Back

AI-driven Classification of Heart Failure Preserved and Reduced Ejection Fraction Patients Using the Total Protein Approach

Lenzi, A.; Carvalho, L. B.; Teigas-Campos, P. A. D.; Biagini, D.; Ghimenti, S.; Armenia, S.; Pugliese, N. R.; Masi, S.; Francesco, F. d.; Lomonaco, T.; Lodeiro, C.; Capelo, J. L.; Santos, H. M.

2024-11-26 biochemistry
10.1101/2024.11.25.625184 bioRxiv
Show abstract

Heart failure (HF) presents two major subtypes: HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF), each one with distinct metabolic characteristics. This study utilized artificial intelligence, high-resolution mass spectrometry and the Total Protein Approach (TPA) to identify key features differentiating these subtypes. Aldolase A (ALDOA), a glycolytic enzyme, was found upregulated in HFrEF patients, reflecting an increased glycolysis pathway, while Arginase 1 (ARG1), a key enzyme in the urea cycle, was also elevated, indicating an increased urea pathway. In contrast, HFpEF patients showed TPA ALDOA and ARG1 levels similar to healthy controls. The combined use of ALDOA and ARG1 TPA values successfully classified 82% of patients (14 out of 17). Additionally, most HFpEF patients were over 80 years old, suggesting an age-related metabolic shift. The combination of ALDOA and ARG1 are promising biomarkers for distinguishing HFpEF and HFrEF using the TPA approach, with potential implications for targeted therapies.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.