| The above title may sound funny but with the | | | | eliminate some of the need for traditional, |
| advent of microarray technology it is entirely possible | | | | doctor-enabled pattern recognition. I do not think, |
| for your doctor to ask you a question like this. | | | | however, that the pattern-recognition capacity of |
| Namely, any array-based diagnostic test that | | | | microarrays is anywhere near to do so because (1) |
| determines a multi-component disease signature is | | | | technical standards for diagnostic microarrays do not |
| inherently generating a statistical statement. For | | | | exist, (2) the mathematics of pattern-recognition |
| example: | | | | makes sense to statisticians but not doctors and |
| The test results demonstrate with 90% confidence | | | | patients, and most importantly, (3) the medical |
| that your chances to have Disease X are 75% as | | | | community does not have surrogate biomarkers, |
| detected by the marker-pattern, which is up to 85% | | | | except for infectious disease. In short, in addition to |
| sensitive and specific to Disease X. | | | | great potential, the microarray technology brings |
| The above statement may sound unintelligible and | | | | unique challenges for scientists, IVD industry, medical |
| make no medical sense but if you compare the | | | | community, and the regulatory institutions. Some of |
| process behind this hypothetical machine-generated | | | | these challenges are formulated in DIAGNOSTIC |
| statement to traditional clinical diagnostics, then you | | | | NUCLEIC ACID MICROARRAYS [MM12A, 2006; |
| realize the similarity. Namely, both are actually pattern | | | | Clinical and Laboratory Standards Institute (CLSI)]. |
| recognition. Traditionally, diagnostics has been enabled | | | | And I would like to point here to my favored one: |
| by doctors' experience so that the more experienced | | | | QUALITY MANAGEMENT OF THE PRODUCTION |
| the doctor, the better his of her ability to recognize | | | | AND PERFORMANCE OF DIAGNOSTIC |
| symptoms and synthesize these symptoms into a | | | | MICROARRAYS. |
| disease-pattern, a.k.a. as DIAGNOSIS. Except for | | | | Imagine the amount of quality control and quality |
| simple cases, doctors do pattern-recognition routinely. | | | | assurance (QC/QA) you need for a 10-element array |
| For example, you go to your doctor with complaints | | | | as opposed to a traditional ELISA test that |
| including chronic fatigue, occasional fever, head-ache, | | | | determines only a single marker. Remember that one |
| shortness of breath, and loss of appetite. Your | | | | has to be able to QC/QA all of the array elements. |
| doctor listens to you, looks at you, and analyzes | | | | The best way do so is to design a statistical QC/QA |
| your chest X-rays, blood-test etc. Depending on | | | | methodology, and cut back on the number of array |
| what your doctor finds, you might either have some | | | | elements as much as possible. In summary, despite |
| pulmonary ailment or no detectable disease at all. | | | | great promise, diagnostic arrays will have to |
| How do doctors come up with these diagnoses? | | | | overcome formidable technical challenges. And before |
| Very simply, they analyze patterns, which can greatly | | | | they enter routine clinical practice, the diagnostic |
| overlap from disease to disease but also contain | | | | arrays that produce multi-component diagnostic |
| specific components that determine the diagnosis and | | | | signatures will have to prove that they make clinical |
| therapy. | | | | diagnostics more accurate and cost-effective. Unless |
| At some point in the future, the era of diagnostic | | | | they become capable of detecting surrogate |
| microarrays will arrive, and the clinical pattern | | | | biomarkers, which for most diseases are yet to be |
| recognition is enabled by tiny chips, which quantify | | | | discovered, or provide useful information as to the |
| molecular disease markers instead of talking to you, | | | | best therapy for a patient, we will only be seeing |
| looking at you, listening to you, and analyzing your | | | | experimental tests along with statistical diagnostics |
| X-rays | | | | (see above). So, would you like to be statistically |
| Thus, the future diagnostic microarrays will potentially | | | | diagnosed? |