You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@ctakes.apache.org by "Finan, Sean" <Se...@childrens.harvard.edu> on 2014/12/19 23:11:46 UTC
RE: cTakes Annotation Comparison --- (^:
Apologies accepted. I'm really glad that you found the problem.
So what you are saying is (just to be very very clear to everybody reading this thread):
>FastUMLSProcessor found 2795 matches (2,842 including overlaps)
While
> UMLSProcessor found 2632 matches (2,735 including overlaps)
--- So recall is BETTER in the fast lookup
And...
>FastUMLSProcessor found 30,716 annotations
While
>UMLSProcessor found 31,598 annotations
--- So precision is also looking BETTER in the fast lookup
Now maybe there will be a little more buy-in for the fast lookup.
Cheers,
Sean
-----Original Message-----
From: Bruce Tietjen [mailto:bruce.tietjen@perfectsearchcorp.com]
Sent: Friday, December 19, 2014 5:05 PM
To: dev@ctakes.apache.org
Subject: Re: cTakes Annotation Comparison
My apologies to Sean and everyone,
I am happy to report that I found a bug in our analysis tools that was missing the last FSArray entry for any FSArray list.
With the bug fixed, the results look MUCH better.
UMLSProcessor found 31,598 annotations
FastUMLSProcessor found 30,716 annotations
There were 23,522 annotations that were exact matches between the two.
When comparing with the gold standard annotations (4591 annotations):
UMLSProcessor found 2632 matches (2,735 including overlaps) FastUMLSProcessor found 2795 matches (2,842 including overlaps)
[image: IMAT Solutions] <http://imatsolutions.com> Bruce Tietjen Senior Software Engineer
[image: Mobile:] 801.634.1547
bruce.tietjen@imatsolutions.com
On Fri, Dec 19, 2014 at 1:49 PM, Bruce Tietjen < bruce.tietjen@perfectsearchcorp.com> wrote:
>
> I'll do that -- there is always a possibility of bugs in the analysis
> tool.
>
>
> [image: IMAT Solutions] <http://imatsolutions.com> Bruce Tietjen
> Senior Software Engineer
> [image: Mobile:] 801.634.1547
> bruce.tietjen@imatsolutions.com
>
> On Fri, Dec 19, 2014 at 1:39 PM, Finan, Sean <
> Sean.Finan@childrens.harvard.edu> wrote:
>>
>> Sorry, I meant “Do some spot checks on the validity”. In other
>> words, when your script reports that a cui and/or span is missing,
>> manually look at the data and see if it really is. Just open up one
>> .xmi in the CVD and see what it looks like.
>>
>>
>>
>> Thanks,
>>
>> Sean
>>
>>
>>
>> *From:* Bruce Tietjen [mailto:bruce.tietjen@perfectsearchcorp.com]
>> *Sent:* Friday, December 19, 2014 3:37 PM
>> *To:* dev@ctakes.apache.org
>> *Subject:* Re: cTakes Annotation Comparison
>>
>>
>>
>> My original results were using a newly downloaded cTakes 3.2.1 with
>> the separately downloaded resources copied in. There were no changes
>> to any of the configuration files.
>>
>> As far as this last run, I modified the UMLSLookupAnnotator.xml and
>> AggregatePlaintextFastUMLSProcessor.xml. I've attached the modified
>> ones I used (but they may not get through the mailing list).
>>
>>
>>
>>
>>
>>
>> [image: Image removed by sender. IMAT Solutions]
>> <http://imatsolutions.com>
>>
>> *Bruce Tietjen*
>> Senior Software Engineer
>> [image: Image removed by sender. Mobile:]801.634.1547
>> bruce.tietjen@imatsolutions.com
>>
>>
>>
>> On Fri, Dec 19, 2014 at 1:27 PM, Finan, Sean <
>> Sean.Finan@childrens.harvard.edu> wrote:
>>
>> Hi Bruce,
>>
>> I'm not sure how there would be fewer matches with the overlap
>> processor. There should be all of the matches from the non-overlap
>> processor plus those from the overlap. Decreasing from 215 to 211 is
>> strange. Have you done any manual spot checks on this? It is really
>> bizarre that you'd only have two matches per document (100 docs?).
