Researchers Believe Data Mining is the Wave of the Future in Virtual Research
The days of lengthy and expensive clinical trials may be coming to an end, as researchers now believe that virtual research which includes data mining can provide more detailed results in less time, even while spending less money.
Testing a new or existing drug’s efficacy and potential dangers is extremely important. This is particularly true in the case of drugs that are already approved for use because while they may be okay to use on their own, research may prove that the drugs are fatal when used in combination with other drugs. A good example of this is in the cases of the antidepressant drugs Paxil and Pravachol. While Paxil was first approved for use in 1992, and Pravachol was approved for use in 1996 for lowering cholesterol, it was proven that on their own, both drugs work and they were safe. However, researchers from Stanford University eventually discovered that when the drugs are taken together, patients suffered from increased sugar levels. This condition was particularly dangerous for diabetics.
Generally when researchers run clinical tests the process is a lengthy and arduous one. They have to gather the test patients and group them according to various factors including age, sex, weight and medical history. Once the testing is completed, the patients are split into different classes, such as those who reacted well to the drug, those that had a neutral reaction and those that had a bad reaction.
The information collected in the trials is then used to predict how new patients will respond to the drug by following patterns. This method takes up a great deal of time and money. Using data mining to collect data rather than clinical trials is a simpler way to get the information those researchers need when looking for the same patterns in patients. Russ Altman, director of Stanford's Biomedical Informatics Training Program, whose group published the Paxil/Pravachol result in the journal Clinical Pharmacology and Therapeutics, says "you're not constrained by the need to actually get patients lined up in a clinical trial that would be incredibly expensive. We had most of this paper done probably in a month."
Data mining is a research technique where researchers gather information from patient databases (based on the criteria of their research) and search for patterns to answer their questions. These databases are usually drawn from hospitals and medical records. So if a researcher wants to know how Paxil affects the elderly, they will use medical records and hospital files of senior patients using Paxil to gather up their information. Data mining is proving itself to be a significantly faster and cheaper route to clinical trials, and may wind up being the wave of the future when it comes to virtual research.