/
Study Design Methods to Handle Noncompliance Study Design Methods to Handle Noncompliance

Study Design Methods to Handle Noncompliance - PowerPoint Presentation

yoshiko-marsland
yoshiko-marsland . @yoshiko-marsland
Follow
368 views
Uploaded On 2018-11-02

Study Design Methods to Handle Noncompliance - PPT Presentation

Loss to FollowUp In clinical medicine and research loss to follow up refers to a person who has not returned for continued care or evaluation eg because of death disability relocation or dropout ID: 710497

study follow patients loss follow study loss patients analysis treat cohort intention data randomized bias denominator treatment retrospective groups

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "Study Design Methods to Handle Noncompli..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Slide1

Study Design

Methods to Handle NoncomplianceSlide2

Loss to Follow-Up

In clinical medicine and research, loss to follow up refers to a person who has not returned for continued care or evaluation (e.g., because of death, disability, relocation, or drop-out).Slide3

Loss to Follow Up

Loss to follow-up can occur when researchers lose contact with participants in a trial for such reasons as migration or failure to maintain contact prior to the termination of a study or of planned endpoints. Planned data collection is incomplete as a result.Slide4

Loss to follow-up (LTF) bias

Loss to follow-up bias can occur when persons leaving the study are different to persons who stay in the study with respect to both the exposure

and the

outcomeSlide5

Loss to follow-up bias

If loss to follow up is low, loss to follow up bias is unlikely. If not low, identify whether loss to follow up was similar across groups. If not similar, identify whether loss to follow up was related to both the exposure

and the outcome.Slide6

Loss to follow-up bias

Vulnerable study designs are:

RCT (Randomized Controlled Trial)

Prospective cohort

Retrospective cohort

Case-control studies are not vulnerable because there is no follow-upSlide7

Loss to follow-up bias

There is much confusion about how to determine the proportion of patients lost to follow-up. In order to correctly calculate the follow-up rate, one needs to know the denominator.Slide8

Loss to follow-up

In a randomized controlled trial (RCT), the denominator for each group is the number of patients who were randomized,

not the number who received the treatment

. Slide9

Loss to follow-up

In a prospective cohort study the denominator is the entire group recruited at the start of the study.Slide10

Loss to follow-up

When calculating loss to follow-up in a retrospective cohort study, all individuals receiving treatment during the study period should be used as the denominator, not just those with complete data.Slide11

Intention to Treat Analysis

The preferred method of analysis of all subjects when there has been a significant drop-out or crossover rate is to use an intention-to-treat methodology. Slide12

Intention to Treat Analysis

In this method, all patient outcomes are counted with the group to which the patient was originally assigned even if the patient dropped out or switched groups. This approximates real life where some patients drop out or are non-compliant for various reasons. Slide13

Intention to Treat Analysis

Patients who dropped out or switched therapies must still be accounted for at the end of the trial since if their fates are unknown, it is impossible to accurately determine their outcomes. Some studies will attempt to use statistical models to estimate the outcomes that those patients should have had if they had completed the study, but the accuracy of this depends on the ability of the model to mimic reality.Slide14

Intention to Treat Analysis

Another biased technique involves removing patients from the study. Removing patients after randomization for reasons associated with the outcome is patently biased and grounds to invalidate the study. Leaving them in the analysis as an intention-to-treat is honest and will not inflate the results.Slide15

Intention to Treat Analysis

If the outcomes of patients who left the study are not known, a best case/worst case scenario should be applied and clearly described so that the reader can determine the range of effects applicable to the therapy.Slide16

Question

A researcher wants to compare decompression plus lumbar fusion with decompression alone in disc

herniation

and the data available are all patients receiving either treatment in the last 5 years (N = 275). However, the database from which the data are obtained is incomplete and only 190 have the necessary data available. Since the investigators stated as part of the inclusion criteria that only those patients with complete data are included, they consider the follow-up to be 100% (190/190). This is an example of a wrong conclusion being drawn in a:

Prospective Cohort Study

Randomized Controlled Trial

Retrospective Cohort StudySlide17

Answer

Retrospective Cohort Study

When calculating loss to follow-up in a retrospective cohort study, all individuals receiving treatment during the study period should be used as the denominator, not just those with complete data.

The denominator should include all patients who underwent the surgery irrespective of completeness of data. The follow-up rate for this example is 69% (190/275).Slide18

Question

Which of the following statements best describes an intention-to-treat analysis?

Analyses compare characteristics of participants who did and did not adhere to the randomized treatment.

Analyses exclude all participants who did not adhere to the assigned randomized treatment.

Analyses maintain the original randomized assignment of treatments in the definition of intervention and control groups.

Analyses reorganize participants into intervention and control groups based on their actual participation.Slide19

Answer

Analyses maintain the original randomized assignment of treatments in the definition of intervention and control groups.