Monday, May 31, 2010

MDD

Minutes (courtesy Patience Gallagher)

Minutes:

  • PV
    • Reminder of the original concept:
      • Group patients on SSRIs into 3 groups based on whether their medication had a high, medium or low affinity for the serotonin transporter - determine if there is a dose response for bleeding events
        • Use this design instead of a case-control
        • Decided against self-matched analysis because that approach is best when the exposure is intermittent and has immediate, transient effects
      • Doing this study is important, as there is limited data available in the literature, but the prior is high (Smoller et al., 2009, Archives of Internal Medicine)
      • Outcome of interest: Bleeds (e.g. stroke, GI bleeds)
    • Vivian, Roy and Victor have worked on various iterations of the same general idea – the group needs to decide on final approach.
    • The Plan:
      • Use a test of proportions (Zak has a reference for this that he can distribute)
        • (This approach is kind of like a Chi Square)
      • Use only patients on monotherapy
        • We are not looking at dose of medication, just where the prescription falls on the affinity spectrum, which will be divided into three groups (high, medium and low affinity)
      • Start with a patient’s first exposure to AD (not first event) à look forward 6 months. If event doesn’t happen in those six months, restart the clock.
        • Although six months is the primary window of time, a sensitivity analysis of 30 days will also be done.
      • If a patient switches categories (goes from high to medium affinity drug) they are censored. However, if a patient switches from one drug to another within the same affinity category, they stay in the analysis.
      • As a control, we’ll look at patients with: MI, DVT, prostate cancer, colon cancer, asthma, and breast cancer (?)
      • The 3 groups (high, medium and low affinity) will be compared on visit intensity, age, gender
        • As long as visit intensity isn’t associated with just one of the categories of affinities, it should not be a confounder.
    • Victor has written most of the code needed for these analyses, so he will incorporate the ideas discussed today and bring the results to the meeting next week.
    • Additional issues to consider:
      • Using another psychotropic comparator as a negative control would be good, but difficult to do.
      • Look at depression response (do patients actually get better while on AD?)
      • Collaboration with the Stroke Service at MGH (Dr. Furie) – They are interested in collaborating – Roy will follow up with them.
        • They have a comprehensive stroke database (that includes imaging data) that could be incredibly useful for the PV component – And reciprocally, our AD exposure info/algorithms would be beneficial to them.
        • Protocol will need to be amended to incorporate their data in our analyses

No comments: