A very basic definition of data mining is the searching through large amounts of computerized data to find useful trends or patterns.  At one point this might have been plotted on a simple Excel sheet or graph, but in the realm of today’s standards, the amount of data and nuances involved far exceed minimal plotting.  Especially in an industry as large and data-rich as healthcare, the discovery of patterns requires a lot more processing power.

Clinical analytics means examining vast amounts of information in order to uncover recurring trends, which in turn produce predictive or future forecast data.  Just as when watching a weather forecast, the computers that make the predictions for five or ten days out take into account the patterns in the highs and lows currently happening, and then find previous models that held similar flows and calculates what should happen.  Though this is quite simplified, this example shows the value of data mining from years of previously stored and analyzed information.

(photo courtesy of photostock/FreeDigitalImages.net)

Being able to predict the future of patients and their healthcare opens the doors to being able to identify and deal with high-risk patients more appropriately, rather than continually admitting them into costly hospital beds.  Also, being able to ascertain the patients with severe or chronic illnesses who might be susceptible to readmissions can be headed off with other preventative measures instead of another hospital stay.  Armed with the ability to distinguish when patients fall into certain patterns, doctors and other health professionals would be able to manage staff, space, resources and the overall costs expended due to effective and efficient planning.

Healthcare and the many different fields of medicine are one of the larger industries creating a majority of data generated each day.  This data is compiled together and shared as part of the information exchange that takes into account demographics, such as age, gender and zip code, along with patient’s needs, and plots out general and diverse patterns, especially within communities or populations.  These patterns are then applied by professionals when treatment is sought in order to categorize the patient into a more personalized course of healing.

Data mining in healthcare doesn’t benefit just one group of people, but works to help everyone that is involved at the many different levels of treatments; doctors and other staff have more information at their fingertips to correctly and quickly diagnose a patient.  The patients may not be subjected to unnecessary testing or periods of unknowing because of the actionable data.  Hospitals can run more efficiently due to the fine-tuned productivity found within the patterns.  Even the prevention of fraud and fraudulent behavior can be identified from previously recognized trends.

(photo courtesy of David Castillo Dominici/FreeDigitalImages.net)

The most unfortunate aspect in all of this is the healthcare industry is playing a game of catch up within the realm of data mining.  Most other businesses and industries have fewer points for which they are trying to model.  The sheer complexity of data that is kept in healthcare has been a hindrance to making or finding the right software to implement.  Additionally, the privacy that needs to be upheld on medical files has slowed the adaptation of data mining technology.  But, persistence and a better working knowledge of restrictions and requirements that needed to be respected, a breakthrough for the healthcare industry.

The basic definition of data mining helps to describe the minimal possibilities for any business that utilizes it.  However, the enormous possibilities available when implemented to its fullest potential, there is almost limitless growth.  This isn’t just within healthcare but for anyone, yet healthcare may be the spheres in which data mining might have the most significant ability.  At one time or another all of us will be a patient, whether for that yearly physical or for something much more dire.  If you are like me, I want all those who are helping me to have as much knowledge available to them, and if that includes previous patterns determined from data collected over many years and patients, I am happy to a beneficiary.  Even if we think we are absolutely unique, there are some features that make us ordinary under the hood (so to speak).

The demand for receiving more at a lower cost is a daily mantra.  That goal doesn’t just affect individuals, but industries as well. The healthcare industry is certainly one that has that aim.  Of course, just saying the words doesn’t make everything fall into place.  Much understanding and work needs to be put into action before change occurs.  This is where healthcare analytics is called upon to head up the transformation.

The data that is generated throughout medical offices, specialists and healthcare professionals is both vast in nature and deeply complex.  Organizing the information is just scratching the surface; the need to discern multifaceted patterns is where the strength of knowledge and action can take place, and where analytics is housed.

However, there are steps that must be taken before analysis is implemented, simply stated: data must be collected, shared, and then analyzed.  At present, many offices are collecting data electronically known as the electronic health records (EHR).  The data sharing is happening thanks to the health information exchange (HIE).

Because these terms may be new to you, let’s go into a little more in depth.  An EHR is a patient’s file that contains medical history, but isn’t in a traditional paper format, and is instead stored as a computer file.  This enables the healthcare provider to share the information with other providers, which eliminates human or timely errors that might otherwise occur from transfers of hard copies.

