# ShinyEvents: harmonizing longitudinal data for real world survival estimation

## TL;DR

ShinyEvents is a web-based tool that helps analyze patient treatment timelines and estimate survival outcomes using longitudinal data.

## Contribution

The novel contribution is a web-based framework for integrating and analyzing multilayered longitudinal data with interactive visualizations and survival analysis.

## Key findings

- ShinyEvents enables interactive visualization of patient clinical events and treatment timelines.
- The tool supports cohort-level analysis and real-world progression-free survival estimation using Kaplan-Meier and Cox regression.
- It provides Sankey and Swimmer diagrams for visualizing treatment lines and clinical courses.

## Abstract

Longitudinal data analysis of the patient’s treatment course is critical to uncovering variables that influence outcomes. However, existing tools have significant limitations in integrating multilayered time-series data. Here, we developed ShinyEvents, a web-based framework for complex longitudinal data analysis. ShinyEvents allows users to upload data and generate interactive timelines of the patient’s clinical events. Our tool can perform cohort-level analysis, including the assignment of treatment clusters and clinical endpoints. Our tool also provides informative cohort visualizations, such as a Sankey diagram of the treatment line and Swimmer diagram of the clinical course. Finally, our tool can infer a real-world progression-free survival (rwPFS) based on user-defined endpoints to perform Kaplan-Meier and Cox proportional hazards regression analysis. With these features, the tool can then associate the lines of treatment with clinical outcomes. Altogether, ShinyEvents facilitates the integration of multilayered longitudinal data and enables survival analysis in real-time. A live link to the tool is available https://shawlab-moffitt.shinyapps.io/shinyevents/.