Clinical research and methodology: What usage and what hierarchical order for secondary endpoints?

Silvy Laporte; Marine Diviné; Danièle Girault; participants of Giens XXXI, Round Table No. 2

doi:10.1016/j.therap.2016.01.002

Clinical research and methodology: What usage and what hierarchical order for secondary endpoints?

Therapie. 2016 Feb;71(1):27-41. doi: 10.1016/j.therap.2016.01.002. Epub 2016 Feb 3.

[Article in English, French]

Authors

Silvy Laporte¹, Marine Diviné², Danièle Girault³; participants of Giens XXXI, Round Table No. 2

Collaborators

participants of Giens XXXI, Round Table No. 2:
Pierre Boutouyrie⁴, Olivier Chassany⁵, Michel Cucherat⁶, Hervé de Trogoff⁷, Sophie Dubois⁸, Cecile Fouret⁹, Natalie Hoog-Labouret¹⁰, Pascale Jolliet¹¹, Patrick Mismetti⁴, Raphaël Porcher¹², Cécile Rey-Coquais¹³, Eric Vicaut¹⁴

Affiliations

¹ Inserm UMR1059, unité de recherche clinique, innovation, pharmacologie, université Jean-Monnet, CHU Saint-Etienne, 42055 Saint-Étienne, France. Electronic address: [email protected].
² Laboratoire Amgen, 92650 Boulogne-Billancourt, France.
³ Société Denelia, 92110 Clichy, France.
⁴ Assistance publique-Hôpitaux de Paris, 75908 Paris, France.
⁵ EA 7334 REMES, unité de recherche clinique URC-ECO, université Paris Diderot, AP-HP, 75004 Paris, France.
⁶ UMR CNRS 5558, université Lyon 1, 69008 Lyon, France.
⁷ Astellas Pharma, 92309 Levallois-Perret, France.
⁸ Takeda, 92800 Puteaux, France.
⁹ Medtronic, 92100 Boulogne-Billancourt, France.
¹⁰ Pôle recherche et innovation, INCA, 92100 Boulogne-Billancourt, France.
¹¹ Faculté de médecine, université de Nantes, 44035 Nantes, France.
¹² Centre de recherche épidémiologie et statistique, Sorbonne Paris Cité (CRESS-Inserm UMR1153), AP-HP, 75010 Paris, France.
¹³ Laboratoires Pfizer, 75668 Paris, France.
¹⁴ Hôpital Saint-Louis Lariboisière, AP-HP, 75010 Paris, France.

PMID: 27080628
DOI: 10.1016/j.therap.2016.01.002

Abstract

In a randomised clinical trial, when the result of the primary endpoint shows a significant benefit, the secondary endpoints are scrutinised to identify additional effects of the treatment. However, this approach entails a risk of concluding that there is a benefit for one of these endpoints when such benefit does not exist (inflation of type I error risk). There are mainly two methods used to control the risk of drawing erroneous conclusions for secondary endpoints. The first method consists of distributing the risk over several co-primary endpoints, so as to maintain an overall risk of 5%. The second is the hierarchical test procedure, which consists of first establishing a hierarchy of the endpoints, then evaluating each endpoint in succession according to this hierarchy while the endpoints continue to show statistical significance. This simple method makes it possible to show the additional advantages of treatments and to identify the factors that differentiate them.

Keywords: Endpoint; Hierarchical test procedure; Inflation of type I error; Secondary endpoints.

Publication types

Review

MeSH terms

Biomedical Research
Endpoint Determination*
Humans
Research Design*
Sample Size