+ Reply to Thread
Results 1 to 4 of 4

Thread: Frequent user of ED

  1. #1
    Points: 8,411, Level: 61
    Level completed: 87%, Points required for next Level: 39

    Posts
    20
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Frequent user of ED




    At work we have 213 patients who were identified as frequent users of the emergency department in a hospital.

    These patients have over the last 18 months been referred to a clinic where they received lifestyle classes in order to stop them using the emergency services with such regularity. The time they received instruction was between 1 month and 8 months, average 5 months, depending on how well they responded.

    We have summed their ED attendances in 6 month blocks covering four years prior to referral and summed the attendances 6 months after discharge. Prior to referral the number of attendances per 6 month period was, 95, 90, 80, 107, 123, 125, 139 and 180. In the six months after discharge the number of attendances was 112. Note the periods do not necessarily correspond to the same calendar periods as both referrals and discharges were staggered over the 18 months.

    The business question is, has the clinic succeeded in changing behaviour of these patients? Unfortunately due to national IG laws and patient confidentiality, until a person is referred we cannot track their activity even though the information is available and consent to use their data is only given on referral. I was thinking of pairing each patient with a similar patient who had not been referred and carry out the same analysis for them.

  2. #2
    TS Contributor
    Points: 19,174, Level: 87
    Level completed: 65%, Points required for next Level: 176
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,079
    Thanks
    123
    Thanked 428 Times in 329 Posts

    Re: Frequent user of ED

    Quote Originally Posted by scotchpie View Post
    I was thinking of pairing each patient with a similar patient who had not been referred and carry out the same analysis for them.
    This sounds broadly sensible, but do such similar patients exist? Aren't these 213 people your 213 patients with the highest frequency of admissions, such that any comparison group would necessarily have a lower frequency of admission?
    Matt aka CB | twitter.com/matthewmatix

  3. #3
    Points: 8,411, Level: 61
    Level completed: 87%, Points required for next Level: 39

    Posts
    20
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Frequent user of ED

    Quote Originally Posted by CowboyBear View Post
    This sounds broadly sensible, but do such similar patients exist? Aren't these 213 people your 213 patients with the highest frequency of admissions, such that any comparison group would necessarily have a lower frequency of admission?
    Exactly but I thought if there was no decline in the control group it would add wait to the argument that being referred reduces attendances.

    I think the best way forward is just to use these numbers and comparing previous behaviour with more recent behaviour but trying to determine if the decline is due to being referred is what's causing me problems.

    I did initially analyse the data on a patient by patient basis. Basically for each patient I took the average weekly attendance from 12 months prior to referral and depending on how many weeks they had post discharge, randomly selected and summed that many numbers from a Poisson distribution centred on the weekly average to give an expected count per patient. I then summed all the results to give an overall expected count and repeated 1000 times to give a distribution which I then compared to the summed actuals.

    However a university near us involved in the evaluation said we haven't considered regression to the mean and so management want to start again.

  4. #4
    TS Contributor
    Points: 19,174, Level: 87
    Level completed: 65%, Points required for next Level: 176
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,079
    Thanks
    123
    Thanked 428 Times in 329 Posts

    Re: Frequent user of ED


    Yep - regression to a mean is a huge concern here. Given that you've selected a group based on their extreme scores on a variable that no doubt includes some random variation, it'd be almost inevitable that their admissions would be lower on the next measurement point.

    Keep in mind also that the latest measurement point is lower than the one immediate previous, but is about the same as the average admission rate in the baseline period.
    Matt aka CB | twitter.com/matthewmatix

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats