Biotech Values

[the_busy_ant]

These databases are not standardized. It's always difficult and time consuming to analyze large datasets from different sources.

At some level, you must be right, because it has apparently taken this long and it will take another 6-9 months to "validate" the data.

But this should not be as hard as it appears to be. Most of these databases use standardized preferred terms for adverse reactions (e.g., Cleft Palate) and there are only so many ways you can slice or dice a drug name like Topiramate, so it shouldn't be that time consuming to mine even several disparate claims databases. I would guess that this industry (software for claims database mining) is due for some type of disruption on their business model.