According to an article in Technology Review, Doctor Database: New search technology from IBM could help patients and doctors locate life-saving treatments, the International Federation of Pharmaceutical Manufacturers and Associations (IFPMA) and IBM announced the release of the IFPMA Clinical Trials Portal. The IFPMA and IBM hope it will "enable doctors and patients to find potentially useful trials and to make more informed medical decisions based on past trials." The portal is designed to cut through medical jargon, correct misspelled search terms, and search for results in five different languages (German, French, Japanese, and Spanish).

The portal sifts through different types of data (PDF, text, and HTML files) from different sources (databases and websites), finds the information buried within documents that best match the search terms. According to Marc Andrews, director of strategy and business development for content discovery at IBM, instead of using Google like technology (sorting through indexed web pages and ranking by title, key words, and number of hyperlinks) the portal searches the body of the text, pulls in specific information and assembles it into concepts. "Instead of indexing words," Andrews says, "we're indexing concepts that are referenced in the documents."

Krafty's thoughts:
I can see the benefit of such a database but I am concerned.

Sources?
There is no mention what specific clinical trial websites, databases, etc. the portal is mining. How do we know they aren't missing a place, or whether it is truly global in nature? They allow people to search for things in five other languages, but are they tracking or finding clinical trials in those countries as well? Or is it just finding clinical trials in the United States or those funded by American drug companies?

Searching?
Currently users can search for information from two areas; current ongoing trials and research trial results. While it seems logical to me, I am not sure if it is logical to a patient. This is just my opinion, but I would think a patient would want to do one search and the results have icons or words detailing whether it is a current trial or results of a trial. I think patients could easily be lulled into looking for current trials to find information and once they found something not look any further in trial results. Perhaps the drug they are interested in had poor results or caused serious injuries in previous trials. Will patients take the time to look at both searches when they think they have found the answer in one of them?

Content?
Specifically I am skeptical of the content (or lack of) in the clinical trial results search. The Technology Review said the transparency between clinical trials and results is a "topic that's been making headlines for a number of years, and recently in the clinical trial of PolyHeme, a blood substitute developed by Northfield Laboratories, in which ten patients suffered heart attacks and two died after receiving the treatment. The trial was stopped early and the results weren't made public, the Wall Street Journal reported in February."

(article on Polyheme in the Wall Street Journal Feb 22, 2006. p. A.1 Red Flags: Amid Alarm Bells, A Blood Substitute Keeps Pumping; Ten in Trial Have Heart Attacks, But Data Aren't Published; FDA Allows a New Study; Doctors' Pleas Are Ignored)

So I tried to search for trial results with Polyheme. No results were found. However, if you search ongoing trials you will find one clinical trial. To say that the IFPMA Clinical Trials Portal will display results of clinical trials is slightly misleading. It should say that it will display publicly released results of clinical trials.

The portal is worth looking in if you are looking for current clinical trials and you don't want to search multiple sites. But like with every product you need to know the limitations.