Statistics in Practice Part I - Tagged PDF

Statistics in Practice Salma Ayis, Reader in Medical Statistics [email protected] School of Life Course and Population Sciences Statisticians work with clinicians in research to explore and test hypothesis and to validate assumptions using actual data Examples of Clini...

Statistics in Practice Salma Ayis, Reader in Medical Statistics [email protected] School of Life Course and Population Sciences Statisticians work with clinicians in research to explore and test hypothesis and to validate assumptions using actual data Examples of Clinical Trials run by King's Researchers Randomized Trial of Peanut Consumption in Infants at Risk for Peanut Allergy Randomization Blinding Intention to treat analysis Per protocol analysis  Randomization Random allocation into an experimental group and a control group Avoids selection bias Successful randomisation makes different groups have similar characteristics at baseline  Blinding A blind experiment is an experiment in which information about the test is masked (kept) from the participants Aim: to reduce or eliminate bias Bias may be intentional or unconscious  Types of Blinding Type Description Unblinded / All parties are aware of the treatment allocation open label Single blind / Participants are unaware of the treatment they receive single-masked Double blind / Participants and clinicians / data collectors are unaware of the treatment double-masked participants receive Triple blind Participants, clinicians / data collectors and data analysts are all unaware of the treatment participants receive Un-blinding: the disclosure to participants or study team of which treatment participants received during the trial  Intention to treat (ITT) analysis ITT analysis includes every subject who is randomized according to randomized treatment assignment Ignores noncompliance, protocol deviations, withdrawal, and anything that happens after randomization ITT analysis maintains prognostic balance generated by randomisation Estimate of treatment effect is generally conservative. A better application of the ITT approach is possible if complete outcome data are available for all randomized subjects.  Per protocol analysis A subset of the ITT population who completed the study without any major protocol violations  Randomized Trial of Peanut Consumption in Infants at Risk for Peanut Allergy Learning Early About Peanut” (LEAP) Published in the New England Journal of Medicine. The consumption of a peanut-containing snack by infants who are at high- risk for developing peanut allergy prevents the subsequent development of allergy. The LEAP study, led by Professor Gideon Lack at Kings College London, is the first randomized trial to prevent food allergy in a large cohort of high-risk infants Conclusions The early introduction of peanuts significantly decreased the frequency of the development of peanut allergy among children at high risk for this allergy and modulated immune responses to peanuts  Summary and Conclusions NEJM February 2015 http://www.nejm.org/doi/full/10.1056/NEJMoa1414850 Further research: Explore the introduction of more types of allergenic food Further research: Explore the introduction of more types of allergenic food  the EAT Study Randomized Trial of Introduction of Allergenic Foods in Breast-Fed Infants Michael R. Perkin, Ph.D., Kirsty Logan, Ph.D., Anna Tseng, R.D., Bunmi Raji, R.D., Salma Ayis, Ph.D., Janet Peacock, Ph.D., Helen Brough, Ph.D., Tom Marrs, B.M., B.S., Suzana Radulovic, M.D., Joanna Craven, M.P.H., Carsten Flohr, Ph.D., and Gideon Lack, M.B., B.Ch., for the EAT Study Team*  Randomisation of children to trial arms o We recruited, from the general population, 1303 exclusively breast-fed infants who were 3 months of age. o Children were randomly assigned to:  The early introduction of six allergenic foods (peanut, cooked egg, cow’s milk, sesame, whitefish, and wheat; early-introduction group) or  The current practice recommended in the United Kingdom of exclusive breast-feeding to approximately 6 months of age (standard introduction group). o The primary outcome was food allergy to one or more of the six foods between 1 year and 3 years of age. Skin prick testing This involves a small amount of the allergen being placed onto the skin and then pricking the skin (it does not draw blood) If the child is allergic to any of the allergens being tested a small bump (hive) will develop within 5-15 minutes. This disappears after about 30 minutes.  Skin prick testing Infants in the early-introduction group who had a wheal of any size on skin-prick testing at baseline underwent an open-label incremental food challenge totalling 2 g of protein of that food. Families of infants in the early-introduction group who had negative results on skin prick testing or who had positive results on skin-prick testing but negative results on the food challenge were asked to continue feeding their infants 2 g of the allergen protein twice weekly Families of infants who had a positive result on the food challenge at baseline were instructed to avoid giving the infants that food but to continue feeding the infants the other foods The infants in the standard-introduction group did not undergo skin-prick testing at baseline because the results could have influenced the timing of the introduction of allergenic foods. Blood test The blood sample is used to help understand why some children develop food allergies and others do not. At the 3 month visit and at 1 year’s visits Blood would be taken by a dedicated specialist in taking blood, or a doctor  Children Included in the Analysis For the primary outcome: 595 of 651 enrolled participants (91.4%) in the standard-introduction group 567 of 652 (87.0%) in the early introduction group were included in the intention to-treat analysis (ITT)  Follow up data on children's food consumption All the families completed an online questionnaire each month to 1 year of age, and then every 3 months until the child reached 3 years of age. This questionnaire recorded the frequency of consumption of allergenic foods in the two groups. In addition, the parents of the participants in the early-introduction group kept a weekly diary to record the quantity of the six foods consumed  Statistical Methods and Power of the Study The ITT analysis for the primary outcome included all the participants who had data that could be evaluated. Proportion of participants in the two groups who had food allergy to one or more of the early-introduction foods, were compared_ chi-square test / Fisher exact for smaller samples. ITT: every subject would be analysed according to randomized treatment assignment. The trial had 80% power at the 5% significance level to detect a halving of the prevalence of food allergy, from 8% in the standard-introduction group to 4% in the early-introduction group.  Results In the ITT analysis, food allergy to one or more of the six intervention foods developed in 7.1% of the participants in the standard-introduction group and in 5.6% of those in the early-introduction group (P = 0.32). In the per-protocol analysis, the prevalence of any food allergy was significantly lower in the early-introduction group than in the standard introduction group (2.4% vs. 7.3%, P = 0.01). The prevalence of peanut allergy was (0% vs. 2.5%, P = 0.003) The prevalence of egg allergy (1.4% vs. 5.5%, P = 0.009); There were no significant effects with respect to milk, sesame, fish, or wheat. The consumption of 2 g per weekof peanut or egg-white protein was associated with a significantly lower prevalence of these respective allergies than was less consumption. The early introduction of all six foods was not easily achieved but was safe.  SUMMARY AND CONCLUSIONS -NEJM The trial did not show the efficacy of early introduction of allergenic foods in an intention-to-treat analysis. The per Protocol findings highlights the importance of the size of portion and the number foods in compliance with the planned introduction. The study raised a question of whether the prevention of food allergy by means of early introduction of multiple allergenic foods was dose-dependent.