Search

Background: Elevated serum uric acid (sUA) is associated with heart failure (HF). Hypothesis: Urate‐lowering therapy (ULT) in HF is associated with lower risk of HF hospitalization (hHF) and mortality. Methods: Data on patients with HF and gout or hyperuricemia in the Clinical Practice Research Datalink database linked to the Hospital Episode Statistics and the Office for National Statistics in the United Kingdom were analyzed. Risks of hHF and all‐cause mortality or cardiovascular‐related mortality by ULT exposure (ULT initiated within ≤6 months of gout or hyperuricemia diagnosis) were analyzed in a propensity score‐matched cohort using adjusted Cox proportional hazards regression models. Results: Of 2174 propensity score‐matched pairs, patients were predominantly male, aged >70 years, with mean ± standard deviation sUA 9.3 ± 1.8 (ULT‐exposed) and 9.4 ± 1.9 mg/dL (ULT‐unexposed). At 5 years, ULT‐exposed patients had a 43% lower risk of hHF or all‐cause mortality (adjusted hazard ratio [HR]: 0.57; 95% confidence interval [CI]: 0.51–0.65) and a 19% lower risk of hHF or cardiovascular‐related mortality (adjusted HR: 0.81; 95% CI: 0.71–0.92) versus no ULT exposure. Conclusion: ULT was associated with reduced risk of adverse clinical outcomes in patients with HF and gout or hyperuricemia over 5 years. Practitioner points: Raised serum uric acid is strongly associated with heart failure (HF); however, it is unknown whether urate‐lowering therapy (ULT) could help patients with HF.We assessed the relationship between ULT and HF outcomes using UK patient data, and found that the risk of the composite of hospital admission for HF or death was lower with ULT than with no ULT.These results support further investigation into the potential benefit of ULT in HF. [ABSTRACT FROM AUTHOR]

We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property of interest. This problem arises in discovery processes that rely on screening funnels for trading off the overall costs against throughput and accuracy. Typically, individual stages in these processes are loosely connected and each one generates data at different scale and fidelity. We consider this setup holistically and demonstrate empirically that existing transfer learning techniques for graph neural networks are generally unable to harness the information from multi-fidelity cascades. Here, we propose several effective transfer learning strategies and study them in transductive and inductive settings. Our analysis involves a collection of more than 28 million unique experimental protein-ligand interactions across 37 targets from drug discovery by high-throughput screening and 12 quantum properties from the dataset QMugs. The results indicate that transfer learning can improve the performance on sparse tasks by up to eight times while using an order of magnitude less high-fidelity training data. Moreover, the proposed methods consistently outperform existing transfer learning strategies for graph-structured data on drug discovery and quantum mechanics datasets.Modern molecular discovery processes generate millions of measurements at different quality levels. Here, the authors develop a new deep learning method for transfer learning from low-cost and abundant data to enhance the efficiency of drug discovery. [ABSTRACT FROM AUTHOR]