D&C Lug - Home Page
Devon & Cornwall Linux Users' Group

[ Date Index ][ Thread Index ]
[ <= Previous by date / thread ] [ Next by date / thread => ]

[LUG] open source data mining (for medical records)



This may interest some of you




Herewith a brief announcement of some software or potential interest
to members of the openhealth list. Some additional comments follow
the announcement.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The Australian National University Data Mining Group, in
collaboration with the Centre for Epidemiology and Research in 
the New South Wales Department of Health, is pleased to announce the
first (alpha) release of prototype program code intended to make 
probabilistic record linkage easier, faster and more accurate for 
biomedical and other researchers.

The programs, known collectively as "Febrl" - Freely Extensible
Biomedical Record Linkage - currently address the data cleaning
and standardisation tasks which are an essential first step for
most record linkage projects, as well as providing a number of
support functions for record linkage. The next release will include
record linkage routines.

Febrl, which is written is the free, open source Python programming
language, is itself available under a free, open source license,
which we hope will encourage others to contribute to its further 
development and support. Contact details, background information,
documentation and, of course, the program code are all available from
the project Web site at

? ? ? ? http://datamining.anu.edu.au/linkage.html 

We would like to stress that the programs are still in the early stages
of development, and we do not yet recommend them for production use,
but we encourage you to try them and to provide us with feedback.

We particularly welcome bug reports and ideas for future development.
There are many ways to help with the project: testing, programming and
software engineering, testing, documentation and technical writing,
testing, translation, testing, provision of (anonymous,
non-confidential) training and example datasets, and testing (did we 
mention that already?).

We look forward to hearing from you.

Peter Christen and Tim Churches
Principal Developers of Febrl
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Apart from being of interest to researchers working in fields such as
population health, health services evaluation and genetic epidemiology,
Febrl has the potential to become the core of a robust and scalable
open source Patient Master Index (PMI) or Patient Identification System 
(PIDS). Although the first few releases will be aimed at researchers who
mostly need batch processing facilities, we are engineering the software
with online use in a community or population PIDS in mind, with access
via various Web services and Grid computing interfaces. 

As noted above, this first release contains only some of the components
of
the complete system, which we hope to have available by the end of 2002 
or early in 2003.

Tim C
-- 
From one of the Linux desktops of Dr Adrian Midgley 
http://www.defoam.net/             

--
The Mailing List for the Devon & Cornwall LUG
Mail majordomo@xxxxxxxxxxxx with "unsubscribe list" in the
message body to unsubscribe.


Lynx friendly