Sections

List of Technical Tools

Summary

In this section, we list various powerful tools that can be used for all the different stages of the patient matching exercise.

Dataset generator Package and Notebook

How to install the package:

CIKM 2013 Demo - DMM - ANU

Welcome to the online GeCo demo. This tool allows the generation of various types of personal data, ranging from names and addresses, dates, social security and credit card numbers, to numerical values such as salary or blood pressure. Our tool can model dependencies between attributes, and it allows the corruption of values in various ways.

dmm.anu.edu.au

Developed by Khoi-Nguyen Tran, Dinusha Vatsalan, and Peter Christen

Notebook:

Google Colaboratory

colab.research.google.com

Developed by Jembi

Blocking Notebook

Notebook:

Google Colaboratory

colab.research.google.com

Developed by Jembi

Fastlink R Package and Notebook

How to install the package:

Embed GitHub

Developed by Ted Enamorado, Benjamin Fifield, and Kosuke Imai

Notebook:

Google Colaboratory

colab.research.google.com

Developed by Jembi

Fastlink R documentation:

fastLink: Fast Probabilistic Record Linkage with Missing Data

Implements a Fellegi-Sunter probabilistic record linkage model that allows for missing data and the inclusion of auxiliary information. This includes functionalities to conduct a merge of two datasets under the Fellegi-Sunter model using the Expectation-Maximization algorithm. In addition, tools for preparing, adjusting, and summarizing data merges are included.

cran.r-project.org

fastLink: Fast Probabilistic Record Linkage with Missing Data

Fastlink R Ethiopia Interim Solution Package

To be made available at a later date.

Developed by Jembi

Splink Package and Notebook

How to install the package:

GitHub - moj-analytical-services/splink: Implementation of Fellegi-Sunter's canonical model of record linkage in Apache Spark, including EM algorithm to estimate parameters

splink implements Fellegi-Sunter's canonical model of record linkage in Apache Spark, including the EM algorithm to estimate parameters of the model. It: Works at much greater scale than current open source implementations (100 million records+). Runs quickly - with runtimes of less than an hour.

github.com

GitHub - moj-analytical-services/splink: Implementation of Fellegi-Sunter's canonical model of record linkage in Apache Spark, including EM algorithm to estimate parameters

Developed by the UK MoJ data linking team

Notebook:

GitHub: moj-analytical-services/splink_demos/master

Click to run this interactive environment. From the Binder Project: Reproducible, sharable, interactive computing environments.

mybinder.org

GitHub: moj-analytical-services/splink_demos/master

Splink documentation:

Splink: MoJ's open source library for probabilistic record linkage at scale

The Ministry of Justice ( MoJ) has received funding from ADR UK for an ambitious programme of work called Data First, which aims to improve the quality of the department's data to enable better research. As part of this work, a new team has been established to develop and implement cutting edge approaches to data linkage at scale.

www.gov.uk

Splink: MoJ's open source library for probabilistic record linkage at scale

Python Record Linkage Toolkit

How to install the package:

GitHub - J535D165/recordlinkage: A toolkit for record linkage and duplicate detection in Python

The Python Record Linkage Toolkit is a library to link records in or between data sources. The toolkit provides most of the tools needed for record linkage and deduplication. The package contains indexing methods, functions to compare records and classifiers. The package is developed for research and the linking of small or medium sized files.

github.com

GitHub - J535D165/recordlinkage: A toolkit for record linkage and duplicate detection in Python

Developed by Jonathan de Bruin

Notebooks:

GitHub: mayerantoine/2019-intro-patient-matching/master

Click to run this interactive environment. From the Binder Project: Reproducible, sharable, interactive computing environments.

mybinder.org

GitHub: mayerantoine/2019-intro-patient-matching/master

Developed by Antoine Mayer

Embed GitHub

Python Record Linkage Toolkit documentation:

About - Python Record Linkage Toolkit 0.14 documentation

In record linkage, the attributes of the entity (stored in a record) are used to link two or more records. Attributes can be unique entity identifiers (SSN, license plate number), but also attributes like (sur)name, date of birth and car model/colour. The record linkage procedure can be represented as a workflow [Christen, 2012].

recordlinkage.readthedocs.io

Link Plus

How to install the package:

Link Plus

Link Plus is a record linkage tool for cancer registries. It can run in two modes- To detect duplicates in a cancer registry database. To link a cancer registry file with external files. Although originally designed to be used by cancer registries, the program can be used with any type of data in fixed width or delimited format.

www.cdc.gov

Developed by U.S. Centers for Disease Control and Prevention (CDC), Cancer Division

OpenCR

How to install the package:

Local Installation

Time to complete 60 Minutes Warning This guide is for demonstrations or tests only, not for production environments. Note This installation method requires familiarity with the command line. CPU/RAM: Modern CPUs with 8GB RAM. Java version 8 (1.8). Oracle-licensed Java (requires sign-in) and AdoptOpenJDK (not sign-in required) have been tested.

intrahealth.github.io

Developed by IntraHealth International with support from PEPFAR through the USAID MEASURE Evaluation Project. Technical direction was provided by CDC.

OpenCR documentation:

Welcome!

Thank you for taking an interest in the Open Client Registry (OpenCR)! This is a community project and meant for others to adopt to their use cases as they wish. Tip Regardless if you're just curious, an implementer, or a developer, please read the this page first and then the User Manual.

intrahealth.github.io