Universidad de Ciudad del Cabo

Understanding Clinical Research: Behind the Statistics

637 ratings

If you’ve ever skipped over`the results section of a medical paper because terms like “confidence interval” or “p-value” go over your head, then you’re in the right place. You may be a clinical practitioner reading research articles to keep up-to-date with developments in your field or a medical student wondering how to approach your own research. Greater confidence in understanding statistical analysis and the results can benefit both working professionals and those undertaking research themselves. If you are simply interested in properly understanding the published literature or if you are embarking on conducting your own research, this course is your first step. It offers an easy entry into interpreting common statistical concepts without getting into nitty-gritty mathematical formulae. To be able to interpret and understand these concepts is the best way to start your journey into the world of clinical literature. That’s where this course comes in - so let’s get started! The course is free to enroll and take. You will be offered the option of purchasing a certificate of completion which you become eligible for, if you successfully complete the course requirements. This can be an excellent way of staying motivated! Financial Aid is also available.

De la lección

Getting things started by defining study types

Welcome to the first week of this course. We’ll be tackling five broad topics to provide you with an intuitive understanding of clinical research results. This isn’t a comprehensive statistics course, but it offers a practical orientation to the field of medical research and commonly used statistical analysis. The first topics will look at research methods and the collection of data - with a specific focus on study types. By the end of the lectures you should be able to identify which study types are being used and why the researchers selected them when you are reading a paper.

Observing and intervening: Observational & experimental studies3:10

Observing and describing: Case series studies3:14

Comparing groups: Case-control studies3:18

Collecting data at one point in time: Cross-sectional studies3:39

Studying a group with common traits: Cohort studies4:31

Let's intervene: Experimental studies6:48

Working with existing research: Meta-analysis and Systematic Review4:35

Conoce a los instructores

Juan H Klopper
Dr
Department of Surgery

Now we're going to move things up a gear.

We're going to discuss Case- control studies now.

In the previous lecture, I mentioned that there's actually more than one group.

There's going to be a case Group and a control group and

they�ve got to differ in some fundamental way.

There�s got to be some variable in which they differ.

And now begin to identify other sets of variables and

we're going see, is there a difference in those variables between those two groups.

So what we really do is we're choosing a spot in time and then we look rearwards.

And what do we want to do?

We want to identify differences in those variables and perhaps risk factors.

Now, I mentioned I did the same operation on a set of patients over and

over again and some developed a complication, some others did not.

When they developed those complications that is our spot in time.

We now look at data before those complications occur, so

that is a rearward look.

Now, let's consider an example.

Yung and colleagues,

they looked at factors associated with atopic disease in toddlers.

Now, that's allergic disease.

Now, the first sentence in the abstract says in this case-control study, so

it's a beautiful example of a case-control study.

So, they selected 206 toddlers.

Toddlers visiting a clinic and they collected all sorts of data

on a variety of variables but they had two main groups.

The case group was toddlers with atopic disease and

the control group without atopic disease.

So that diagnosis was made.

It was a point in time, and

then now they looked at data before that diagnosis was made.

So they looked at age, and gender, they looked at delivery variables,

breastfeeding patterns, family history, etc.

They took one at a time, one of these variables, and looked at differences

between those two groups, the group with atopic disease and the group without.

Wanted to see was there differences.

So notice very carefully, it is a rearward look, and

that is what makes a case-control study or series.

Now there are problems, they don't stand out from cases perhaps, but

there are problems with case-control series.

Number one is bias.

Now if you read that article, you'll see the authors

say that this clinic was four people from a higher socioeconomic group,

we got to ask the question, is the answers they came up with after the analysis,

is that generalizable to a more general population.

And inherent to these types of studies really is confounding.

Now what is confounding?

Confounding really is hidden causes.

Say for instance, for argument's sake,

they found a big difference in the breast feeding patterns between the two groups.

We could now say there is a difference between the two groups in the breast

feeding patterns, but that does not prove that breast feeding was the cause for

the difference between children with and without atopic disease.

So simply very important we can't exclude,

most of the time, confounding factors in case-control series.

Next up, we're going have a look at cross-sectional series.