SearchDictionaryMobileLogin Register FREE

FAQ

  1. My doctor has recommended a drug whose performance is low on the CureHunter Effectiveness scale or one of the charts in my report, does that mean he or she is making a mistake?
  2. Can CureHunter make mistakes in evaluating clinical effectiveness and "optimal medications"?
  3. How do scientists validate CureHunter recommendations?
  4. Why does CureHunter report some data from animal studies?
  5. Why does CureHunter report some drugs that are very old and others that my physician can't prescribe?
  6. How is CureHunter different than Google or the other Medical Information sites on the web?
  7. Does CureHunter use "relevance ranking" to find good information?
  8. How do search engines differ from medical data mining systems?
  9. How is CureHunter used in Biomedical Research and New Drug Discovery?
This section provides answers to frequently asked questions about the science behind CureHunter.

My doctor has recommended a drug whose performance is low on the CureHunter Effectiveness scale or one of the charts in my report, does that mean he or she is making a mistake?

Absolutely not. CureHunter is not a doctor. It is a robot. A smart robot, but only a machine that knows nothing about you as a specific patient, and nothing about your specific health history, diagnosis, and clinical test results. It cannot give medical advice nor prescribe medication. CureHunter can only provide supporting information for review and consideration by your doctor.

Can CureHunter make mistakes in evaluating clinical effectiveness and "optimal medications"?

"To err is human" and also characteristic of machines built by humans. CureHunter can make mistakes:
  1. Its reader module may misinterpret some of the information in the scientific article and create a "false positive" or case where it believes it has captured a successful outcome but really hasn't.
  2. It may produce some "false negatives" as well: It read an article but did not "see" the positive outcome in the information and missed capturing a good data point.
  3. Other forms of "error" may occur from simply insufficient data to create a meaningful median, average or other statistical trend line from the available number of studies. For this reason, many users may want to default to only drugs where a fair number of large clinical trials of the target drug are reported. This is not a bad strategy, but often an inadequate one. As many as 30% of patients may not be helped at all by first and second line default medications as determined by large clinical trials.

How do scientists validate CureHunter recommendations?

There are several primary ways technical professionals validate CureHunter clinical decision support recommendations and challenge them when necessary:
  1. Compare results reported to those in the major medical textbooks.
  2. Consult with specialists to see if they agree with the findings for drugs in their areas of specialization.
  3. Use a Turing Test with qualified physicians recommending their first and second line drugs to treat a set of test diseases. Then compare the physician results with the CureHunter results for the same diseases.
  4. Carry out a clinical trial in their medical organization where a group of physicians is prescribing with a CureHunter evidence check and a control group is prescribing without a supporting CureHunter consult and they determine if prescribing behavior is different in either case.

Why does CureHunter report some data from animal studies?

The current release of CureHunter provides data for both Clinical and Biomedical research. Animal studies often provide leading indicators of what new drugs will be available in the future or critical insights into the behavior of important biologically active molecules influencing a drug's primary mechanism of action.

Why does CureHunter report some drugs that are very old and others that my physician can't prescribe?

Some old drugs are safer and far less expensive than new ones...and frequently still work as well as newer medications. You can see the relative age of a drug from when it first appeared in the scientific literature by scanning CureHunter's history charts.

How is CureHunter different than Google or the other Medical Information sites on the web?

CureHunter is unlike Google and ordinary search engines used in general commerce and health information retrieval in several important ways--including its basic theory of operation. CureHunter is built on the model of scientific instruments. The machine must control samples and sample preparation. It must produce testable results consistently and be subject to test by other methods of analysis outside itself to provide 3rd party validation of its conclusions and returns. It must also have extremely large and carefully controlled technical medical dictionaries that are generally not found in common search engines that fail to recognize many words in the scientific research and thus deliver incorrect results.

Does CureHunter use "relevance ranking" to find good information?

CureHunter does not use the concept of "relevance ranking" at all. All its data extractions (search results) must be precisely relevant to start with. A very advanced natural language processing module has the task of reading the literature the same way a human scientist would. There are no "top 10 or 20" supposedly important articles followed by millions of "hits found" of totally irrelevant or weakly related information.

How do search engines differ from medical data mining systems?

Search engines point to information in distributed articles of all kinds and tell you to then click one article at a time, go read the article yourself and see if the article has any information you believe useful. They also ask you to write 1 to many hundreds of different queries with different spellings of words and names for various related ideas. Often the great majority of information returned has no meaningful value to you at all: "42 million hits found." CureHunter automatically extracts the key data (mines it), reads it, analyzes it, and draws scientific conclusions for presentation to you and your doctor.

How is CureHunter used in Biomedical Research and New Drug Discovery?

In professional online versions (you or your institution must subscribe), CureHunter data is automatically exported to powerful scientific analysis software including statistical analysis from companies such as SAS Institute and Salford and many original university-built solutions using Steiner Trees, Bayesian Network, and general Graph Theory programs that map cellular communication pathways, protein-protein interactions, genetic links, pathogenesis chains and metabolic pathways. By correlating and analyzing vast volumes of information human scientists would not live long enough to read, it can often bring new insights into disease mechanisms and possible new cures forward for review by the specialist scientific team.