Randomisation

brief description about different types of randomisation

1. RANDOMISATION IN CLINICAL TRIALS Sekhar babu. B 3 rd year post graduate Dept. of pharmacology

2. OVERVIEW Introduction What is Randomisation Need of Randomisation C riteria of Randomisation Methods of Randomisation Bias and types

3. INTRODUCTION Clinical trials are research studies that test how well new medical approaches work in people Randomisation is a process by which allocation of subjects to treatment groups is done by chance, without the stability to predict who is in what group

4. RANDOMISATION A method based on chance alone by which study participants are assigned to treatment group Randomisation minimises the differences among groups by equally distributing with particular characteristics among all trial arms. The researchers donot know which treatment is better

5. NEED OF RANDOMISATION Primary: To prevent bias in allocating subjects to treatment groups Secondary: To achieve comparability between the groups

6. CRITERIA FOR RANDOMISATION Unpredictability : Each participant has the same chance of receiving any of the interventions Allocation is carried out using a chance mechanism so that neither the participant nor the investigator will know in advance which will be assigned Balance: Treatment groups are of a similar size, groups are alike in all important aspects and only differ in the intervention each group receives

7. Simplicity: Easy for investigator to implement

8. SIMPLE RANDOMISATION Simple and easy to implement in clinical research Based on single sequence of random assignment Flipping a coin, computer generated sequence Two treatment groups (control versus treatment), side of a coin ( heads – control, trials – treatment ) determine the assignment of each group

9. Systemic randomisation Used when complete list of population from which sample is to be drawn is available When population is large, discrete, scattered and homogenous Choose a sample by taking kth patients K is sample interval, k= total population/desirable sample size One random number is selected, less than or equal to K Every kth patient after this random number is taken as sample

10. Advantages: Simple and easy to implement Time and labour is relatively small If population is large, homogenous this method give accurate result Disadvantage: Complete list of population with numbering is available

11. RANDOM ALLOCATION Procedure in which identified sample participants are randomly assigned to a treatment and each participant has same probability of being assigned to any particular treatment If the design is based on N participants and n1 are to be assigned to Treatment 1 then all the possible samples of size n1 have the same probability of being assigned to Treatment 1

12. BLOCK RANDOMISATION Commonly used in the two treatment situation where sample sizes for the two treatments are to be equal or approximately equal The process involves recruiting participants in short blocks and ensuring that half of the participants within each block are allocated to treatment A and other half to treatment B

13. Next step is to select randomly amongst these six different blocks for each group of four participants that are recruited Random selection can be done using a list of numbers generated using statistical software As there are only 6 different blocks 525164646325633 Blocks are selected according to above sequence

14. STRATIFICATION A stratification factor is a categorical covariate which divides the patient population according to levels Sex: 2 levels – male/female Age : <40, 40-59, >59 Recruitment centers Any other known prognostic factor

15. Stratification and randomisation

16. MULTISTAGE RANDOMISATION Procedure carried out at several stages using random sampling technique In cases of large country survey Example : Random number of districts are selected from each states followed by random number of taluka, village, unit, respectively For hookworm survey 10% in the village of a taluka are chosen for stool examination

17. Advantages: Flexibility in sampling 2. Can use division and subdivision of district to decrease labour

18. MULTIPHASE RANDOMISATION Part of sample is taken from the whole sample and part from subsample Example physical examination and Mantoux test done in all cases X-ray done in M antoux positive cases or with clinical sign sputum examination done in X-ray positive cases Number in subsample become smaller and smaller Less cost, less laborious.

19. MINIMISATION Process of adaptive stratified sampling Aim is to minimise the imbalance between the number of patients in each treatment group over number of variables Randomisation method allocates subjects to the treatment groups with maintaining balance in terms of prognostic factors Effective in sample size and with multiple prognostic variables

20. INAPPROPRIATE RANDOMISATION METHODS Assigning patients alternately to treatment group Assigning first half of the population to one group Assignments by methods based on patient characteristics based on date of birth, order of entry into the clinic, day of clinical attendance is not reliably random

21. BIAS Occur if the results observed reflect other factors in addition to effect of the treatment Conscious and subconscious level Occur at conduct of trial, data analysis and interpretation of data

22. PATIENT BIAS Patients knowledge that he is receiving a new treatment may substantially affect the patients subjective assessment There is a subject and disease interaction

23. CARE PROVIDER BIAS Care providers knowledge of which treatment a patient is receiving may affect the way the provider Deals with the patient Treats the patient These differences may give the patient, information about the treatment the patient is receiving, affect the outcome of the study

24. ASSESSOR BIAS The assessors knowledge of which treatment the patient is receiving may affect the way the assessors assess the outcome Would directly affect the validity of the conclusions of the study If the assessment is done while the patient is still receiving treatment, this may provide the patient with information about the treatment being received

25. LABORATORY BIAS Knowledge of which treatment the patient received may affect the way in which the test is run or interpreted, or be retested

26. ANALYSIS AND INTERPRETATION BIAS Knowledge of the treatment group may effect the results of the analysis of the data by Seeking an explanation of an anomalous finding when one is found contrary to the study hypothesis Accepting a positive finding without fully exploring the data

27. Knowledge of the treatment group may affect the decision made by external monitors of a study by Terminating a study for adverse events because they were expecting it Terminating a study for superior of treatment because they were expecting it

28. REFERENCES An overview of randomisation techniques: an unbiased assessment of outcome in clinical research J Hum Reprod Sci. 2011 Jan- April; 4(1): 8-11 Designing a research project: Randomised controlled trials and their principles- J M Kendall Risk and evidence of bias in randomised controlled trials- Alex Eble and Peter boone 2012 Randomisation in clinical trials, Dr Urmila - pune Concept of randomisation and blinding in clinical trials – Suraj P Anand

29. Thank u