A temporal correlation function for the association between patient-reported outcome and clinical endpoints.

Area of Science:

• Biostatistics
• Clinical Trial Methodology
• Health Outcomes Research

Background:

• Clinical trials often involve multiple endpoints, necessitating methods to understand their interrelationships.
• Quantifying the association between different types of endpoints, such as patient-reported outcomes and clinical measures, presents a challenge.

Purpose of the Study:

• To propose and validate a novel multiple event approach for profiling temporal correlations between two clinical trial endpoints.
• To provide a tool for visualizing and inferring associations, extending existing recurrent event methodologies.

Main Methods:

• Developed a multiple event approach incorporating a temporal correlation function.
• Utilized a correlation function plot with confidence bands for visualization.
• Extended methodologies from recurrent event data analysis.

Main Results:

• The proposed approach is generally unbiased.
• Demonstrated utility through application to a real clinical trial dataset.
• The method effectively profiles temporal associations between endpoints.

Conclusions:

• The multiple event approach offers a valuable tool for analyzing associations between clinical trial endpoints.
• Applicable to patient-reported outcomes, adverse events, and any two time-to-event endpoints.
• Facilitates data visualization and inference in clinical trial research.