>>
>> Thanks,
>> Sean
>>
>> -----Original Message-----
>> From: Bruce Tietjen [mailto:bruce.tietjen@perfectsearchcorp.com]
>> Sent: Friday, December 19, 2014 3:23 PM
>> To: dev@ctakes.apache.org
>> Subject: Re: cTakes Annotation Comparison
>>
>> Sean,
>>
>> I tried the configuration changes you mentioned in your earlier email.
>>
>> The results are as follows:
>>
>> Total Annotations found: 12,161 (default configuration found 8,284)
>>
>> If counting exact span matches, this run only matched 211 (default
>> configuration matched 215).
>>
>> If counting overlapping spans, this run only matched 220 (default
>> configuration matched 224)
>>
>> Bruce
>>
>>
>>
>> [image: IMAT Solutions] <http://imatsolutions.com> Bruce Tietjen
>> Senior Software Engineer
>> [image: Mobile:] 801.634.1547
>> bruce.tietjen@imatsolutions.com
>>
>> On Fri, Dec 19, 2014 at 12:16 PM, Chen, Pei <
>> Pei.Chen@childrens.harvard.edu>
>> wrote:
>> >
>> > Kim,
>> >
>> > Maintenance is the factor not bugs/issue to forge ahead.
>> >
>> > They are 2 components that do the same thing with the same goal (As
>> > Sean mentioned, one should be able configure the new code base to
>> > replicate the old algorithm if required- it’s just a simpler and
>> > cleaner code base. If this is not the case or if there are issues,
>> > we should fix it and move forward.).
>> >
>> > We can keep the old component around for as long as needed, but
>> > it’s likely going to have limited support…
>> >
>> > --Pei
>> >
>> >
>> >
>> > *From:* Kim Ebert [mailto:kim.ebert@imatsolutions.com]
>> > *Sent:* Friday, December 19, 2014 1:47 PM
>> > *To:* Chen, Pei; dev@ctakes.apache.org
>> >
>> > *Subject:* Re: cTakes Annotation Comparison
>> >
>> >
>> >
>> > Pei,
>> >
>> > I don't think bugs/issues should be part of determining if one
>> > algorithm vs the other is superior. Obviously, it is worth
>> > mentioning the bugs, but if the fast lookup method has worse
>> > precision and recall but better performance, vs the slower but more
>> > accurate first word lookup algorithm, then time should be invested
>> > in fixing those bugs and resolving those weird issues.
>> >
>> > Now I'm not saying which one is superior in this case, as the data
>> > will end up speaking for itself one way or the other; bus as of
>> > right now, I'm not convinced yet that the old dictionary lookup is
>> > obsolete yet, and I'm not sure the community is convinced yet either.
>> >
>> >
>> >
>> > [image: IMAT Solutions] <http://imatsolutions.com>
>> >
>> > *Kim Ebert*
>> > Software Engineer
>> > [image: Office:]801.669.7342
>> > kim.ebert@imatsolutions.com <gr...@imatsolutions.com>
>> >
>> > On 12/19/2014 08:39 AM, Chen, Pei wrote:
>> >
>> > Also check out stats that Sean ran before releasing the new
>> > component
>> on:
>> >
>> >
>> > http://svn.apache.org/repos/asf/ctakes/trunk/ctakes-dictionary-look
>> > up- fast/doc/DictionaryLookupStats.docx
>> >
>> > From the evaluation and experience, the new lookup algorithm should
>> > be a huge improvement in terms of both speed and accuracy.
>> >
>> > This is very different than what Bruce mentioned… I’m sure Sean
>> > will chime here.
>> >
>> > (The old dictionary lookup is essentially obsolete now- plagued
>> > with bugs/issues as you mentioned.)
>> >
>> > --Pei
>> >
>> >
>> >
>> > *From:* Kim Ebert [mailto:kim.ebert@perfectsearchcorp.com
>> > <ki...@perfectsearchcorp.com>]
>> > *Sent:* Friday, December 19, 2014 10:25 AM
>> > *To:* dev@ctakes.apache.org
>> > *Subject:* Re: cTakes Annotation Comparison
>> >
>> >
>> >
>> > Guergana,
>> >
>> > I'm curious to the number of records that are in your gold standard
>> > sets, or if your gold standard set was run through a long running
>> cTAKES process.
