sdtmteam is a Visual Studio Code extension built on the open-source kilocode project. It serves as an intelligent agent to help clinical programmers and data managers generate CDISC SDTM datasets from raw data extracted from EDC systems or external transfers.

The agent performs smart analysis on raw datasets, generates mapping specifications, enables user review and confirmation, and then produces working code in SAS, R, or Python to convert raw data into SDTM-compliant datasets (e.g., CSV or SAS XPT files).

• 🔍 Analyzes raw clinical data and suggests SDTM mapping specs
• 👥 Allows human review and editing of generated specs
• 🧠 Learns from feedback to improve future suggestions
• 💻 Generates SDTM implementation code in SAS, R, or Python
• 📦 Converts raw data into SDTM-format outputs (CSV, XPT)
• 🔄 Supports both EDC extract and external data transfer formats

1. Make sure you have Visual Studio Code installed.
2. Clone or download this repository:

   git clone https://github.com/your-org/sdtmteam.git
   cd sdtmteam

3. Open the folder in VSCode:

   code .

4. Press F5 to launch the extension in a new Extension Development Host window.

Note: This extension may require access to Python, R, or SAS on your local machine depending on your selected output language.

1. Launch sdtmteam from the VSCode Command Palette (Ctrl+Shift+P) → SDTMTEAM: Start Agent.
2. Load your raw clinical dataset (CSV, XLSX, or custom format).
3. The extension will analyze the structure and propose a mapping spec.
4. Review and edit the spec using the built-in SDTM Spec Editor.
5. Confirm the mapping and choose your output format:
   • Generate SDTM as CSV
   • Generate SAS XPT
6. Export the implementation code in:
   • SAS
   • R
   • Python

You can rerun the agent at any time after modifying your data or mappings.

We welcome contributions from the clinical programming and data science community.

1. Fork this repo
2. Create a new branch:

   git checkout -b feature/my-new-feature

3. Make your changes and commit:

   git commit -am 'Add new feature'

4. Push to the branch:

   git push origin feature/my-new-feature

5. Open a pull request 🚀

MIT License

• Built on top of kilocode
• Inspired by real-world SDTM mapping workflows