| Lab Tools |
|---|
| EBM |
|---|
| Diagnosis |
| Therapy |
| Prognosis |
| Etiology |
| Checklists |
| Systematic Reviews |
| ANNs |
| Statistical Modeling |
| Links |
| Bioinformatics Links |
|---|
| Genomic Mapping |
| RNA Sequence Analysis |
| DNA Sequence Analysis |
| Protein Structure |
| Biological Pathways |
| Microarrays |
| Proteomics |
| Nucleotide Polymporphisms |
2x2 Table for Therapy Studies
Event |
||||
|---|---|---|---|---|
Present |
Absent |
Total |
||
Treatment |
New |
a |
b |
a+b |
Standard |
c |
d |
c+d |
|
Total |
a+c |
b+d |
a+b+c+d |
|
Clinical Parameters
1. Experimental Event Rate (EER) = a÷(a+b)
The experimental event rate (EER) is the probability of an event (good or bad) for a patient receiving the experimental, or new, treatment.
2. Control Event Rate (CER) = c ÷(c+d)
The control event rate (CER) is the probability of an event (good or bad) for a patient receiving the control, or standard, treatment.
3. Absolute Risk Reduction (ARR) or Absolute Risk Increase (ARI) = CER-EER
The absolute risk reduction is the amount by which the risk is reduced for those in the experimental group. In other words, the ARR quantifies the decreased risk due to the new treatment relative to standard treatment. Since neither the CER nor the EER can be less than 0% nor more than 100%, the ARR cannot be more than 100%. A negative ARR means that the risk is actually increased and the parameter is called the absolute risk increase (ARI). An absolute risk increase indicates that the new treatment is not only not better than the control, but is in fact more harmful than standard treatment.
4. Relative Risk Reduction (RRR) or Relative Risk Increase (RRI) = (CER-EER)÷CER
The relative risk reduction quantifies the decreased risk due to the new treatment relative to the control risk. In cases where the CER and EER are very small, the decreased risk can be made to appear huge by using the RRR instead of the ARR. If the value for the RRR is negative then the risk is actually higher and the parameter is called the relative risk increase. A relative risk increase means that the new treatment is not only not better than the control, but is in fact more harmful than standard treatment.
5. Number Needed to Treat (NNT) or Number Needed to Harm (NNH) = 1÷ARR [where ARR is expressed as a proportion--NOT a percentage]
The number needed to treat quantifies the number of patients that would need to receive the new treatment before one might be expected to benefit from treatment. The lower the NNT the more effective the treatment, i.e., an NNT of 4 means that only 4 patients would need to be treated to see a positive event (lack of recurrent AMI, for example) in one of the patients. If the NNT is negative then it really reflects the number of patients that must be treated to have one negative (venous thrombosis, for example) event. In this case, the parameter is called the number needed to harm (NNH).
6. Relative Risk (RR) = (a÷(a+b))÷(c ÷(c+d)) = eer÷cer
The relative risk is the ratio of the proportion of those with a positive event in the experimental group to that of those with a positive event in the control group. Along with the odds ratio, the relative risk is often used either directly or following log (or natural log) transformation as a parameter for combining studies in meta-analysis and systematic reviews.
7. Odds Ratio (OR) = (a÷b)÷(c+d)
The odds ratio is the ratio of the odds of a positive event in the experimental group to the odds of a positive event in the control group. Along with the relative risk, the odds ratio is often used either directly or following log (or natural log) transformation as a parameter for combining studies in meta-analysis and systematic reviews.