16:57:58 <RRSAgent> RRSAgent has joined #hcls2
16:57:58 <RRSAgent> logging to http://www.w3.org/2010/12/02-hcls2-irc
17:02:39 <ericP> Zakim, this is tmo
17:02:53 <Zakim> ok, ericP; that matches SW_HCLS(TMO)11:00AM
17:02:54 <ericP> Zakim, please dial ericP-office
17:03:03 <Zakim> ok, ericP; the call is being made
17:03:07 <Zakim> +EricP
17:03:23 <Bob> Bob has joined #hcls2
17:04:24 <Zakim> +epichler
17:04:53 <jluciano> jluciano has joined #hcls2
17:06:11 <Zakim> + +1.518.276.aaaa
17:06:32 <jluciano> what's eric talking about?
17:06:41 <jluciano> the children's hosp project?
17:06:47 <michel> i2b2
17:07:00 <mscottm> mscottm has joined #hcls2
17:07:28 <michel> ericP: simple data structure, no complex relations
17:07:29 <Zakim> +mscottm
17:07:43 <Zakim> - +1.518.276.aaaa
17:08:04 <Zakim> + +1.518.276.aabb
17:08:05 <michel>  ... they're excited about adding semantics to describe concepts, ericP excited about adding semantics for the relations
17:08:27 <michel>  ... patients have a portal into the clinical database
17:08:44 <Zakim> +Joanne_Luciano
17:09:56 <Bob> Michel: Open MRS had a demo, can't really do all things, like have to know patient's name
17:10:20 <Bob> ...but it is open w meet-ups etc, concept library like i2b2
17:10:50 <ericP> ericP: there's also MLHIM (Multi-level Health Information Modeling)
17:10:59 <Bob> ...Are there other platforms where we can work on plumbing and concepts?
17:11:20 <Bob> Eric: All these projects have a few coders on them
17:11:41 <Bob> ...don't now that i2b2 or Indivio offers serious advantage over others
17:11:48 <michel> requirements: interface, basic plumbing that can be customized, provide new content
17:12:32 <michel> regrets: matthias
17:12:47 <michel> attending: ericP, michel, scott, bob, joanne, elgar
17:12:50 <jluciano> TIm Lebo
17:13:12 <michel> topic: patient data
17:13:25 <Bob> Eric: Stuck a couple of claims in the paper, when forced to come up w model
17:13:56 <Bob> ...some bag of assertions that need not be elevated into ontology
17:14:21 <Bob> ...huge amount of info in SNPs, can be condensed into SNP variation for a person
17:14:26 <mscottm> Another system that I and Matthias looked at back in June: http://www.tolvenhealth.com/ It was being used by Collaborx
17:14:52 <Bob> ...need a SNP expert, maybe join that with other things
17:15:43 <Bob> ...SNPs appear as XML, we need RDF. What would that look like in Indivo? Don't quite know
17:16:20 <Bob> ...what is true of all SNPs, don't need to code for individual patient.
17:16:52 <Bob> Joanne: Are SNPs relevant for Alzheimer's?
17:17:29 <Bob> Michel: Value of SNP is hiding in text: major allele, position, current allele
17:18:16 <Bob> ...info not quite structured in the way we need, but it is in there.
17:18:47 <Bob> Eric: Micro-parsing is ahead of us.
17:19:01 <Bob> ...need to generically represent tests
17:19:26 <Bob> ...there is a whole lot of structure in the patient data about SNPs that are incomprehensible
17:20:11 <Bob> Michel: RDF-ize dbSNP, would specify the structure
17:20:49 <Bob> Eric: We can push this back to Indivo, make an informed plea
17:21:56 <Bob> Joanne: Paper, still need to use TMO in queries
17:23:39 <Bob> Eric: trans:, TMO, also strong desire to force units
17:24:16 <Bob> ...TMO is principled, wrote some OWL to map to units etc
17:24:58 <Bob> Michel: trans: gets the RDF done, need a formal mapping trans: to schema relations
17:25:33 <Bob> ...more painful way is to formally analyze every transformation generates TMO
17:26:07 <jluciano> q+
17:26:11 <Bob> Eric: There is practical value to have another namespace, like trans:
17:26:22 <jluciano> q-
17:26:33 <Bob> Scott: Is trans: from bottom-up?
