MediStat / Survival analysis

MediStat Kaplan–Meier

Compare groups with survival curves

Review Kaplan–Meier curves, log-rank tests, median survival and numbers at risk.

By Ki-Hyun Jeon

What to prepare

A dataset with follow-up time, event and group variables

What you get

Survival curves · numbers at risk · median survival · unadjusted HR

Requirements

Python · lifelines, openpyxl, matplotlib, pandas, numpy

Python setup guide ↗

Interpreting the results

This is an unadjusted survival analysis. Use MediStat Cox to estimate covariate-adjusted hazard ratios.

01 / INSTALL

Install in Claude Code

Enter these commands in the Code view of the Claude app or the Claude Code panel in VS Code. These are installation commands, not prompts for a regular Claude chat.

Run the first line, then the second. Restart Claude Code after installation to load the skill.

Installation commands · run one line at a time

/plugin marketplace add JeonKH81/MediStat-KM
/plugin install medistat-km@medistat-km

These commands register the skill. Python, R and analysis packages must be prepared separately; check the requirements above and the original documentation.

Installation instructions on GitHub ↗

02 / USE

Try this prompt after installation

Replace the bracketed fields with your own information, then paste the prompt into Claude Code.

Ready-to-copy prompt

[Goal]
Perform Kaplan–Meier survival analysis.

[Inputs]
File: [data filename]
Time variable and unit: [variable, days]
Event variable: [variable; event=1, censored=0]
Groups: [variable and group labels]

[Task]
Use MediStat KM to report survival curves, numbers at risk, the log-rank test and median survival.

[Checks]
Confirm time units and event definitions first. Label the results as unadjusted analyses.

Source: JeonKH81/MediStat-KM ↗ · Original documentation

This page provides usage and installation guidance. Analyses and file processing take place in your installed Claude Code environment.