cTAKES handling of fractions in dosage
Hi, I am running the DrugAggregatePlainTextUMLSProcessor and noticing that cTAKES is not handling fractions for medication dosage correctly. For example, "Benadryl 1/2 tsp 3 times daily" produces a MedicationMention with a dosage of 2. Having tried different fractions (1/2, 1/3, 2/4, etc.), apparently the dosage is always set to the digit on the right of the '/'. I am wondering if this is a documented issue with cTAKES (I am using cTAKES version 3.1). Thanks in advance. Jain
RE: cTAKES handling of fractions in dosage
Pei, Thanks. I also wanted to mention that I have noticed the same behavior when ranges are specified in the context of dosage and frequency. For example, when I try: 'Take Lipitor 1-2 tabs 3-4 times a day for 7 days', dosage is annotated as '2' and frequency value is annotated as '4'. Looks like the same pattern is surfacing here (use the latter half) as well. Best,Jain > From: pei.c...@childrens.harvard.edu > To: dev@ctakes.apache.org > Subject: RE: cTAKES handling of fractions in dosage > Date: Thu, 20 Mar 2014 14:41:32 + > > Jain, > Jira has been open to track this: > https://issues.apache.org/jira/browse/CTAKES-289 > > It seems like a possible bug to me, but I only had a quick glance at the code: > http://svn.apache.org/repos/asf/ctakes/trunk/ctakes-drug-ner/src/main/java/org/apache/ctakes/drugner/fsm/machines/elements/DosagesFSM.java > It does seem to reuse the FractionStrengthCondition, but perhaps others could > comment it. > > --Pei > > > -Original Message- > > From: Ajay Jain [mailto:goti...@hotmail.com] > > Sent: Wednesday, March 19, 2014 3:48 PM > > To: dev@ctakes.apache.org > > Subject: cTAKES handling of fractions in dosage > > > > Hi, > > I am running the DrugAggregatePlainTextUMLSProcessor and noticing that > > cTAKES is not handling fractions for medication dosage correctly. For > > example, "Benadryl 1/2 tsp 3 times daily" > > produces a MedicationMention with a dosage of 2. Having tried different > > fractions (1/2, 1/3, 2/4, etc.), apparently the dosage is always set to the > > digit > > on the right of the '/'. I am wondering if this is a documented issue with > > cTAKES (I am using cTAKES version 3.1). Thanks in advance. > > Jain
De-identified lab tests dataset
Hello All, I am working on a use case for lab tests data using cTAKES and my online search to find a test dataset has been futile. I'll greatly appreciate if someone can share such a dataset or can point me in the right direction to go looking for one. Best, Ajay -- Founder & CEO Mobile Insights, Inc. (630) 408-8623
Re: De-identified lab tests dataset
Sorry, I wasn't clear. I am working on a related project and trying to figure out if the code can be repurposed for a lab mention annotator for cTAKES. From what I have seen, test names from different institutions are not standardized which makes it hard to standardize the resulting annotation. Getting access to a larger lab tests dataset (structured) will help me fine tune the model. Hope this helps. Ajay Sent from my iPhone > On Sep 29, 2014, at 2:12 PM, "Savova, Guergana" > wrote: > > Ajay, > cTAKES currently does not implement a method to discover labs from the text. > The motivation is that you can get that easily from the structured part of > the EMR (what Pete explained below). Hope this makes sense! > --Guergana > > -Original Message- > From: Peter Szolovits [mailto:p...@mit.edu] > Sent: Monday, September 29, 2014 2:32 PM > To: dev@ctakes.apache.org > Subject: Re: De-identified lab tests dataset > > Ajay, I'm confused by your query. cTakes is good at interpreting text, but > most lab test results are reported in tabular form that is most appropriately > searched by SQL queries. Sometimes lab results are also reported in > narrative notes, but parsing those is often more a matter of deciphering the > text structure of tables than of parsing real English text. What am I > misunderstanding? > > --Pete Sz. > >> On Sep 29, 2014, at 2:25 PM, Ajay Jain wrote: >> >> Hello All, >> >> I am working on a use case for lab tests data using cTAKES and my >> online search to find a test dataset has been futile. I'll greatly >> appreciate if someone can share such a dataset or can point me in the >> right direction to go looking for one. >> >> Best, >> Ajay >> >> -- >> Founder & CEO >> Mobile Insights, Inc. >> (630) 408-8623 >
Re: De-identified lab tests dataset
John, I am in the initial stages of my project and I'll take whatever dataset you are able to provide without spending a lot of effort extracting it. Thanks. Ajay Sent from my iPhone > On Sep 30, 2014, at 5:22 AM, "John Green" wrote: > > How large? And across how many EMRs? > > > JG > — > Sent from Mailbox > > On Mon, Sep 29, 2014 at 6:58 PM, Ajay Jain > wrote: > >> Sorry, I wasn't clear. I am working on a related project and trying to >> figure out if the code can be repurposed for a lab mention annotator for >> cTAKES. From what I have seen, test names from different institutions are >> not standardized which makes it hard to standardize the resulting >> annotation. Getting access to a larger lab tests dataset (structured) will >> help me fine tune the model. >> >> Hope this helps. >> Ajay >> Sent from my iPhone >>> On Sep 29, 2014, at 2:12 PM, "Savova, Guergana" >>> wrote: >>> >>> Ajay, >>> cTAKES currently does not implement a method to discover labs from the >>> text. The motivation is that you can get that easily from the structured >>> part of the EMR (what Pete explained below). Hope this makes sense! >>> --Guergana >>> >>> -Original Message- >>> From: Peter Szolovits [mailto:p...@mit.edu] >>> Sent: Monday, September 29, 2014 2:32 PM >>> To: dev@ctakes.apache.org >>> Subject: Re: De-identified lab tests dataset >>> >>> Ajay, I'm confused by your query. cTakes is good at interpreting text, but >>> most lab test results are reported in tabular form that is most >>> appropriately searched by SQL queries. Sometimes lab results are also >>> reported in narrative notes, but parsing those is often more a matter of >>> deciphering the text structure of tables than of parsing real English text. >>> What am I misunderstanding? >>> >>> --Pete Sz. >>> >>>> On Sep 29, 2014, at 2:25 PM, Ajay Jain wrote: >>>> >>>> Hello All, >>>> >>>> I am working on a use case for lab tests data using cTAKES and my >>>> online search to find a test dataset has been futile. I'll greatly >>>> appreciate if someone can share such a dataset or can point me in the >>>> right direction to go looking for one. >>>> >>>> Best, >>>> Ajay >>>> >>>> -- >>>> Founder & CEO >>>> Mobile Insights, Inc. >>>> (630) 408-8623
