[chai-t] Re: August meeting plans!
- From: "Rose William" <William.Rose@xxxxxxxxxxxx>
- To: <chai-t@xxxxxxxxxxxxx>
- Date: Fri, 17 Aug 2012 08:11:08 +1000
Hi all,
A reminder that we're meeting again today at 3pm at Peter Mac, in
Research Meeting Room 2.
As a reminder the map is below:
Kind regards,
William Rose
Business Intelligence Manager
Information Management
+61 3 9656 5231 | Level 8, St Andrews Place, East Melbourne VIC 3002
________________________________
From: chai-t-bounce@xxxxxxxxxxxxx [mailto:chai-t-bounce@xxxxxxxxxxxxx]
On Behalf Of Rose William
Sent: Tuesday, 7 August 2012 8:28 AM
To: chai-t@xxxxxxxxxxxxx
Subject: [chai-t] August meeting plans!
Hi all,
My belated thanks to those who made the trek in July: I think the sunny
room was an advantage. We spent a fair bit of time on the costing &
revenue dashboard Simon has been working on at Peter Mac, and then
switched to data mining & analytics, then ABF.
I think the consensus is that there is a lot of potential in the data
mining & analytics area, but it is hard to find ways to get to that in
the constant stream of pressing requirements. So I was very interested
to hear that the elusive Ray from Austin has built a better mousetrap
WIES estimator, as this is one of those things that frustrates me with
our reporting.
It was also interesting to hear about people's experience so far with
ABF and NWAU calculation, particularly the idea that under certain
circumstances particularly with private patients the initial calculation
of NWAU could lead to negative NWAU for the episode (!!!). If anyone has
a worked example of this, I'm keen to see how this can come up.
Last week I was at HIC in Sydney, and while I focussed on talks about
NLP and data analysis, there was quite a lot of stuff presented. Some of
the topics I think might be interesting to the group are:
* NSW Bureau of Health Information - at HIC and earlier this year
at DG2012 I saw quite a few examples of the kind of work they do at BHI,
and it made me think a more detailed review of what they produce might
yield some interesting ideas on what were sensible things to report and
ways to present it for Victoria.
* iDASH - another lavishly funded NCBC initiative that is
providing a platform for cross-organisational de-identified data sharing
and analysis, somewhat similar to BioGrid who live locally. One tidbit
from the iDASH talk was the idea of patients whose records were
aggregated for clinical research being able to view, PCEHR-style, a list
of the projects to which their "data altruism" had contributed.
* Semantic search - I've been tinkering with ordinary web search
engines for a bit, and plan to try to run one over our typed letters,
path reports and DI reports, plus coding data. The idea is to have a
Google-like front-end to locating encounters, patients or tests by
keywords, which I think might be an alternative way of opening up access
to clinicians / HIMs. The semantic search work (e.g. CSIRO, NICTA
locally) extends this by mixing in SNOMED-CT and NLP to improve
precision and recall over simple keywords.
* NLP for content extraction - not presented, but mentioned in
conversation with Hanna from NICTA, was that someone at Peter Mac has
been working on a dashboard for aspergillus surveillance, by
automatically classifying microbiology reports. I am slightly miffed
that I find out about this from someone based in Canberra at a
conference in Sydney, but mostly excited to go chase up some more. The
possibilities for meaningful clinical reporting increase significantly
if these techniques can be rolled out more widely.
Apart from stuff I'm chasing, though, I'd like to hear about a few of
the things happening around the traps too! Last I heard:
* Chris MacManus was neck-deep in a single-handed SQL2012 data
warehouse rollout -- Chris, are you still alive? Want to tell us what's
going on? Commiserate?
* Felicity and Sweta were similarly getting to work on their own
reporting strategy - any progress?
* Ray "Mr Elusive" Robinson from Austin gets regularly mentioned
in connection with skunkworks development at Austin, but doesn't get to
come along - Peter: can we come to you?
* Anthony Gust has a secret stash of SAS code he uses to do
reporting things that SQL nerds can only dream of - Anthony/Chris: are
these things that you can demo?
* David Stephens thought he might be able to demo meercats in
addition to the technological wonders of the new RCH.
* Jenny has already done a demo, but has so many ideas I'm sure
there is more to see.
* Rajesh and Steve from St Vincents have been very quiet so far,
which means they are working on something big. Very BIG.
So with that in mind, the next meeting date is August 17th, at 3pm, at
Peter Mac Research Meeting Room 2, unless someone else wants to have it
at their place.
Suggestions welcome for the agenda!
Kind regards,
William Rose
Business Intelligence Manager
Information Management
+61 3 9656 5231 | Level 8, St Andrews Place, East Melbourne VIC 3002
This email (including any attachments or links) may contain confidential
and/or legally privileged information and is intended only to be read or
used by the addressee. If you are not the intended addressee, any use,
distribution, disclosure or copying of this email is strictly
prohibited. Confidentiality and legal privilege attached to this email
(including any attachments) are not waived or lost by reason of its
mistaken delivery to you. If you have received this email in error,
please delete it and notify us immediately by telephone or email. Peter
MacCallum Cancer Centre provides no guarantee that this transmission is
free of virus or that it has not been intercepted or altered and will
not be liable for any delay in its receipt.
This email (including any attachments or links) may contain
confidential and/or legally privileged information and is
intended only to be read or used by the addressee. If you
are not the intended addressee, any use, distribution,
disclosure or copying of this email is strictly
prohibited.
Confidentiality and legal privilege attached to this email
(including any attachments) are not waived or lost by
reason of its mistaken delivery to you.
If you have received this email in error, please delete it
and notify us immediately by telephone or email. Peter
MacCallum Cancer Centre provides no guarantee that this
transmission is free of virus or that it has not been
intercepted or altered and will not be liable for any delay
in its receipt.
Other related posts:
