15:01:14 <RRSAgent> RRSAgent has joined #HCLS
15:01:14 <RRSAgent> logging to http://www.w3.org/2012/05/15-HCLS-irc
15:01:33 <BobF> BobF has joined #hcls
15:01:40 <Suajn> Suajn has joined #hcls
15:02:01 <michel> zakim, this is hcls
15:02:01 <Zakim> ok, michel; that matches SW_HCLS()11:00AM
15:02:06 <michel> zakim, who is here?
15:02:06 <Zakim> On the phone I see ??P18, Tony, +1.613.293.aabb
15:02:08 <Zakim> On IRC I see Suajn, BobF, RRSAgent, Zakim, michel, luke, achille_z, jun, MacTed, ericP
15:02:14 <Zakim> + +1.519.638.aacc
15:02:36 <Zakim> + +1.518.276.aadd
15:03:04 <swoosh> swoosh has joined #hcls
15:03:08 <michel> zakim, +1.613.293.aabb is michel
15:03:08 <Zakim> +michel; got it
15:03:18 <sujan> sujan has joined #HCLS
15:03:31 <marc> marc has joined #hcls
15:03:43 <matthias_samwald> matthias_samwald has joined #hcls
15:03:55 <Zakim> +??P20
15:04:07 <michel> zakim, ??P20 is matthias
15:04:07 <Zakim> +matthias; got it
15:04:23 <Zakim> +??P21
15:04:23 <mscottm> mscottm has joined #hcls
15:04:44 <michel> zakim, ??P21 is mscottm
15:04:44 <Zakim> +mscottm; got it
15:06:00 <michel> chair: Michel Dumontier
15:06:10 <Zakim> -Tony
15:06:17 <Zakim> +[GVoice]
15:06:44 <MarkW> MarkW has joined #hcls
15:06:57 <michel> Meeting: OSCAR
15:07:34 <MarkW> Hey Swoosh!  Grats on the paper, dude!!!
15:07:35 <Zakim> + +1.905.385.aaee
15:07:36 <Joanne_Luciano> Joanne_Luciano has joined #hcls
15:08:52 <Joanne_Luciano> Mark Dumontier - OSCAR health care records
15:09:03 <bobP> bobP has joined #hcls
15:09:29 <Joanne_Luciano> To provide OSCAR with controlled vocab and pharmacogenomic 
15:09:37 <michel> zakim, who is speaking?
15:09:48 <Zakim> michel, listening for 10 seconds I heard sound from the following: [GVoice] (61%)
15:09:50 <Zakim> +Bob_Powers
15:09:52 <michel> please mute your microphone
15:10:00 <mscottm> Marc Dumontier
15:10:17 <Joanne_Luciano> (thanks for the correction! (on spelling of Marc's name)
15:10:22 <bobP> ok now?
15:10:38 <Joanne_Luciano> There is an echo
15:10:39 <michel> zakim, who is talking?
15:10:50 <Zakim> michel, listening for 10 seconds I heard sound from the following: +1.519.638.aacc (65%), Bob_Powers (18%), [GVoice] (57%)
15:10:58 <michel> zakim, mute [GVoice]
15:10:58 <Zakim> [GVoice] should now be muted
15:11:01 <Zakim> -Bob_Powers
15:11:35 <mscottm> bobP - the echo seems to have originated from GVoice, not your phone
15:11:42 <bobP> k
15:11:43 <Zakim> + +1.937.775.aaff
15:11:43 <Joanne_Luciano> Physicans don't want to type in code - EVER, so will be in form of narrative in the patient chart
15:11:52 <Zakim> +Bob_Powers
15:12:28 <Joanne_Luciano> so, we're stuck with getting the info out of the record narrative - 
15:13:17 <Joanne_Luciano> Mark and Michel talked about developing a system that provided a form on the side of the screen that included the concept that they can edit (remove) if incorrect
15:13:26 <matthias_samwald> JBoss Drools
15:14:56 <Zakim> +??P26
15:15:10 <jun> zakim, ??P26 is jun
15:15:10 <Zakim> +jun; got it
15:16:19 <Joanne_Luciano> would someone type in what matthias just said?
15:16:41 <Zakim> + +1.610.592.aagg
15:16:53 <michel> discussion about the feasibility of using OpenCDS, since it's based on JBoss Drools
15:17:04 <michel> 1. NLP parsing of narrative
15:17:25 <matthias_samwald> matthias: OpenCDS = JBoss Drools + HL7 "Virtual Medical Record" interface for CDS + Apelon DTS for taxonomy management
15:18:01 <Zakim> +??P28
15:19:21 <benvvalk> benvvalk has joined #hcls
15:20:48 <michel> NCBO annotator - Nigam Shah has used this to do concept recognition and large scale associations - noisy part doesn't really matter in this case
15:20:52 <Joanne_Luciano> I'm wondering if we can do 'training' on the entries, like what's done with voice recognition
15:21:23 <Zakim> -matthias
15:21:46 <michel> each part of the clinical record contains different kinds of information; 
15:22:21 <michel> specialist - cardiology, dermatology - all context that could be used to downweight suggestions
15:22:54 <michel> semantic drupal could be effective
15:22:55 <matthias_samwald1> matthias_samwald1 has joined #hcls
15:23:40 <Zakim> +??P20
15:23:48 <michel> marc: mostly interested in progress notes - iterative development to make it more intelligent - pull out from past notes
15:23:51 <matthias_samwald1> zakim, ??P20 is matthias_samwald
15:23:51 <Zakim> +matthias_samwald; got it
15:24:01 <mscottm> Zakim, who is talking?
