Development and validation of clinical prediction models for personalized renal function monitoring in people with heart failure in primary care: the RENAL-HF study protocol

Aims: Heart failure (HF) is a growing problem in society with an ageing population and many patients with heart failure are affected by renal dysfunction. The RENAL-HF project aims to develop predictive risk models to support personalized renal function monitoring and treatment in patients with HF in primary care. Methods and results: This study will use electronic health records from the Clinical Practice Research Datalink (CPRD) database for patients who were diagnosed with HF. We will develop three prediction models-Mixed-effects model, Growth mixture model, and recurrent neural network-long short-term memory model to predict future worsening renal function, including events that lead to hospitalization, and death. Using an internal-external validation approach based on geographic region, we will choose the top-performing model using various metrics to evaluate the predictive performance. Conclusion: This protocol provides a detailed description of the methods used for developing and validating prognostic models for personalized renal function monitoring in people with HF in primary care. Protocol registration: The study and use of CPRD data were approved by the Independent Scientific Advisory Committee for Clinical Practice Research Datalink research (