Ken Harvey wrote: > Computer Scientist Sorts Out Confusable Drug Names > > http://www.sciencedaily.com/releases/2006/03/060302180023.htm > ... > Was that Xanex or Xanax? Or maybe Zantac? If you're a health care > professional you'd better know the difference--mistakes can be fatal. > ... > Kondrak co-authored a paper on this topic that was recently published in > the journal Artificial Intelligence in Medicine. Earlier, he gave a > presentation to Health Canada officials, who are interested in following > the FDA's lead in addressing the problem of confusing drug names.
A nice idea. In a paper I co-authored in 2004 on "blindfolded record linkage" (see http://www.biomedcentral.com/1472-6947/4/9 ), we suggested that our blindfolded record linkage method could be used by pharma company A to check whether a candidate name for a new drug was similar to candidate names for new drugs by pharma companies B, C and D, without any of the companies having to reveal to the other parties, nor to anyone else, what those candidate drug names might be: "It could also be used by pharmaceutical companies who wish to determine whether candidate names for new drugs which they have under development are similar to new drug names being considered by their competitors, without having to reveal the actual names. n-grams can also be formed from words (or other tokens), rather than individual letters. Thus, minimum-knowledge n-gram similarity comparisons can be used to compare record-or line-oriented text or data, such as poetry or computer program code, or any other information comprising sequences of tokens. In the case of computer program code, the output of the tokeniser built into the language compiler or interpreter could be used as input to detect potentially plagiarised program code, without either party revealing their intellectual property." Of course, our method only finds like spellings, not sound-alikes. And no drug companies or regulatory agencies (or anyone else) have beaten a path to our door. However, some better, more elegant and more practical methods for achieving the same results have subsequently occurred to us... > A number of linguists and computer scientists are also now using > Kondrak's ALINE for various purposes, and he is pleased his software, > once criticized as being useless, is much in demand, though he does not > charge anyone to use it. > > "If anyone asks for it, I just give it to them," Kondrak said. "I was a > funded researcher, and I look at it as my responsibility to share what > I've learned and what I've done." > > "When you do basic research sometimes you don't know how it might become > of use, but if this software helps to reduce even just 10 per cent of > prescription errors in the U.S. that translates into helping a lot of > people, and it's very satisfying to contribute to that." Yes. Tim C _______________________________________________ Gpcg_talk mailing list [email protected] http://ozdocit.org/cgi-bin/mailman/listinfo/gpcg_talk
