In the hunt for improvement to the healthcare industry many have turned to a concept that has been accepted and practiced within other industries for ages: analytics.  The need to understand what has happened and what is coming is essential to finding problematic areas in a department or throughout a business as a whole.  It’s not to say that analytics hasn’t been used in healthcare; it just hasn’t been applied in ways that shape the quality of care and change the way workflow is managed.  Now it is time to move beyond simple analytics, and implement prospective analytics as a means of utilizing all that data that
 has been collected. 

 

Prospective analytics isn’t a stand along category of analytics, but encompasses both retrospective and predictive analytics in order to use data to affect decisions, actions and results at the doctor/patient level.  If this is becoming a bit dizzying, there is a reason for it: you cannot step into prospective analytics and proceed forward.  It is built upon a strong foundation of working retrospective and predictive logistics. 

 

The first building block of being a retrospective system means that the organization is able to look back at everything that has happened with patient care and draw out patterns and make conclusions.  For the most part, all healthcare professionals do this without much thought because most patients are relatively similar and have comparable reactions with diseases, illnesses, injuries and treatments.  Thus, when someone exhibits specific symptoms, a doctor can deduce what most likely is going on.  Sometimes it is necessary to back up a supposed diagnosis with tests, exam, x-rays and the sort, but when confirmed, a similar treatment can be prescribed no matter who the patient is.

 

The second building block is predictive analytics, which takes all the information from the retrospective aspects and moves to a more offensive position with patients and patient care.  What this entails are identifying patients that display high-risk behaviors, such as high blood pressure, cholesterol, family history of disease or illness, and work to make improvements within the lives of these patients.  This might take place when a patient comes in for a yearly wellness exam; working to explain and create lifestyle changes to eliminate reoccurrences, emergency situations or readmittance to clinics or emergency rooms. 

 

After organizations are comfortably using each of these types of analytics, and there are well-established guidelines set forth that are adhered to, you can think about capping things off with prospective analytics.  It should be seen here that prospective analytics is more like a set of tools that should be utilized rather than just a way of thinking or performing.  Prospective clinical decision support tools can include:

 

  • Creating and implementation of rule-based system
  • Strict knowledge and adherence to encoding
  • Logistics designed by clinical experts
  • Mathematics-based modeling to create risk scores

 

What all of this adds up to create is a better decision-making process that improves the outcome patients achieve and also lowering the costs involved with healthcare at every level.  When a system is able to predict developing patterns and presents courses of action with possible risk versus reward information, you can see how many healthcare organizations are working towards establishing prospective analytics into their daily activities. 

 

It almost goes without saying that implementing changes can bring out the worst in some people.  Routines and consistencies are how many of us manage challenging work environments.  Selling a new way of managing data and working with patients is one thing, but if the new way workflow entails extensive steps, excessive time and energy, or a manual just to do basic tasks, there are going to be fewer people willing to buy into the program initially and even fewer who are willing to follow through and employ it.  Making a system user-friendly should be a high priority no matter what organization is using it.

  

Retrospective analytics relies on what has already happened and what can be proven.  Predictive analytics take the likeliness of what will happen and uses it for moving forward. Prospective analytics combines these two systems and then use a continual verification and validation process to ensure better treatments and better outcomes.  

 

 

images courtesy of:
-Freedigitalphotos.net/bulldogza
-Freedigitalphotos.net/cooldesign
-Freedigitalphotos.net/hywards

© 2017 Prospective Analytics
Design by schefa.com