15:24:16 <Zakim> mscottm, listening for 14 seconds I heard sound from the following: +1.519.638.aacc (3%), ??P28 (3%)
15:24:39 <michel> template driven - needs to be filtered out
15:24:50 <mscottm> michel - who is talking? :)
15:26:15 <michel> Rafael richards from baltimore
15:26:17 <mscottm> Raphael Richards (MD from Baltimore)
15:27:19 <michel> rafael: semantic vista
15:28:11 <mscottm> q+
15:29:18 <michel> ... problem oriented approach would be more effective to track progress
15:29:19 <Zakim> +Tony
15:29:23 <BobF> BobF has joined #hcls
15:29:42 <michel> marc: oscar does support this, but physicians don't enter the codes, so it can't be tracked properly
15:30:02 <Zakim> -[GVoice]
15:30:07 <michel> rafael: codes are typically used for billing and reimbursement
15:30:20 <michel> marc: being able to not enter codes is the goal
15:31:06 <BobF> I'm back - is there a webex or slides, or just voice today?
15:31:16 <michel> mscottm: snomed codes for insurance; can't expect physician to pull out the code out of a dictionary; in our terminology task force with john madden, daniel rubin, you could have a report validation service
15:31:30 <michel> ... comes back with questions to resolve ambiguities
15:32:10 <Zakim> +[GVoice]
15:32:23 <michel> ... if typing free text in a conclusion section, they can be assisted with autocomplete to access the preferred terminology encoding system; end up with semantically annotated content - "behind" the free text 
15:32:44 <michel> ... try to resolve ambiguity at the point of data entry
15:33:02 <swoosh> swoosh has joined #hcls
15:33:34 <michel> rafael: smart interactive questions
15:33:41 <michel> ... how to capture high quality data?
15:34:08 <michel> ... are there open source tools to give you eclipse-like autocompletion, etc?
15:34:33 <michel> mscottm: NCBO has widgets for autocompletion
15:35:22 <michel> here's the NCBO REST API docs: http://www.bioontology.org/wiki/index.php/BioPortal_REST_services
15:36:23 <michel> rafael: need a clean interface to compose a note - and it's going to load up phrases, vocabulary, etc;  note about patient blood pressure; help you write high quality notes
15:37:00 <michel> mscottm: John Madden had an XML-based approach for reporting; anything that works in RDF?
15:39:43 <Zakim> -??P18
15:40:06 <michel> michel: how does OSCAR architecture facilitate the incorporation of new tool and support
15:40:15 <Zakim> - +1.610.592.aagg
15:40:42 <michel> marc: no plugins architecture as of now;  AJAX like call  or real time web service call; thinking about having a second window that acts as a support;
15:40:51 <michel> ... web service calls would be best
15:41:52 <michel> bobf: a couple of examples that i can provide of using a service call to enter content;  protege plugin for semi-automated content markup
15:42:48 <BobF> Semantator (Protege plug-in for semi-automated markup of clinical notes using ontologies): http://informatics.mayo.edu/CNTRO/index.php/Semantator
15:43:03 <michel> marc: large beta-testing community with different patient demographics - should be able to get good feedback in a reasonable amount of time; measure success - cost to provider
15:44:12 <michel> 2. CDS
15:45:05 <michel> marc: CDS for 2 projects a. ontario renal network - screening patients for potential renal disease
15:45:25 <michel> ... to what degree should we be considering a lab test for chronic kidney disease?
15:46:06 <michel> ... work with diabetes clinics; monitor data; to be able to organize the data would already be helpful; could be applied to many diseases
15:46:50 <michel> ... b. natal care -  reminders based on prior lab tests; or potential test suggestions
15:47:15 <michel> ... currently hard coding specific things which could be more generic ;  sounds like opencds could be useful here
15:47:54 <Zakim> -matthias_samwald
15:48:30 <Zakim> +??P7
15:48:42 <michel> marc: not too sure how easy it is to author rules; but access to it via service seems convenient
15:49:04 <michel> zakim, ??P7 is matthias_samwald
15:49:04 <Zakim> +matthias_samwald; got it
15:50:09 <michel> matthias: opencds makes use of JBoss drools - rule framework - tightly integrated java api; seemingly quite efficient over moderate size kb; 
15:50:40 <michel> ... rules are stored in a format defined by JBoss drools - positive is that it is an industry grade rules framework - but not sure how easy it is to translate to another format
15:51:41 <michel> ... SOAP-based web service provides access;  only send data (?) useful for CDS.
