Time series: what conclusions can we draw from ?

8 Nov

Here below is a link toward a time series published by the French Agency for pharmaceutical safety (aka ANSM). Although the method is well described and doesn’t raise any concern, nevertheless the interpretation that is done from the results in the discussion is subjected to caution.

My expression of concern is motivated by the fact that the authors of the study link the lowering of the incidence of pulmonary embolism to the lowering of sales of third and fourth generations of contraceptive pills.

Indeed a cofactor can explain the concomitant lowering of both time series:
the large warning campaign in the medias with messages about a) the risks attached to those third and fourth generations of contraceptive pills AND b) the risks of pulmonary embolism (ie blood clots in the lung) every woman faces under contraceptive pills, no matter the generation of the contraceptive pill.

Thus the practitioners could have been more attentive to the risk for all their patients and stopped the contraceptive pill, even for the first and second generation of pill, in case of any doubt (eg a phlebitis of the leg or a tobacco addiction).

One thing is for sure: the results of this study show that the campaign in the media had an impact in term of public health, but no causality can be formally drawn between the lowering of the sales of the third and fourth generations of contraceptive pills and the lowering of pulmonary embolism from the results of this study.

The study:

Etude de l’impact de la modification récente des méthodes de contraception sur la survenue d’embolies pulmonaires chez les femmes de 15 à 49 ans (07/11/2014) application/pdf (316 ko)

http://ansm.sante.fr/content/download/69461/886199/version/1/file/Etude-COC-Embolie-pulmonaire2014.pdf

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: