomarkers, particularly in resource-limited settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".