PICOT question: Do more Congestive Heart Failure patients get more Nosocomial Infections than other Cardiac patients on a Cardiac Unit?
Which of those three variables would be Dependent, vs. Independent?
Hi! We are glad that you posted here! We mainly just want to see what you have tried so far and that you have put some effort into the problem. I would also suggest checking out this thread for some guidelines on smart posting behavior that can help you get answers that are better much more quickly.
Stand down @idahostats - this is a civil place for open dialog. The site is called TalkStats not StatAnswersNow. It is import to rationalize and probe an OP to understand their current knowledge base and logic.
Dependent variable is the outcome
Independent variables impact the outcome. Just looking at binary classification of patients as CHF (Y/N), would be fairly crude and may not address the true etiological/causal mechanism. Covariate of interest may include LOS, comorbidities, etc.
"Do congestive heart failure patients have a higher rate of nosocomial infection than non-congestive heart failure patients treated within a Cardiac Unit over the past ?? days when controlling for appropriate covariates."
That’s all my professor gave us, and other students tried it multiple ways. I originally had nosocomial infection as the independent but researched more on the internet that told me I probably was wrong. I was looking for a hard fast answer. If there isn’t one, and it’s open to interpretation, that’s all I need to know. My assignment was due last night as I posted the question. Hence the urgency.
The difficulty with this question for me was there was no “effect” from any one variable to measure. And there were only categorical data. I’ve been a nurse for 25 years, and could write a paper just on confounding variables, but that’s not built into the problem I was asked to solve. It’s a Nursing Research course, not a Stats course.
Just to clarify, a nosocomial infection is a hospital acquired infection. So CHF (y/n) = subsequent infection during stay, with CHF being the reason for admission, so occurring prior to infection. Given this context and scenario, what they are looking for is CHF = IV and Infection = DV.
My point is that CHF alone doesn't cause DV in the bigger picture of things. Nosocomial infection may be related to, if you are intubated, on antibiotics, length of stay, etc. CHF can be related to some of those things, so it is kind of naïve to say CHF caused nosocomial infection, but that is what they were looking for. I have seen enough PICO questions to guess that is the underlying intention.
I changed my dependent variable to Nosocomial infections after reading and using these two examples on the internet:
According to Kollef, Sharpless, Vlasnik, Pasque, (1997), "We identified four risk factors associated with the development of nosocomial infection (duration of mechanical ventilation, duration of urinary tract catheterization, postoperative empiric antibiotic administration, and female gender). The first three of these risk factors appear to be amenable to interventions aimed at reducing the occurrence of nosocomial infections." Interestingly, these authors tell us that three of these factors could potentially be controlled, to help reduce the rate of nosocomial infections.
Another study by Sheng, Wang, Lin, and Chang (2007), reported that of the 554 patients with nosocomial infections that died, the Host Factor of Congestive Heart Failure had a p-value of 0.005. They cited measures such as improving the immunity status of the host as possible ways to reduce the in-patient deaths due to nosocomial infections.
Could maybe someone clarify for a non-native speaker whether they have 2 DVs
(number of infections per patient, and number of patients infected), or whether
they just used sloppy language ("Do more Congestive Heart Failure patients get
more Nosocomial Infections?").