A1229
Title: Joint modelling of longitudinal creatinine trajectories and kidney disease risk in children with autoimmune disorders
Authors: Qendresa Selimi - The University of Manchester (United Kingdom) [presenting]
Christiana Charalambous - University of Manchester (United Kingdom)
Taban Baghfalaki - The University of Manchester (United Kingdom)
Abstract: Research on paediatric kidney disease remains limited, and existing approaches do not fully exploit the information contained in longitudinal biomarkers that evolve over time. Longitudinal data, consisting of repeated measurements of a variable over time, are often used in clinical research to capture subject-specific trajectories. In parallel, survival data record the time to an event of interest -such as death or diagnosis- and are crucial in understanding clinical outcomes. As both data types are typically collected on the same subjects, they are linked; analysing them separately may lead to biased estimates. A joint modelling framework was employed to investigate the relationship between longitudinal serum creatinine measurements and the risk of adverse kidney outcomes in paediatric patients with autoimmune disorders at Great Ormond Street Hospital for Children NHS Foundation Trust, London. The framework combines creatinine trajectories with the time to death or diagnosis of acute kidney injury or chronic kidney disease. The results demonstrate a strong association between evolving creatinine profiles and the risk of the composite event. Dynamic risk predictions were generated using patients' observed creatinine trajectories to demonstrate the practical utility of the proposed framework. These predictions illustrate the potential of joint models to support personalised medicine and clinical decision making in paediatric nephrology through real-time risk assessment.
