Time Dependent Roc logo

Time Dependent Roc

OrganizationPopular
aipoch
time-dependent-roc

Use when performing time-dependent ROC curve analysis for survival data with follow-up time, event status, and a numeric marker. Supports CSV/TXT/TSV/Excel input, `risk_score` as the default marker unless `--marker_col` is provided, parameter validation, standardized output directories, AUC table export, ROC point export, and PDF figure generation.

Overview

Publisheraipoch
Repositorymedical-research-skills
Skill nametime-dependent-roc
Stars
1.9K
Forks
188
Bundled files
11
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 11 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aipoch on GitHub. Read the source before you install it.

Installation

Install the Time Dependent Roc AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Data%20Analysis/time-dependent-roc
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Time Dependent Roc in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Time Dependent Roc on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Time Dependent Roc is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Source: https://github.com/aipoch/medical-research-skills

Time-Dependent ROC Analysis

Use this skill to compute and plot time-dependent ROC curves for survival outcomes.

Use This Skill When

  • You have survival data with futime and fustat columns.
  • You need time-specific ROC curves and AUC values for a numeric risk marker.
  • You want a command-line workflow with parameter validation and standardized outputs.
  • Your file contains a numeric marker column named risk_score, or you will provide another marker explicitly with --marker_col.

Primary Command

bash
Rscript scripts/main.R \
  --data_file <input_file> \
  --times <comma_separated_times> \
  --output_dir <output_dir>

Prerequisites

  • Rscript is available in the shell.
  • Required R packages: optparse, timeROC, survival, ggplot2.
  • Optional package for Excel input: openxlsx.
  • Install missing packages with Rscript -e 'install.packages(c("optparse", "timeROC", "survival", "ggplot2", "openxlsx"), repos="https://cloud.r-project.org")'.

Core Arguments

ArgumentRequiredDescription
--data_fileYesInput data file in CSV, TXT, TSV, TAB, XLS, or XLSX format
--timesNoPrediction time points, comma-separated. Default 1,3,5
--marker_colNoMarker column name. Default risk_score; provide this option when your file uses a different marker
--output_dirNoOutput directory, default ./TimeROC_Results
--time_unitNoTime unit label for plot/output: year, month, or day. Default year
--auto_convert_daysNoIf TRUE, convert large futime values from days to the selected unit when appropriate. Default TRUE
--weightingNoIPCW weighting method: aalen, marginal, or cox. Default aalen
--causeNoEvent code treated as the outcome of interest. Default 1

Input Requirements

  • The input file must contain futime and fustat columns.
  • The selected marker column must exist and be numeric or coercible to numeric.
  • If --marker_col is omitted, the input file must contain risk_score.
  • futime must be numeric or coercible to numeric.
  • fustat must be numeric or coercible to numeric.
  • Rows with missing futime, fustat, or marker values are excluded.
  • At least 5 complete rows and at least 1 event for the requested cause are required.

Example input:

text
id	fustat	futime	risk_score	risk_group	GPR161	RIBC2
TCGA-C5-A1M5	1	5.6219	-1.1070	low	2.8252	5.3532
TCGA-EA-A5O9	0	2.1589	-0.8964	low	2.6046	4.4293
TCGA-C5-A3HL	0	1.7014	-0.9044	low	4.1248	4.9166

Minimal Workflow

  1. Confirm the input file exists and includes futime, fustat, and risk_score, or plan to pass --marker_col.
  2. Run scripts/main.R with the requested time points.
  3. Check the output directory for the AUC table and PDF figure.

If you omit --data_file, the script exits with SKILL_MISSING_INPUT.

Outputs

Expected output structure:

text
<output_dir>/
├── data/
│   └── time_roc_points.<csv|txt>
├── session_info.txt
├── figure/
│   └── time_roc.pdf
└── table/
    └── time_roc_auc.<csv|txt>

Primary output files:

  • data/time_roc_points.csv or data/time_roc_points.txt
  • table/time_roc_auc.csv or table/time_roc_auc.txt
  • figure/time_roc.pdf
  • session_info.txt

Exported result fields include:

  • time
  • time_unit
  • auc
  • marker_col
  • n_complete
  • n_events

Exported ROC point fields include:

  • false_positive_rate
  • sensitivity
  • time
  • time_unit
  • auc
  • curve_label

Read These Files When Needed

NeedFile
Statistical details and assumptionsreferences/algorithm.md
More CLI examplesreferences/cli-guide.md
Error diagnosisreferences/troubleshooting.md
Main execution entry pointscripts/main.R
Sample test datatests/data/

Quick Examples

Basic analysis:

bash
Rscript scripts/main.R \
  --data_file tests/data/time_roc_sample1.txt \
  --times 1,3,5 \
  --output_dir tests/output_basic

Specify marker column and plot styling:

bash
Rscript scripts/main.R \
  --data_file tests/data/time_roc_sample2.txt \
  --marker_col GPR161 \
  --times 1,2,4 \
  --line_colors "#4DBBD5,#E64B35,#00A087" \
  --legend_position bottom \
  --output_dir tests/output_gpr161

Validation

bash
Rscript scripts/main.R --help
bash
Rscript scripts/main.R \
  --data_file tests/data/time_roc_sample1.txt \
  --times 1,3,5 \
  --output_dir tests/validation_output

After running analysis, verify that these files exist:

  • tests/validation_output/data/time_roc_points.csv
  • tests/validation_output/table/time_roc_auc.csv
  • tests/validation_output/figure/time_roc.pdf
  • tests/validation_output/session_info.txt

Common Errors

  • SKILL_FILE_NOT_FOUND: Input file path is wrong or inaccessible.
  • SKILL_MISSING_COLUMNS: futime or fustat is missing.
  • SKILL_INVALID_DATA: The marker column is non-numeric, no complete rows remain, event coding is unsuitable, or requested time points yield unusable AUC values.
  • SKILL_INVALID_PARAMETER: An argument value is invalid.
  • SKILL_INSUFFICIENT_DATA: Too few complete rows or no target events remain.
  • SKILL_DEPENDENCY_MISSING: A required R package such as optparse, timeROC, survival, ggplot2, or openxlsx is unavailable.

If the issue is not obvious, read references/troubleshooting.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Time Dependent Roc AI skill do?

Use when performing time-dependent ROC curve analysis for survival data with follow-up time, event status, and a numeric marker. Supports CSV/TXT/TSV/Excel input, `risk_score` as the default marker unless `--marker_col` is provided, parameter validation, standardized output directories, AUC table export, ROC point export, and PDF figure generation.

Why use Time Dependent Roc on TypingMind?

Because you install it once and use it with any model. Time Dependent Roc is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Time Dependent Roc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Data%20Analysis/time-dependent-roc. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Time Dependent Roc?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Time Dependent Roc?

As many as you like. As long as a model supports skills, you can use Time Dependent Roc with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Time Dependent Roc AI skill free?

Yes. It is published on GitHub by aipoch under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