>> > I know at some point we fixed a bug in the old dictionary lookup
>> > that caused the permutations to become corrupted over time.
>> > Typically this isn't seen in the first few records, but over time
>> > as patterns are used the permutations would become corrupted. This
>> > caused documents that were fed through cTAKES more than once to
>> > have less codes returned than the first time.
>> >
>> > For example, if a permutation of 4,2,3,1 was found, the permutation
>> > would be corrupted to be 1,2,3,4. It would no longer be possible to
>> > detect permutations of 4,2,3,1 until cTAKES was restarted. We got
>> > the fix in after the cTAKES 3.2.0 release.
>> > https://issues.apache.org/jira/browse/CTAKES-310
>> > Depending upon the corpus size, I could see the permutation engine
>> > eventually only have a single permutation of 1,2,3,4.
>> >
>> > Typically though, this isn't very easily detected in the first 100
>> > or so documents.
>> >
>> > We discovered this issue when we made cTAKES have consistent output
>> > of codes in our system.
>> >
>> >
>> >
>> > [image: IMAT Solutions] <http://imatsolutions.com>
>> >
>> > *Kim Ebert*
>> > Software Engineer
>> > [image: Office:]801.669.7342
>> > kim.ebert@imatsolutions.com <gr...@imatsolutions.com>
>>
>> >
>> > On 12/19/2014 07:05 AM, Savova, Guergana wrote:
>> >
>> > We are doing a similar kind of evaluation and will report the results.
>> >
>> >
>> >
>> > Before we released the Fast lookup, we did a systematic evaluation
>> across three gold standard sets. We did not see the trend that Bruce
>> reported below. The P, R and F1 results from the old dictionary look
>> up and the fast one were similar.
>> >
>> >
>> >
>> > Thank you everyone!
>> >
>> > --Guergana
>> >
>> >
>> >
>> > -----Original Message-----
>> >
>> > From: David Kincaid [mailto:kincaid.dave@gmail.com
>> > <ki...@gmail.com>]
>> >
>> > Sent: Friday, December 19, 2014 9:02 AM
>> >
>> > To: dev@ctakes.apache.org
>> >
>> > Subject: Re: cTakes Annotation Comparison
>> >
>> >
>> >
>> > Thanks for this, Bruce! Very interesting work. It confirms what
>> > I've
>> seen in my small tests that I've done in a non-systematic way. Did
>> you happen to capture the number of false positives yet (annotations
>> made by cTAKES that are not in the human adjudicated standard)? I've
>> seen a lot of dictionary hits that are not actually entity mentions,
>> but I haven't had a chance to do a systematic analysis (we're working
>> on our annotated gold standard now). One great example is the
>> antibiotic "Today". Every time the word today appears in any text it
>> is annotated as a medication mention when it almost never is being used in that sense.
>> >
>> >
>> >
>> > These results by themselves are quite disappointing to me. Both the
>> UMLSProcessor and especially the FastUMLSProcessor seem to have
>> pretty poor recall. It seems like the trade off for more speed is a
>> ten-fold (or more) decrease in entity recognition.
>> >
>> >
>> >
>> > Thanks again for sharing your results with us. I think they are
>> > very
>> useful to the project.
>> >
>> >
>> >
>> > - Dave
>> >
>> >
>> >
>> > On Thu, Dec 18, 2014 at 5:06 PM, Bruce Tietjen <
>> bruce.tietjen@perfectsearchcorp.com> wrote:
>> >
>> >
>> >
>> > Actually, we are working on a similar tool to compare it to the
>> > human
>> >
>> > adjudicated standard for the set we tested against. I didn't
>> > mention
>> >
>> > it before because the tool isn't complete yet, but initial results
>> > for
>> >
>> > the set (excluding those marked as "CUI-less") was as follows:
>> >
>> >
>> >
>> > Human adjudicated annotations: 4591 (excluding CUI-less)
>> >
>> >
>> >
>> > Annotations found matching the human adjudicated standard
>> >
>> > UMLSProcessor 2245
>> >
>> > FastUMLSProcessor 215
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> > [image: IMAT Solutions] <http://imatsolutions.com>
>> > <http://imatsolutions.com> Bruce Tietjen
>> >
>> > Senior Software Engineer
>> >
>> > [image: Mobile:] 801.634.1547
>> >
>> > bruce.tietjen@imatsolutions.com
>> >
>> >
>> >
>> > On Thu, Dec 18, 2014 at 3:37 PM, Chen, Pei
>> >
>> > <Pei.Chen@childrens.harvard.edu
>> >
>> >
>> >
>> > wrote:
>> >
>> >
>> >
>> > Bruce,
>> >
>> > Thanks for this-- very useful.