15:52:51 <michel> ... opencds mixes standards based approach with pragmatism
15:53:43 <michel> ... fairly complex; need lots of knowledge engineers to encode this into the system; 
15:54:15 <michel> ... not sure if I would use opencds - still a bit new - not much in terms of medical rules - system seems a bit heavyweight and complex
15:54:59 <michel> marc: like the idea of having a central webservice for this; oscar deployed at many clinics - could imagine each building rules; being able to share these would be important without having to redistribute them
15:55:21 <michel> ... pretty complex; not too sure how to build rules;  have to create drool files
15:55:41 <michel> matthias: used the rules that were provided, never created my own
15:55:42 <Zakim> -jun
15:56:33 <michel> ... want to make it as easy as possible to create these rules; don't want to necessarily interact with IT professionals
15:56:49 <michel> ... from the W3C perspective - how could parts of the framework be connected to SW technologies
15:56:59 <michel> ... other kinds of terminology or CDS services
15:57:08 <Zakim> -??P28
15:57:42 <michel> ... drools developers are looking at adding RDF/OWL
15:58:48 <michel> mscottm: what are the features of drools that attract you?  cecil lynch mentioned jess for a rule engine - but it has a commercial license 
15:59:10 <michel> ... rules are a form of knowledge that ought to be shareable; 
15:59:35 <michel> matthias: being able to integrate it into other workflows would be important
16:01:05 <Zakim> - +1.937.775.aaff
16:01:10 <BobF> (follow up from the first agenda topic...) Here are some toy examples of autocomplete using a terminology service on the back end:  http://informatics.mayo.edu/cts2widgets/search.html (autocomplete on the 'Ontology' field), http://informatics.mayo.edu/cts2/rest/widgets/viewmap.html (pulls from an eXist XML database)
16:01:11 <michel> ... with semantic web technologies - OWL reasoning, SPARQL queries
16:02:43 <mscottm> BobF - interesting - there is an EHR system in NL based on eXist, XForms, XQuery, etc.
16:02:52 <Zakim> -matthias_samwald
16:05:06 <Zakim> - +1.519.638.aacc
16:05:07 <Zakim> -Bob_Powers
16:05:07 <Zakim> -Tony
16:05:08 <Zakim> - +1.518.276.aadd
16:05:08 <Zakim> - +1.905.385.aaee
16:05:09 <Zakim> -michel
16:05:10 <Zakim> -mscottm
16:05:15 <luke> luke has left #HCLS
16:05:59 <michel> rrsagent, draft minutes
16:05:59 <RRSAgent> I have made the request to generate http://www.w3.org/2012/05/15-HCLS-minutes.html michel
16:06:10 <michel> rrsagent, make log world-visible
16:08:40 <Zakim> -[GVoice]
16:08:41 <Zakim> SW_HCLS()11:00AM has ended
16:08:41 <Zakim> Attendees were +1.613.293.aaaa, Tony, +1.519.638.aacc, +1.518.276.aadd, michel, matthias, mscottm, [GVoice], +1.905.385.aaee, Bob_Powers, +1.937.775.aaff, jun, +1.610.592.aagg,
16:08:41 <Zakim> ... matthias_samwald
16:27:30 <MacTed> MacTed has joined #hcls
17:10:26 <mscottm> mscottm has joined #hcls
17:37:13 <matthias_samwald> matthias_samwald has joined #hcls
18:06:06 <mscottm> mscottm has joined #hcls
18:18:38 <Zakim> Zakim has left #HCLS
18:51:58 <jun> jun has joined #hcls
18:54:42 <mscottm> mscottm has joined #hcls
19:12:40 <egonw_> egonw_ has joined #HCLS
19:20:31 <mscottm> mscottm has joined #hcls
19:36:53 <egonw_> egonw_ has joined #HCLS
19:37:49 <jun> jun has joined #hcls
20:00:37 <matthias_samwald> matthias_samwald has joined #hcls
20:13:37 <matthias_samwald> matthias_samwald has joined #hcls
20:27:07 <mscottm> mscottm has joined #hcls
20:28:35 <matthias_samwald> matthias_samwald has joined #hcls
20:31:31 <matthias_samwald1> matthias_samwald1 has joined #hcls
20:39:56 <matthias_samwald> matthias_samwald has joined #hcls
20:48:09 <matthias_samwald> matthias_samwald has joined #hcls
21:15:26 <matthias_samwald> matthias_samwald has joined #hcls
21:40:15 <matthias_samwald> matthias_samwald has joined #hcls
21:40:44 <matthias_samwald> matthias_samwald has joined #hcls
22:03:57 <mscottm> mscottm has joined #hcls
23:54:56 <matthias_samwald> matthias_samwald has joined #hcls