David has over 40 years of industry experience in software development and information technology and a bachelor of computer science
Bringing Order to Chaos
We collect information on everything these days. We're good at that. We count the number of people that use public transit. We count the number of items you purchase at the grocery store. And your family Doctor even keeps records of your regular visits, and your blood work. But wouldn't it be nice if we could take that a step further, and derive some useful meaning from the information? Certainly, and that's where data mining can help.
What is Data Mining?
Data mining is a discovery process. It examines, organizes, and recognizes patterns in, large information sets. It involves a number of technical disciplines including general computer science, artificial intelligence, machine learning, database technology, and statistics. Its ultimate goal is to derive conclusions from seemingly random sets of data. Let's look at a simple example.
Say we have the following set of numbers: 4, 2, 0, 8, 16. They look random, but are they? Let's organize (sort) them from the smallest to largest. This gives us 0, 2, 4, 8, 16. Now, let's look for a pattern. Careful examination reveals that these numbers are a sequence.
To be specific, this pattern follows the integer powers of 2. 2 to the power of 0 is 0, 2 to the power of 1 is 2, 2 to the power of 2 is 4, 2 to the power of 3 is 8, and 2 to the power of 4 is 16. So, the conclusion that can be drawn is that this sequence is the integer powers of 2. We can even take that a step further and predict that the next number in the sequence would be 32 (2 to the power of 5). Granted, this example is trivial, but you get the idea.
What Are the Benefits of Data Mining?
As we saw in the example, there are a few benefits to data mining. First, it can bring order to something that is initially chaotic (through sorting). Second, we can determine a pattern which, in this case, is our initial conclusion (a sequence of integer powers). And lastly, we can generate additional conclusions. In the example, we predicted the next number in the sequence (2 to the power of 5 is 32). This can be very powerful, and we'll see how in the next section.
How Would This Benefit Healthcare?
If we examined all of the blood work for people in Canada and the US (a little over 350 million people), broken down by age and gender, would we not be able to recognize patterns? Certainly! Further, could we determine correlations between those patterns, and the issues these people have over the courses of their lives? Definitely! Or what if we examined all of the vital signs (blood pressure, pulse, respiration) for these same people, grouped them by age and gender, then determined any patterns. Would we be able to correlate this with occurrences with things like heart decease? Absolutely!
In the end, data mining would not only give us the ability to recognize basic relationships between observed information and outcomes, it would give us the ability to predict them. Powerful indeed!
To recap, data mining is the process of discovering new information from existing information. It does this by examining, organizing and recognizing patterns in the initial information. It involves a number of areas in computer science (general computer science, artificial intelligence, machine learning, databases), and statistics. Its ultimate goal is prediction. And it is particularly useful in Healthcare because it can help us recognize, and predict, health related issues.
To unlock this lesson you must be a Study.com Member.
Create your account
Register to view this lesson
Unlock Your Education
See for yourself why 30 million people use Study.com
Become a Study.com member and start learning now.Become a Member
Already a member? Log InBack