The basic notion here is that averages hide individual differences and Haywood and Kent emphasize the need for risk stratification to be included in randomized clinical trials.
Earlier on I had been able to access a full text version of a classic article on this same general topic but now my attempts to link to that have been met with the realization that now a subscription is required. This is a real shame as it is an article every med student and physician should read and digest.
The Journal is
Milbank Quarterly ( 82(4),661-687, Dec. 2004 and the article is " Evidence-based Medicine;Heterogeneity of treatment effects and the trouble with averages" by Kravitz,RL,Duan N, and Braslow J.
Here is the abstract ( apparently all you can get without a paid subscription now) with my addition of the highlighting of certain phrases.
"Evidence-based medicine is the application of scientific evidence to clinical practice. This article discusses the difficulties of applying global evidence ("average effects" measured as population means) to local problems (individual patients or groups who might depart from the population average). It argues that the benefit or harm of most treatments in clinical trials can be misleading and fail to reveal the potentially complex mixture of substantial benefits for some, little benefit for many, and harm for a few. Heterogeneity of treatment effects reflects patient diversity in risk of disease, responsiveness to treatment, vulnerability to adverse effects, and utility for different outcomes. Recognizing these factors, researchers can design studies that better characterize who will benefit from medical treatments, and clinicians and policymakers can make better use of the results."