Mike Anderson at Harvard's Social Science Statistics Blog looks at the recent change in recommendations for women with regard to breast cancer screening from the perspective of Bayes' Theorem. This calculation was particularly interesting:
So if you're a woman in your 40s, and you get a positive result from your latest mammogram, you'll still only have an 11.9% probability of having breast cancer -- basically the same as a woman's lifetime risk of 12%.
Of course none of this takes into account the myriad other factors (cost of a false positive or negative, improved understanding of risk factors, etc.) but it does shed some light on the controversial recommendation change.
Update Nov 20: As noted here in the comments, the linked post has been removed, possibly due to an error in its calculations.
Update Dec 3: The post has since been replaced.
Social Science Statistics Blog: breast cancer, mammograms, rare diseases, and bayes rule (via @drewconway)
I noticed what looked like an error in the original blog post (briefly, the author seemed to have taken the true.positive.rate to be 1-false.positive.rate and plugged into the bayes rule) and posted a comment pointing this out. This morning, the original post has disappeared! Weird.
BTW, I enjoy reading your posts a great deal. Thanks!
Posted by: Rama Ramakrishnan | November 20, 2009 at 07:08
Breast cancer is one of the most studied and studied forms of cancer. The oldest known descriptions of breast cancer (although the term "cancer" was not yet known and is not used) was found in Egypt and dates from about 1600 year BC. So-called "Edwin Smith Papyrus describes 8 cases of tumors or ulcers of the breast, which were treated with cauterization by fire. The text reads: "The disease does not care, it always leads to death." At least one described in the Papyrus of eight cases of breast cancer arose from men.
Posted by: generic viagra | March 09, 2010 at 09:29
Here's a fascinating view on what is cancer and what causes it...
What is Cancer
The researcher claims that cancer is not only curable, but also a natural response of the cells mutating for surviving in an unnatural environment. Pretty interesting idea. I wonder if there is any solid research backing this up.
Posted by: Zan | March 06, 2011 at 23:26
This is pure mathmatics. We need a clearer insight concerning breast cancer and women risk factor!
thanks for the post anyway!
Posted by: Jennette Green | March 11, 2011 at 04:29