HIE is the secure electronic exchange of a patient’s EHR between healthcare providers as a means of improving the, “speed, quality, safety and cost of patient care.”  When a patient or provider isn’t called upon to transfer a medical file in person, by fax or mail, yet is accessible to appropriate entities, privacy can be better maintained, and there is a lesser likelihood of unintentional mistakes.  The exchange happens in two ways: the first is a healthcare professional forwarding specific information on a patient to another provider.  The second way is a healthcare professional being able to look up the information on a patient, such as in an emergency room visit, and know fundamental information in order to treat that patient most effectively.

Once data is collected and shared, the next step is to analyze it, which is where the true value of information is realized.  But this doesn’t come without a combined support found with business intelligence (BI) and data warehousing.   Technically speaking, many consider analytics to be a section within BI, yet analytics is such a significant subset, that it is partitioned separately from many of the other business requirements.  Analytics is described as the, “data, statistical, and quantitative analysis, explanatory and predictive models, and fact-based management to drive decisions and actions.”

Real life application of analytics has far reaching capabilities.  Looking at an individual patient who goes into a hospital for emergency care, he/she would no longer be a blank page to all the attending professionals, but with the aid of the HIE, he/she would receive much more accurate and timely treatment.

As unique as we all like to believe we are, humans are creatures of patterns.  Patterns that are created by how our bodies are built; how they are injured and heal; how our minds process stress and pain; and how to predict the future.  All the data that has been collected is analyzed to find the patterns that may not be plausible for a human to identify, but these facts and figures point out when someone fits into parameters of previous patients that showed related symptoms.  Because it is impossible for doctors to memorize every possible condition known, having real-time analytic answers provided will ensure better care.  This method of managing patient treatment can eliminate the need for some testing or medicines in order to discover the root of the issue.

Also, by reducing unnecessary costs on procedures, the overall cost of healthcare can be greatly reduced.  Obviously, there will be basic tests that should always be conducted, but by the process of elimination, a health professional may not be required to conduct avoidable services if a more precise and predictive hypothesis is presented to them.  Essentially, it is taking some of the guessing out of the game.

Analytics can also be used to understand what is going on within a community.  Known as population health management, it is the ability to predict health crises and other visits or hospitalizations.  This is accomplished by way of care teams that provide improved access to care, enable patients to better self-manage their health and reduce the frequency of emergency room visits.  This would then cut costs to both patient and professional, and not divert necessary personnel to the handling of more trivial matters.

Overall, being able to predict the future of where and when staff should be available, how to best provide care for all patients and to do so in the safest and most timely manners, and meet the basic standard of getting more for less.  This applies to people no matter whether they are sitting in a doctor’s office, a specialist’s office, or a hospital.

We live at a time that is completely unprecedented in all of human history: data available at the touch of a button, global communication in a matter of moments, medical procedures and remedies to handle many of life’s wicked twists and turns, and a plethora of other things that make life easier or better. With various devices and data at our fingertips, the realization of personal exposure has become an ever-growing issue. How many places or companies have fundamental information about us in their records? Whether this is from the purchase of a home or vehicle, or maybe from the established medical history at a doctor’s office, we could be susceptible to data mismanagement.

Data governance is defined as the process of managing not only the security but also the quality, usability, consistency and availability of information. There is no doubt that privacy and security of an individual’s records is of the utmost importance, but have you ever thought about the significance of how your data could be used to make your life easier? When an establishment is able to use your information to process payments more efficiently or let you know when it is time to make an appointment, everyone could be a beneficiary.

Looking at the big picture a little more particularly, every day, it is estimated that we create 2.5 quintillion bytes of data. One sector that holds vast amounts of data which needs extensive governance is in the healthcare industry. I’m sure that we have all been through similar sequence of appointments and referrals, such as: family doctor, x-ray technician, specialist to read x-ray, specialist for specific care, and follow up with family doctor. With each visit, there are new forms to fill out, but basically the same questions asked and answered. All of our information is entered into different databases and only accessible at the individual locations. If medical data is forwarded to another doctor or specialist, it must be entered into the new recipient’s database.

