Basic Stats for the FRCS (Urol) Exam


Published on

A presentation covering basic statistics for the FRCS (Urol) Exam

Published in: Health & Medicine, Business

Basic Stats for the FRCS (Urol) Exam

  1. 1. Nikhil Vasdev, David ThomasDepartment of UrologyFreeman HospitalNewcastle upon Tyne
  2. 2.  Help in understanding clinical evidence that influences our day to day practice Essential to have a thorough understanding to function as a successful urologist Important to validate literature Essential for the FRCS (Urol) exam
  3. 3.  As Urologist we must be aware of a number of different ‘biases’ present in current literature which include Media Pharmaceutical Industry Colleagues
  4. 4.  Terminology1. Prevalence – Total number of cases in a population at a given time2. Incidence – The number of new cases in a population per unit time3. Prevalence = Incidence X disease duration4. Prevalence > Incidence = Applicable for chronic disease5. Prevalence = Incidence – for acute disease (e.g. common cold)
  5. 5.  Sensitivity  Number of true positives divided by number of all people with the disease  “Sensitivity = Positive in disease” Specificity  Number of true negatives divided by number of all people without the disease  “Specificity = Negative in health”
  6. 6.  Positive Predictive Value (PPV)  Number of true positives divided by number of people who tested positive for a disease  The probability of having a condition, given a positive test Negative Predictive Value (NPV)  Number of true negatives divided by number of people who tested negative for the disease  The probability of not having the condition given a negative test Important points  Unlike sensitivity and specificity, PPV is dependent on the prevalence of the disease  The higher the prevalence of a disease, the higher the positive predictive value of the test
  7. 7. Disease Table 1 + - Test + A B - C DSensitivity = A Specificity = D ______ ______ A + C B + DPPV = A NPV= D _______ _______ A + B C + D
  8. 8.  Meta-analysis Case-control study Cohort study Clinical trial
  9. 9.  Meta-analysis  Pooling of data from several studies (often via a literature search) to achieve a greater statical power  Main disadvantage – Cannot overcome limitations of individual studies or bias in study section Case-control study  Observational study (Retrospective)  Sample chosen on the basis of presence (cases) or absence (controls) of disease  Information collected about risk factors Cohort study  Observational study  Sample chosen on the basis of presence or absence of risk factors  Subjects are followed over time for development of disease Clinical trial  Experimental study  Compares benefits of 2 or more treatments  Highest quality study = RANDOMIZED CONTROL TRIAL
  10. 10.  Statistical technique for combining results of several studies into a single numerical estimate Validity of MA depends on the quality of the systematic review on which it‘s based Results are usually displayed with C.I., p values and a Forest plot ‘
  11. 11. A forest plot (or blobbogram) is a graphical display designed to illustratethe relative strength of treatment effects in multiple quantitativescientific studies addressing the same question. It was developed for usein medical research as a means of graphically representing a meta-analysis of the results of randomized controlled trials
  12. 12.  A Bias is defined as when an outcome is more likely to occur than another Selection Bias  Subjects choose group Recall Bias  Knowledge of presence of disorder alters recall by subjects Sampling Bias  Subjects are not representative Late look bias  Information gathered at an inappropriate time
  13. 13.  Blind studies Placebo responses Crossover studies Randomization
  14. 14.  Phase 1: evaluates safety with increasing dose Phase 2: early work on possible benefits/ efficacy Phase 3: Formal evaluation (RCT) Phase 4: Safety reporting in use
  15. 15. Disease Table 1 + -Exposure + A B - C D RR = [ a / a+b] ________ [c / c + d]
  16. 16.  “PROSCAR more than halves the risk of developing acute urinary retention and the need for surgery”’ Urologists had different points of view regarding: “the 48% to 57% relative risk reduction promoted and the 1.9% to 2.4% absolute risk reductions actually observed in the median risk of AUR and surgery, respectively” [PLESS; MTOPS]
  17. 17. Disease Table 1 + - Exposure + A B - C DExperimental event rate (EER) = A / A+BControl event rate (CER) = C /C+DRelative risk = EER /CER
  18. 18. Retention Table 1 + - Finasteride + 42 1471 (2.8%) - 99 1404 (6.6%)RRR = Risk difference = 2.8% = 57% _____________ ____ Baseline difference 6.6%ARR = CER – EER = 6.6 – 2.9 = 3.8
  19. 19. Retention Table 1 + - Finasteride + 42 1471 (2.8%) - 99 1404 (6.6%)NNT = 1 = 1 = 26 ____________________ ________________ Absolute Risk Reduction 0.038
  20. 20.  Absolute risk of a disease is your risk of developing the disease over a time period. We all have absolute risks of developing various diseases such as heart disease, cancer, stroke, etc. The same absolute risk can be expressed in different ways. For example, say you have a 1 in 10 risk of developing a certain disease in your life. This can also be said to be a 10% risk, or a 0.1 risk - depending if you use percentages or decimals. Relative risk is used to compare the risk in two different groups of people. For example, the groups could be smokers and non-smokers. All sorts of groups are compared to others in medical research to see if belonging to a group increases or decreases your risk of developing certain diseases. For example, research has shown that smokers have a higher risk of developing heart disease compared to (relative to) non-smokers.
  21. 21.  Null (H0)  Hypothesis of no difference  E.g. . There is no association between the disease and the risk factor in the population Alternative (H1)  Hypothesis that there is some difference  E.g.. There is some association between the disease and the risk factor in the population
  22. 22.  Type 1 (α)  Stating that there is an effect or difference when none exists (to mistakenly accept the experimental hypothesis but reject the null hypothesis)  E.g. . You “saw” the difference that did not exist [Convict an innocent man] P value of < 0.5  This indicates there is a less than a 5% chance that the data will show something that is not really there
  23. 23.  Type 2 (β)  Stating that there is NOT an effect or difference when one exists (to fail to reject the null hypothesis when in fact the null hypothesis is false)  E.g. . You “did not see” the difference that does exist [Setting a guilty man free]
  24. 24.  Probability of rejecting the null hypothesis when it is in fact false Power depends on  Total number of the end points experience by the population  Difference in compliance between treatment groups  The power of a test is the probability that a study of a given size would detect as statistically significant a real difference of a given magnitude “If you increase the sample size, you increase the power. There is power in numbers”
  25. 25.  In statistical significance testing, the p-value is the probability of obtaining a test statistic at least as extreme as the one that was actually observed, assuming that the null hypothesis is true A measure of the effect of chance within a study It is not the probability that the result of the study is true or correct
  26. 26.  Normal = Gaussian distribution = Bell Shaped Bimodal Positive skew (Mean > Median > Mode) Negative skew (Mean < Median < Mode)
  27. 27.  It shows the trade-off between sensitivity and specificity (any increase in sensitivity will be accompanied by a decrease in specificity) The closer the curve follows the left-hand border and then the top border of the ROC space, the more accurate the test The closer the curve comes to the 45-degree diagonal of the ROC space, the less accurate the test The area under the curve is a measure of test accuracy
  28. 28.  The Kaplan–Meier estimator also known as the product limit estimator, is an estimator for estimating the survival function from life-time data The term "survival" is a bit misleading; you can use survival curves to study times required to reach any well-defined endpoint (e.g., re- occlusion of a grafted blood vessel, first metastasis, discharge from the hospital).