Ma, Xiao

Abstract Objectives Heart failure (HF) impacts millions of patients worldwide, yet the variability in treatment responses remains a major challenge for healthcare professionals. The current treatment strategies, largely derived from population based evidence, often fail to consider the unique characteristics of individual patients, resulting in suboptimal outcomes. This study aims to develop computational models that are patient-specific in predicting treatment outcomes, by utilizing a large Electronic Health Records (EHR) database. The goal is to improve drug response predictions by identifying specific HF patient subgroups that are likely to benefit from existing HF medications. Materials and Methods A novel, graph-based model capable of predicting treatment responses, combining Graph Neural Network and Transformer was developed. This method differs from conventional approaches by transforming a patient's EHR data into a graph structure. By defining patient subgroups based on this representation via K-Means Clustering, we were able to enhance the performance of drug response predictions. Results Leveraging EHR data from 11 627 Mayo Clinic HF patients, our model significantly outperformed traditional models in predicting drug response using NT-proBNP as a HF biomarker across five medication categories (best RMSE of 0.0043). Four distinct patient subgroups were identified with differential characteristics and outcomes, demonstrating superior predictive capabilities over existing HF subtypes (best mean RMSE of 0.0032). Discussion These results highlight the power of graph-based modeling of EHR in improving HF treatment strategies. The stratification of patients sheds light on particular patient segments that could benefit more significantly from tailored response predictions. Conclusions Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques.

Introduction: Atrial natriuretic peptide (ANP) is the most potent endogenous activator of the guanylyl cyclase A receptor (GC-A) mediating cardiorenal protective actions by increasing cGMP production. To test the hypothesis that acute decompensated heart failure (ADHF) is associated with increased circulating ANP but with reduced GC-A potency, we developed an ex-vivo precision medicine assay to quantify the potency of circulating ANP in plasma from healthy and ADHF subjects. Further, we assessed the ex-vivo potency of MANP, a novel ANP analog with greater cGMP activation than ANP, also using plasma of healthy and ADHF subjects. Methods: For the potency assay, we engineered HEK293 cells to overexpress human GC-A. Plasma from individual healthy (n=4) and ADHF (n=4) subjects was incubated in the assay and cGMP was assessed. The endogenous ANP derived cGMP was evaluated against the cGMP response of equimolar synthetic ANP (S ANP ) to assess potency of ANP from each cohort. MANP mediated cGMP generation was also assessed in the assay using healthy and ADHF plasma. Results: Healthy plasma, in which plasma ANP was 26±5 pg/mL, generated 10.3±0.7 pmol/mL of cGMP. S ANP added to the assay to mimic endogenous ANP levels in healthy subjects produced 7.8±0.5 pmol/mL of cGMP. ADHF plasma with markedly elevated ANP (350±57pg/mL) generated 23.5±3.1 pmol/mL of cGMP. S ANP mimicking plasma ANP in ADHF produced 59.7±13.8 pmol/mL of cGMP, which was greater than cGMP generated from ADHF patient-derived plasma (p<0.05), consistent with reduced potency of endogenous ANP in ADHF. Low treatment dose of MANP (LD MANP ; 10 -8 M) in healthy plasma increased cGMP to 45±5.5 pmol/ml while high treatment dose (HD MANP ; 10 -6 M) increased cGMP to 167.1±14.1 pmol/mL. In markedly elevated ANP ADHF plasma, LD MANP increased cGMP to 60.4±9.7 pmol/mL while HD MANP increased cGMP to 200.8±5.4 pmol/mL (p<0.03 for both) demonstrating similar cGMP production by MANP in healthy and ADHF plasma. Conclusions: Employing a novel ex-vivo precision medicine ANP/GC-A/cGMP assay, we conclude that ADHF is characterized by elevated ANP yet with impaired potency in GC-A activation and cGMP generation. MANP overcomes this impairment and serves as a potential efficacious GC-A activating therapeutic in heart failure.