LDT Toolkit (Longitudinal Depression Toolkit) is an open toolkit for building longitudinal mental health workflows that combine data handling, analytics, and reproducible research utilities. Basically, LDT Toolkit helps researchers and clinical teams organise depression-related data over time and turn it into Ml analyses, without rebuilding the same pipeline pieces from scratch. An LDT Toolkit workflow can support structured analysis on repeated patient observations, reducing ad-hoc scripting and improving reproducibility.

LDT-Toolkit is a Python based API toolset, and Go Command Line Interface for NO-CODE! You should start at ldt-toolkit; download the toolkit and the CLI; then finally play with it!

Whatever your field, your contribution is welcome. You can contribute in multiple ways:

• add reusable modules and CLI commands
• improve documentation and examples
• contribute tests, benchmarks, and validation utilities
• report bugs and suggest features
• And more importantly, share your study-specific reproducible scripts for longitudinal depression research

If you are getting started, open an issue or discussion in one of the LDT Toolkit repositories and we can help you pick a good first contribution.

LDT-Toolkit emerged from a ressearch internship at the Lifecourse Epidemiology and Psychiatry Research Group (LEAP) at the University of Edinburgh (UK); supervised by Dr. Alex Kwong.

See LEAP's website for more information about the group and their research.

Cheers! 🥳