Is a "retrospective-prospective study design" a recognized study design? Or does this even exist? This is where you take retrospective data as a control group and then implement an intervention on a prospective group (the experimental group) and compare the outcome between the retrospective and prospective data. For example, I'm interested in implementing a new protocol on reducing infection rates on a group of patients on a nursing unit. I use approximately 6 months of "pre-data" based on standard care and then implement this new protocol on new patients in the upcoming 6 months. I then compare infection rates between the group that was before the intervention and then the group after the intervention.
Thank you. I'm asking specifically if there is a design where you use both retrospective and prospective data in the same study. I have not seen this used and I know there are hesitancy with using retrospective data as control.
Yes. There is such a design as a retospective-prospective cohort study ("retropropspective cohort study".). In such a study ,a cohort is identified fro a past time , classified by exposure and followed for incidence and/or mortality into the future and the effect of exposure assessed by relative risk measures. The control group ls can be internal or external. This type of study is often used in occupational epidemiology.
Your study is not really of this type. Rather it is comparing infection rate with the new protocol to an external historic control group which is not ideal as the calendar time effect and patient characteristics and case mix are not controlled for (something else may have changed in the hospital environment or the case mix / age sex distribution may have changed ).
First of all, we should not mix between the study design (like case-control, cohort, clinical trial) with the chronological sequence (retrospective, or prospective). Your study design is a quasi-experimental study (pre-post design).
Regarding the mix of retrospective and prospective, I think that there is a design called historic prospective design.
Namir G Al-Tawil and James Leigh Thank you for your feedback. I agree it is not ideal to use retrospective data as a control group and prospective data to test if an intervention is effective. However, due to low number of participants to recruit from in this case, it almost serves like a quality improvement project but with comparison group being the pre-intervention. A quasi-experimental will make sense using the historical data as the control.
- Badges
- Science topic
- Similar topics
- Psychology