The sheer amount of data that is duplicated is part of what adds up to so many bytes of data being created each day. However, if these databases were unified, there would be a greater level of efficiency and less incidence of error. One area of caution that should immediately come to most people’s minds is that of privacy. If information is so readily available to all doctors, specialists and healthcare professionals, how can there be true governance?

Data governance is tightly associated with the strategy that the appropriate data be accessible by the appropriate people. In an efficient association of healthcare experts, a patient’s fundamental information would be entered at one location only. A data file would be created, yet available for the x-ray technician to load images into, and then reachable for the specialist to enter care and prognoses. Because the principal facts have not been recorded by different individuals, there is a smaller likelihood of errors. There are also less chances that subsequent additions to the file will be misfiled, misplaced or altogether lost.
It is understood that an x-ray technician doesn’t need to know the prescriptions that are listed in the medical file, so this information would not be accessible to that party. Thus, privacy is protected and efficiency is still being practiced. This is just the tip of the iceberg, so to speak, of data governance as a means of assurance and improvement in the healthcare sector.

An important aspect of this discussion is the ownership and, consequently, stewardship of all the collected data. Protection of medical reports is not only essential between different departments and specialists, but also from outside invaders. Training, monitoring and security hierarchy must be common focus areas to maintain the utmost isolation within and without the system.

Open access between health professionals to a person’s medical information should not be the only focal point of discussion. Efficiency, privacy and protection must accompany data governance throughout the life cycle of any system of storage and access. There is an evolution that is happening with data, and in this evolution, there are new definitions that have to be established, new protocol to put in place, and growing pains that will be felt. With careful planning, the possibility of seamless communication and more cost-effective production and services can be in the very near future.

The need for intelligence within business, especially the business of healthcare, seems somewhat self-explanatory. However, there is so much more to Business Intelligence (BI) rather than just sitting in a board meeting with executives giving summaries of recent performance, reviewing problems and making grand decisions based on available information, The Business Dictionary defines BI as: computer techniques used to understanding relationships between different data for better decision making.

; whether in reports or as intelligible graphs and data sets. The software that handles raw data is then able to extract meaningful information, which is utilized for making those critical decisions and setting strategies for public health. This is a simplified version of BI; however this gives us a common launching point for our understanding to progress through more defined aspects and deeper meanings.

BI is a visual tool that can provide a particularized situational look at the small and big pictures of areas like financial, operational, clinical experience and outcome. Because the healthcare industry has one of the most complex collections of data in our modern world, any effective tool available to help understand dynamics can be seen as indispensable.

You need the right tool for the right job, so choosing at random BI software is only going to empty your pockets, frustrate your employees and possibly push you further away from achieving any goals already established. To reach predetermined goals, you need exacting tools that will do what you need them to do, not what someone else may perceive that you need. In order to know the difference between what you see as essential to fulfilling desired outcomes and what someone else might see can be quite vast. But, this means that you need to know the nuts and bolts of your business. No small task.

Once you have made this very important assessment, you are now on the road to implementing a wide range of precise instruments to analyze data that might have seemed either unimportant or inaccessible. One of the first benefits that can be seen is the same information or reports that are created in one office, are available at any other location that is part of your network. This way, everyone is on the same page. Miscommunications and misunderstandings are immediately lessened across the board.

Have you ever felt like you are only seeing a portion of the whole picture, so without pertinent pieces of input, decisions are haphazardly made? Yet, when full access to resources is present, processes and allocations can be better determined and placed. This enables better business choices that can affect the bottom line. Quality of care is also affected because distribution of medical professionals is more acutely controlled with people not being stretched too thin or an overabundance of staff standing around with little to do.

Business intelligence works to diagnose problems that may not be routinely noticeable and drive performance for professionals and patients alike. Improving the culture of quality medical practice also improves the overall satisfaction experienced in both of these groups. But, what if satisfaction isn’t the only outcome received? Enhance safety to patient’s care is also a byproduct of better performance and reduced errors. BI isn’t just the big picture tool, but by having up-to-the-minute information on each patient, accurate treatment will be imparted. The attitude changes from one of simply processing patients in and out, to one of providing the best care on the market.

