Courtesy Patience Gallagher
Minutes:
Collapsing terms
o McLean admission à change to psych admission
o List of terms that Jordan gave Margarita that we didn’t necessarily annotate, Margarita will add after.
o Terms that have the same regular expression will be filtered at the end
o Medication category: fga
- We annotated as IW bipolar, but last time we said was CW, which one is it?
- Sergey says right now doesn’t matter, because the computer will decide
- We will keep it labeled as IW
o Li/vpa/lamtical à change to mood stablilizer
- Add term mood stabilizer(s)
o Neuro/cognitive impairment includes
- Confused and disoriented
- Gross cognitive impairment
- Significant cognitive deficits
- dementia
o Agitation includes
- Hyperactivity
- Hyper
- pacing
o dx depression includes:
- depressive disorder
- dsythymia
o bipolar disorder includes:
- dx bipolar disorder
- 296.0, .1, .4, .5, .6, .7
-
- .2, .3 are MDD, so we cannot say 296.x = BPD
o Inappropriate behavior category, leave in:
- Wanting to disrobe
- Inappropriate sexual contacts (do not put with excessive pleasurable activities)
o Rapid cycling
- 4 or more per year
o Mania will include
- Category now called “mania/manic”
- Category now called “manic episode”
- Cycling, cycles (not specified as rapid/less than 4 per year)
o Typos will include variations on spellings of:
- Grandiose
- distractibility
o “loose associations” will be its own category
o Depressed episode à put with hx depression
o “unable to read, study, concentrate” à put with distractibility
o “tx bipolar disorder” à add in term “rx”
o Hypomania will be own category
o hyper mood à mood elevation
o Delete:
§ Line 310: dx substance abuse, schizophreniaParanoid schizo-affected disorder
§ Out of control
Big group: 9:30-10:30
· Protocol in the grant
- Are we doing what we said in the grant? For ex. Step #3
-
- In grant, describes that classic way of doing NLP
- You come up with list of terms from your head without looking at notes.
- Then expand these terms, add regular expressions, negation
- Our method
-
- Is a hybrid of the 2. We annotated notes, but we also came up with a list of terms
- Annotate notes, generate list of terms, create regular expression, group, add in a priori terms, Tianxi goes through them and takes out terms that don’t matter (lasso), then feed to the computer
- The IRB will not really care that this is slightly different.
- Which method is better?
-
- Unknown
- Classic model relies on what’s in your head, our method relies on # notes reviewed
- We could try to compare, but it’s a little too late because our list of terms wasn’t blind to the notes
- Dr. Savova ) will be coming on boad as NLP team lead
-
- Would be good for her to give mini lecture about NLP so we are prepared to present at conferences
- Should consult with her about project
- Negation
-
- So far Margarita has only added negation to some terms
- Should modify algorithm so that every term also has corresponding negation term
- Negation terms are very common in psych notes
- Sergey to see if this can be done, although a lot of work
- Would be useful for future i2b2 projects
- Margarita explained that she plans on conducting a small validation study
-
- For a particular patient, she can provide an idea of how strong the diagnosis we assign (e.g. BP2) is by showing what are the arguments for/against placing a person in a particular class
· Next steps:
o Jordan, Vivian, Margarita, Sergey, Victor, Roy to meet on Tuesday, October 20th 10:00 – 11:00 to finish collapsing term.
No comments:
Post a Comment