>> >
>> > Perhaps Sean Finan comment more-
>> >
>> > but it's also probably worth it to compare to an adjudicated human
>> >
>> > annotated gold standard.
>> >
>> >
>> >
>> > --Pei
>> >
>> >
>> >
>> > -----Original Message-----
>> >
>> > From: Bruce Tietjen [mailto:bruce.tietjen@perfectsearchcorp.com
>> > <br...@perfectsearchcorp.com>]
>> >
>> > Sent: Thursday, December 18, 2014 1:45 PM
>> >
>> > To: dev@ctakes.apache.org
>> >
>> > Subject: cTakes Annotation Comparison
>> >
>> >
>> >
>> > With the recent release of cTakes 3.2.1, we were very interested in
>> >
>> > checking for any differences in annotations between using the
>> >
>> > AggregatePlaintextUMLSProcessor pipeline and the
>> >
>> > AggregatePlanetextFastUMLSProcessor pipeline within this release of
>> >
>> > cTakes
>> >
>> > with its associated set of UMLS resources.
>> >
>> >
>> >
>> > We chose to use the SHARE 14-a-b Training data that consists of 199
>> >
>> > documents (Discharge 61, ECG 54, Echo 42 and Radiology 42) as the
>> >
>> > basis for the comparison.
>> >
>> >
>> >
>> > We decided to share a summary of the results with the development
>> >
>> > community.
>> >
>> >
>> >
>> > Documents Processed: 199
>> >
>> >
>> >
>> > Processing Time:
>> >
>> > UMLSProcessor 2,439 seconds
>> >
>> > FastUMLSProcessor 1,837 seconds
>> >
>> >
>> >
>> > Total Annotations Reported:
>> >
>> > UMLSProcessor 20,365 annotations
>> >
>> > FastUMLSProcessor 8,284 annotations
>> >
>> >
>> >
>> >
>> >
>> > Annotation Comparisons:
>> >
>> > Annotations common to both sets: 3,940
>> >
>> > Annotations reported only by the UMLSProcessor: 16,425
>> >
>> > Annotations reported only by the FastUMLSProcessor: 4,344
>> >
>> >
>> >
>> >
>> >
>> > If anyone is interested, following was our test procedure:
>> >
>> >
>> >
>> > We used the UIMA CPE to process the document set twice, once using
>> >
>> > the AggregatePlaintextUMLSProcessor pipeline and once using the
>> >
>> > AggregatePlaintextFastUMLSProcessor pipeline. We used the
>> >
>> > WriteCAStoFile CAS consumer to write the results to output files.
>> >
>> >
>> >
>> > We used a tool we recently developed to analyze and compare the
>> >
>> > annotations generated by the two pipelines. The tool compares the
>> >
>> > two outputs for each file and reports any differences in the
>> >
>> > annotations (MedicationMention, SignSymptomMention,
>> >
>> > ProcedureMention, AnatomicalSiteMention, and
>> >
>> > DiseaseDisorderMention) between the two output sets. The tool
>> >
>> > reports the number of 'matches' and 'misses' between each
>> > annotation
>> set. A 'match'
>> >
>> > is
>> >
>> > defined as the presence of an identified source text interval with
>> >
>> > its associated CUI appearing in both annotation sets. A 'miss' is
>> >
>> > defined as the presence of an identified source text interval and
>> >
>> > its associated CUI in one annotation set, but no matching
>> > identified
>> >
>> > source text interval
>> >
>> > and
>> >
>> > CUI in the other. The tool also reports the total number of
>> >
>> > annotations (source text intervals with associated CUIs) reported
>> > in
>> >
>> > each annotation set. The compare tool is in our GitHub repository
>> > at
>> >
>> > https://github.com/perfectsearch/cTAKES-compare
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>> >
>>
>