Most of us process data best in visual models such as graphs or charts, which is what BI dashboard tools can offer. A dashboard view needs to be flexible so as to present the same information but in different formats or arrangements. Depending upon the desired insight to be gained, the parameters that are requested for review and understanding can be modified for each user. It is like being able to personalize your Smartphone with specific apps, features and even images. Your characteristics come out, but more importantly, you are accessing what you want and need in a fashion that is comfortable to you. A dashboard serves to render useful information, in a useful manner, and in a means that is comfortable, or more particularly, informative to the user. Large, far-reaching decisions require massive amounts of data, while smaller; more personal decisions require a more exact amount of data. Both groups are satisfied and have the information they need to form their own conclusions.

BI in healthcare has been a long-time in coming, and shows true potential for helping health professionals and patients alike. With the ability to grow as the needs of an organization grow, or any other outside entity requires, medical business intelligence will prove its weight in gold, especially when utilized to its full potential as it is matched with the strategies and goals within your company.

Clinical analytics are here to stay, and that is a good thing. Accuracy in patient care increases as errors decrease; cost of medical treatments decrease because of more efficient management of hospital and other medical professional staff; and best practice standards are adhered to more rigorously. With the additional information that is gathered from healthcare data and population health patterns, benefits not only clinicians, but individual patients and businesses as a whole.

All of this healthcare talk may seem as if we should all just understand what is being explained, however, sometimes delving in just a little deeper to comprehend more succinctly may provide a clearer personal meaning. Do you ever feel in life that there are words thrown at you that you should know, but maybe you don’t fully grasp what the other person is trying to convey?  More and more we are expected to be versed in a large range of subjects, with its entire underlying lingo.  To better take apart a buzz phrase that is now making its rounds and get down to the root of its meaning, I am going to explain clinical analytics.

Not to sound like we are back in 4^th grade English classes, but sometimes the best way to learn the whole is to take its parts.  The definition of clinical as listed on MedicineNet.com has to do with the examination and treatment of patients, especially with regards to medical procedures.  The definition of analytics as laid out by the BusinessDictionary.com site is being involved with the studying of past historical data to find potential trends that can effect decisions or events in the future.

Putting these two words together gives us: the study of patient’s information, as it related to medical treatment, as a means of gaining short- and long-term perception to complex information.

This may not sound like the most exciting of conversations that you could strike up, but with more frequency, clinical analytics is being talked about, being implemented, and is showing great improvement to old methods of managing patients and healthcare issues.

The ease of connecting the word clinical with medical is not a far stretch.  The majority of us have a true understanding of basic healthcare and what it means to visit a doctor or a hospital.  However, the more challenging aspect to the phrase is the analytics side.  So, if we can begin to dig more deeply into the meaning of analytics as it relates to medicine and treatment, we can fully recognize what is being explained instead of glossing over the fundamentals.

The study or analysis of data being received from many sources is a daunting one at best.  That is why most analysis is done by a computer to generate information that is helpful or useful.   The points of data are lined up and formatted in a way that is easy to read and understand, but also in a way that provides a look at patterns.  Patterns that are interpreted well help decision makers to direct resources to where and when they are needed most, and avoid an overabundance of resources in ineffectual locations.

Imagine that you are doing one of those really long division problems that your math teacher thought would be a fun exercise for homework.  You get started and decide that it is too much of a hassle to line up your numbers and calculations correctly, and before long you have no idea what you have completed, or be able to even track your own work.  By then, you are reaching for the nearest calculator and hoping that the teacher can’t follow your calculations but recognizes that you got the right answer.  Well, patterns in healthcare can sometimes feel like a never-ending division problem.  However, there is no calculator that will let you know you have the right answer.

What if you were to have some direction as to when you were headed down the wrong path and could make corrections as you went along?  What if you knew the answer because of patterns that were pointed out?  Do you think you could find your way through the problem?  Of course you could!  Analytics applied with healthcare data and population health patterns can present a better understanding as to needs, direction efforts should be placed and effective decision making.

Let’s take this a step further: the need for dynamic reporting can affect decisions made in the heat of the moment.  When a healthcare professional is able to view information in real time and has access to external data that when combine offer a more detailed picture of a situation as a whole, patience and professionals all benefit.

Image credit: flickr.com