Self-guided training

This self-guided training series walks you through LinXmart's core linkage capabilities using synthetic test data, progressing from foundational tasks to more advanced, real-world scenarios. Module 1 introduces basic concepts by de-duplicating a single file, while Module 2 builds on this with a two-file linkage between death and hospital records. Module 3 and Module 4 cover the operational side of managing a project — refining your linkage strategy using quality review and threshold adjustments, then finalising a project through reporting and linkage key extraction. Module 5 ties these skills together in a complex, clear-text simulation linking four datasets (general practice, hospital, emergency, and death records) to model a Primary-to-Secondary care research linkage.

The remaining modules focus on Privacy-Preserving Record Linkage (PPRL). Module 6 shows how to use the Envelope Builder to encode data ahead of a PPRL project, Module 7 applies PPRL to a single-file de-duplication task, and Module 8 replicates the Module 5 simulation using encoded datasets, demonstrating how the same linkage can be performed without exposing clear-text personal information.

Before you begin these training modules, you will need:

• Access to LinXmart via the web interface
• Synthetic test data - download the training data
• Completed initial data configuration setup

info

All data used in these training modules are synthetic (meaning that it is fake, although it looks real).

📄️ Setup

This page describes the steps to import the configuration required for all modules in the self-guided training.

📄️ 1. Single file dedup

In this Module, you will learn how to create a simple linkage project in LinXmart and how to undertake a de-duplication of a single (small) dataset. The Module will introduce you to some simple concepts in linkage and will help you gain confidence in operating the LinXmart software.

📄️ 2. Two file linkage

In this Module, you will build on what you have learnt from Module 1. You will learn how to undertake a linkage project in LinXmart involving two datasets – death records and hospital records.

📄️ 3. Configuration changes

Once you have linked some data, you may decide that you want to make some changes to your linkage strategy. This usually occurs after you have looked at your Linkage reports and/or have undertaken some checks (quality review) of linkage results.

📄️ 4. Reporting and extraction

When no more linkage decisions are required and you are satisfied with the quality of your linkage results, it will be time to finalise your Project. This process usually involves generating final reports about the Linkage Project and extracting linkage keys to provide to a Data Provider or to a person who is responsible for integrating datasets for research and analysis.

📄️ 5. Clear-text linkage simulation

In this Module, we will conduct a more complex CLEAR TEXT linkage project involving four synthetic, clear-text datasets.

📄️ 6. Envelope Builder for PPRL

In this Module, we will demonstrate how to use the LinXmart Simple Envelope Builder (EB) to prepare data for a PPRL linkage project.

📄️ 7. PPRL single file dedup

In this Module, you will learn how to undertake a de-duplication of a single, encoded dataset using the PPRL features of LinXmart. The Module will help you gain confidence in working with encoded data using LinXmart.

📄️ 8. PPRL linkage simulation

In this Module, we will conduct a complex PPRL linkage project involving four encoded datasets.