Patient data shows that common prostate cancer treatment likely doubles risk of dementia

Well shit, I'm likely to get prostate cancer since my Dad had it, although he was treated with the radioactive seeds. Another medical item I will need to keep up-to-date on.
http://scopeblog.stanford.edu/2016/10/13/patient-data-shows-that-common-prostate-cancer-treatment-likely-doubles-risk-of-dementia/
Improved methods for analyzing patient medical records support the suspicion that a common cancer treatment may increase the risk of dementia.
Such methods may soon make similar studies almost as easy as a Google search, said Nigam Shah, MBBS, PhD, an associate professor of biomedical informatics research and senior author of a study that appears in JAMA Oncology today. Kevin Nead, MD, a resident at the University of Pennsylvania who recently received his medical degree from Stanford, was first author.
Shah and Nead’s study, which was completed in just a few weeks, looked at the effect of a common treatment for prostate cancer on the risk of dementia later in life. The results suggested that prostate cancer patients treated with androgen deprivation therapy have about double the risk of dementia as those with prostate cancer not treated with ADT.
ADT is a constellation of different treatments that depress testosterone levels. As I explained in our news release:

The team looked at records from nearly 10,000 patients with prostate cancer, in the Stanford School of Medicine’s research data warehouse, of whom 1,829 received androgen deprivation therapy. Among prostate patients treated with ADT, 7.9 percent developed dementia within five years, compared with 3.5 percent of those not treated with ADT.

The Shah lab’s work to develop analytic techniques for exploring patient data is expected to help drive precision health at Stanford. The methods will allow researchers and health-care providers to sift through the mountains of information available from patient medical records to find clues about the trajectory of a disease, the outcomes of different treatments or combinations of treatments, and even health provider behavior.
Shah said his team is getting faster. While the current study took a few weeks to complete, another they are working on took only a few days.
Previously: Push-button personalized treatment guidance for patients not covered by clinical-trial results; A new view of patient data: Using electronic medical records to guide treatment