Basic Principles of research design

Research Design Dent 313

Research fields in medicine

Biological sciences

Biology of disease Information to care for individual patients Clinical Epidemiology Epidemiology

Clinical sciences

Population sciences

Study of disease occurring in human population

Health services
Study of how non-biological factors affect the patients health

Clinical epidemiology

The science of making predictions about individual patients By counting clinical events of similar patients And using strong scientific methods To ensure that the predictions are accurate

Purpose of clinical epidemiology

Develop and apply methods of clinical observation that will lead to valid conclusions by avoiding being mislead by systematic error and the play of chance Obtaining the kind of information clinicians need to make good decision in the care of patients

Clinical epidemiology

It is clinical

it answers clinical questions It guides clinical decision making

Evidence-based medicine

Application of clinical epidemiology to the care of the patient

Basic principles

Clinical question Variables

Things that vary and can be measured

Dependent vs. independent variables

Health outcomes Numbers and probability

Quantitative vs. qualitative

Clinical question

Is the patient sick or well (abnormality) How accurate are tests used to diagnose disease (diagnosis) How often does a disease occur (frequency) What factors are associated with an increased risk of disease (risk) What are the consequences of having a disease (prognosis) How does treatment change the course of disease (treatment) Does an intervention on well people keep disease from arising (prevention) What lead to disease (cause)

Health outcomes

Events that can be studied directly in intact humans only Include the five Ds

Disease Discomfort Dissatisfaction Disability Death

Numbers and probability

Clinical science depends on quantitative measures Impressions, instincts and beliefs are only important when added to a solid grounds of numerical information

This allows for better confirmation And estimation of error

Prediction of treatment outcomes or disease sequence

Better be expressed as a percentage

(Probability) needs to be expressed quantitatively

Estimated by referring to past experience with groups of similar patients

Population and samples

Populations All people in a defined setting with certain defined characteristics

Examples:
disease

The general population A hospitalized population A population of patients with a specific

Population and samples

A sample Is a subset of people in the defined population Selected from that population It is not practical to test all the population Clinical research is carried out on samples A sample makes inference about the population

Population and samples

Two important points in sampling

Are the conclusions of the research

correct for the people in the sample?

If so, does the sample represent fairly

the population of interest?

A sample is representative

Depends on how a sample was selected Equal chance for all members vs. misrepresentation Computerized programs for selection of samples

Bias

Definition:

A process at any stage of inference tending

to produce results that depart systematically from the true values Any trend in the collection, analysis, interpretation, publication, or review of the data that can lead to conclusions that are systematically different from the truth

Categories of bias

Selection bias Measurement bias Confounding bias

Selection bias

Occurs when comparisons are made between groups of patients that differ in ways other than the main factors under study Example:
Examine dental caries among different age groups Examine perio condition without adjustment for smoking

Measurement bias

Occurs when the methods of measurement are not similar among different groups of patients Examples
Examine dental caries visually vs. radiographically Examine the WL of Roots using different techniques

Confounding bias

Occurs when two factors or processes are associated or "travel together " and the effect of one is confused with or distorted by the effect of the other Example:
TG and cholesterol levels are associated with risk for coronary heart disease Education and/or income with good health Folic acid vs. lower rates of colon cancer People taking multivitamins are health conscious about diet and exercise

Confounding bias

A variable is not confounded if it is directly along the path from cause to effect A confounding variable is not necessarily a cause itself

May be related to the suspected cause and

the effect in an instance but not related in nature

Bias

Selection bias is an issue in patients selection for observation, and so it is important in the design of a study

Bias

Confounding bias is an issue in analysis of the data, once the observations have been made

Bias

Often in the same study more than one bias operates A distinction must be made between the potential for bias and the actual presence of bias in a particular study

Dealing with bias

Identification of bias Measuring the potential effect of bias

Modifying the research design when the

potential effect on the result is big Changing the conclusions in a clinically meaningful way when the effect is not big enough

Chance

Unbiased samples may misrepresent the population because of chance Chance is the divergence of an observation on a sample from the true population value is called also random variation

Example: Tossing a coin 100 times The larger the sample size the less the
chance

Chance vs. bias

Bias distorts the situation in one direction or another Chance / random variation results in an observation above the true value as likely as one below it.

The mean of many unbiased observations of

a sample approximates the true observation of the population In small samples this may not be close to the true observation of the population

Bias v. chance

Bias can be prevented by proper conduction of clinical investigations Bias can be corrected through proper data analysis
Chance cannot be eliminated Its influence can be reduced by proper research design

Chance
Statistics can be used to estimate the probability of chance or random variation Chance cant be eliminated, but its influence can be reduced by proper design of research

Relationship between bias & chance

True BP Intra-arterial canula

BP measurement
Sphygmomanometer

chance

bias 80 90

Validity

Truth Validity is correspondence to the true value measured or searched for For an observation to be valid, it must be neither biased nor incorrect due to chance Types Internal validity External validity

Internal validity

Is the degree to which the results of a study are correct for the patients being studied Internal

Applies to the conditions of the particular group of patients being observed and not to others

Is determined by how well the design, data collection and analyses are conducted and threatened by biases and random variation Necessary but not sufficient by itself

External validity (Generalizability)

Is the degree to which the results of an observation hold true in other settings The answer of:

Assuming that the results are true in other settings, do they apply to my patients as well?

Generalizability assumes that patients in a study are similar to other patients A study with high internal validity may be misleading if its results are generalized to the wrong patients

All patients with condition of interest

Internal validity

sampling sample
sample

patients

A Selection bias

population

? ?

Measurement & confounding bias

chance

External validity Generalizability

Conclusion