Percentage of loss, absolute kilograms, and the sleight of hand between them
A substudy powered to describe a mean is not a substudy powered to detect a clinically meaningful individual change.
Clinical Trials Dispatch
SURPASS-4 extension data: what happens after the trial stops
A design note rather than a result: what the comparator was, and what that permits you to conclude.
SURPASS-4 met its primary endpoint and did not meet one of its hierarchically tested secondary endpoints, a result which appears in the paper and in almost none of the reporting. Under a pre-specified testing hierarchy a failure at that point formally precludes claims on the endpoints below it, whatever the nominal p-values show.
The endpoint hierarchy was pre-specified in the statistical analysis plan and is reproduced in the supplementary appendix. Readers relying on the abstract will not see it. The Journal reads the analysis plan before the paper for exactly this reason.
Cross-trial comparison is the commonest error in coverage of this field. Populations differ in baseline weight, diabetes status and lifestyle-intervention intensity; durations differ; estimands differ. Two programmes reporting 15% and 20% may or may not reflect a difference between the drugs, and only a head-to-head trial settles it.
"The mean is not the interesting part and it never has been," said Dr Éliane Casgrain, health economist, Université de Montréal. "Show me the decile plot. That is where the clinical question lives."
Our clinical-trials department is reading the supplementary appendix and will publish a design note if the analysis plan differs materially from the published methods.
Note
Trial results describe populations, not individuals. Nothing in this item is clinical advice.
Related coverage
STEP 2 was built to answer the stopping question, and it did
A withdrawal trial answers a narrower question than it appears to. This piece states which question.
SURMOUNT-1 extension data: what happens after the trial stops
A design note rather than a result: what the comparator was, and what that permits you to conclude.
The slide that was not in the abstract
Reported from the sessions, and from the two hours afterwards.
SURPASS-2 extension data: what happens after the trial stops
A design note rather than a result: what the comparator was, and what that permits you to conclude.
Not everybody regains at the same rate, and nobody knows why
The variance around the mean regain trajectory is large and unexplained, exactly as it is for the weight loss.