17:26:43 <Bob> Eric: Yes, nothing special about it
17:26:44 <jluciano> that was Tim Lebo
17:27:13 <Bob> Eric: trans: is a "to-do" namespace artifact
17:28:02 <Bob> Eric: Look at data, look at TMO, ask "How is this supposed to be expressed?"
17:28:22 <Bob> ...eveantually should not see any trans: in the XSLT
17:28:59 <Bob> ...XML data from EHR --> RDF version of Indivo
17:29:37 <Bob> Tim: Generally good idea to push the ontology into the converter?
17:29:45 <Bob> (good question!)
17:30:21 <Bob> Eric: Logical structure for data, then that should be how the data are represented
17:31:55 <Bob> ...get rid of the trans as long as the queries do not become hopelessly erudite
17:33:11 <Bob> Eric: trans: represents questions people do ask plus what questions they might want to ask
17:33:33 <Bob> ...as long as questions are intuitive in TMO, then tweak the XSL
17:33:53 <Bob> ...there becomes less and less trans: in this process
17:34:26 <Bob> ...OWL file is a separate issue, to show fixed units
17:34:46 <Bob> ...tension between that, and TMO
17:35:28 <Bob> Scott: We have discussed this a great deal.
17:36:21 <Bob> ...because we are using a language that is amenable to reasoning then we should use it
17:36:34 <Bob> (that was Michel!)
17:37:07 <Bob> Eric: At what level of tooling do you reduce choices?
17:37:35 <Bob> ...want data normalized *at input*, makes it easier downstream
17:37:50 <Bob> Michel: Trivial to normalize units
17:38:21 <Bob> Eric: Every standard reduces choices, the cost becomes exponentially harder
17:38:46 <Bob> ...generic federation problems appear after download
17:39:24 <Bob> Michel: Once it's in RDF and sparql, well structured, then it't trivial to normalize
17:39:31 <Bob> ...that's what we're looking to do
17:40:01 <Bob> Eric: Still have to examine each one and deal with it. Q is not whether but when.
17:42:33 <Zakim> -Joanne_Luciano
17:43:43 <Bob> Scott: "Standardizing" we require that people use certain units w. TMO. So how to specify that as a constraint?
17:44:13 <Bob> ...can't say from TMO that you need certain units?
17:44:52 <Bob> Eric: Can do some enforcement in OWL
17:47:38 <Bob> Eric: Q is What is the space between the patient data and the TMO?
17:48:56 <jluciano> https://dvcs.w3.org/hg/TMO-Indivo/file/3334734509e9/syntheticPatients/AD_PCHR_1.xml
17:55:37 <mscottm> I lost all audio
17:56:21 <mscottm> got it back again (?)
18:00:03 <mscottm> .rdf files include some CPR - they were produced before using indivo 
18:00:11 <Bob> Eric has missed his lunch.
18:00:21 <Zakim> -EricP
18:00:24 <Zakim> -mscottm
18:00:25 <Zakim> -[IPcaller]
18:00:27 <Zakim> - +1.518.276.aabb
18:00:29 <Zakim> -epichler
18:00:31 <michel> rrsagent, draft minutes
18:00:31 <RRSAgent> I have made the request to generate http://www.w3.org/2010/12/02-hcls2-minutes.html michel
18:00:37 <Zakim> -Bob_Powers
18:00:37 <michel> rrsagent, make log world-visible
18:00:39 <Zakim> SW_HCLS(TMO)11:00AM has ended
18:00:41 <Zakim> Attendees were [IPcaller], Bob_Powers, EricP, epichler, +1.518.276.aaaa, mscottm, +1.518.276.aabb, Joanne_Luciano
19:09:30 <michel> michel has left #HCLS2
19:30:10 <Zakim> Zakim has left #hcls2