<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=1582589251849414&amp;ev=PageView&amp;noscript=1">
bg-blog-header.jpg

Data Mining in Healthcare without Skipping Steps

Paul Boal

From wearable devices and mobile apps, genetic sequencing services, social determinants, and electronic records, the amount of data being collected within the healthcare ecosystem is nothing short of astonishing. In fact, the International Data Corporation reported that 153 exabytes were produced in 2013 and by 2020 an estimated 2,314 exabytes will have been produced. Just to be clear, an exabyte is one billion gigabytes (or 1018 bytes). Any way you slice it, that’s a lot of data.

Tim Berners-Lee, best known as the inventor of the World Wide Web, once said “It’s difficult to imagine the power that you’re going to have when so many different sorts of data are available.” This is a promising statement, but to harness the power of the many different sorts of data, you have to do the work of mining the data to extract knowledge and find actionable insights. This is typically accomplished by identifying patterns, anomalies, or dependencies within a large set of data… but let’s not get ahead of ourselves.

Data Mining in Healthcare but First Things First

Before you put full faith in these insights, you first need to put in place processes that continually assess the level of quality and completeness of your data. This is often called the “preprocessing” stage of data mining in healthcare and it is vitally important. It’s not as glamorous as other stages of the data mining process, but without it you will undoubtedly have missing, redundant, inconsistent or outright erroneous values within the databases your rely on to make critical everyday business decisions. In healthcare, just like any other industry, we want to get the best edge we can, and playing the game without realizing you’re a few ace’s short of a full deck just isn’t going to cut it.

After you have done the proper due-diligence and have an accurate assessment of the data you are using, only then is it wise to explore the powerful benefits of data mining in healthcare. Without those critical first steps, you won’t be able to find the actionable insights that will give you the edge you need to deliver superior care, better experience, and optimized use of resources. So, are you dealing with quality data? Are you aware of its level of completeness? We, at Amitech, take a first principles approach to data and we think you should too. If you have questions about how you can better equip yourself in the shapeshifting healthcare industry building a quality data foundation, simply reach out here.