Tuesday, November 17, 2009

Open Source

A very insightful response from Fred Trotter. He lays down the options in a very nuanced and clear fashion. Much appreciated.

Thursday, November 12, 2009

Major Depressive Disorder

Perlis, Smoller, et al.,


MInutes courtesy Patience Gallagher.


·       Longitudinal Classifier

o   Roy and Victor will finalize parameters of algorithm

o   Victor will then report (and provide a visualization of):

§ % depressed, % well, # of all notes, etc

o   To query Crimson: Victor will provide a list of medical record numbers within the two groups of interest (responsive and resistant) to Lynn Bry who can then report how many samples are currently available within Crimson

§ Parameters may need to be readjusted, depending on response from Crimson

·       Discussion of Validation

o   The issue with last week’s approach:

§ The algorithm is based on the text, so the first level of validation should not use information (i.e. clinician’s extensive knowledge of a patient) that is not in the text.

o   New validation plan:

§ STEP ONE:

·       GOAL: Determine if an expert clinician’s classification (based on notes only) is the same as the result of the algorithm

·       Pull successfully classified notes

o   All of a patient’s notes will be reviewed

o   Clinicians will be blinded to the results of the classifier

o   The sample of notes will reflect the results of the algorithm: “Random but representational”

o   To keep the validation clean, it will be a “case-control” model - Treatment resistant vs. Responsive

o   For now, only the electronic medical record will be used.

§ The consensus was that patient charts would be more annoying than beneficial, and the electronic records probably have sufficient information

§ Additionally, the information from the paper records is not integrated into the algorithm

§ May look at paper records down the road

§ STEP TWO: Compare list of patients that Roy knows are treatment resistant or responsive and run their notes through the classifier

·       (Tianxi says this will be beneficial as it will give more power to the classifier)

§ STEP THREE: Use the Quick Inventory of Depression Severity (QIDS) as an external source of validation

·       Many patients have QIDS scores in their charts – can determine if the algorithm classification is consistent with performance on the QIDS – this would be a cross-sectional measure

o   The output of this approach would be: “Among patients classified s depressed, the mean QIDS score is ____”

§ NEXT STEPS:

·       Do first level of the validation over the next few weeks.

o   Victor will pass the notes to Roy.

o   Roy will be the sole clinician reviewing the notes

·       Manuscript:

o   Victor and Tianxi have provided their input to Roy

o   Roy will integrate this information and then re-distribute the manuscript to the group

·       PV

o   Update from Victor on obesity:

§ Compared the BMIs of this data set with all other patients and the distribution of the MDD sample is very similar, but right shifted compared to majority’s BMI distribution

·       This makes sense! - Being depressed (and on antidepressants) leads to weight gain