When I worked clinically in the healthcare industry I directly participating in hundreds of open heart surgeries, emergency cardiac support cases and traumas that required me to be both prepared and predictive in nature based on past knowledge and case experience. Even before the advancement of predictive analytic technology I found this to be a crucial practice that benefited the outcome of future cases. Nowadays, healthcare practitioners have a huge amount of data and responsibility to deal with while assuring that they provide the best possible care to each patient. If you are in healthcare today you realize that electronic healthcare data is abundant and healthcare workers are facing information overload that directly affects the patient. So, the question is how can we harness this information and how can it be used to improve patient care? The answer is simple, predictive analytic modeling and in this article I will provide a primer for this practice that can be used within the health care industry.
First, let’s define what predictive analytics is. Predictive analytics is an area of statistical analysis that deals with extracting information from data and using it to predict trends and behavior patterns. The technique of predictive analytics uses variables that can be measured to predict the future behavior of a person or other entity. This is all done with the goal of combining the data and a powerful predictive model. When we talk about predictive analytics we are really talking about a set of mathematical techniques applied to a data set for determining the probability that some scenario is likely to happen or become true. These techniques are applied and used in research, genetics, business and healthcare.
Current healthcare practices are based on more traditional statistical analysis that many times leads to treating a patient as a “mean” of a particular patient population. Although this methodology has been used for decades looking at the “mean” such as an individual’s demographics, history, health conditions and genetics in this manner is not an optimal way to determine how a patient will react to a particular treatment or plan. Let’s take this a step further and apply predictive analytics to healthcare data and develop treatments that are more effective and in tune with the individual patient vs. a “mean” population approach. Through predictive analytics practitioners empower themselves with meaningful and accurate information that will help develop a much more powerful patient care plan with a more successful outcome.
Predictive Analytics in healthcare can provide practitioners with numerous benefits to improve patient care such as:
• Reducing Readmissions
• Risk of mortality during hospitalization
• Risk of transferring to the Intensive Care Unit during hospitalization
• Risk of course of treatment
• Risk of surgical intervention
There is no doubt that predictive analysis based on a strong model is a powerful tool in managing patient risk and outcomes. Moreover, understanding a patient’s statistical risk of an outcome or event can help a practitioner and healthcare team make decisions in such areas as creating a patient’s plan of care, identifying the best clinical protocols in the care of that patient and allocating resources, such as tele-health, advanced treatments, or specialty care, to those patients who need them and will
benefit from it the most.
Predictive analytics present such an exciting opportunity for both healthcare professionals and the technology world to make a real difference in the quality of healthcare by improving the overall care of each patient. Predictive analytics will help the healthcare industry become efficient, systematic, and statistically better predict the course of total patient care. The end result of predictive technology is to help practitioners do their jobs better and place focus back on the patients who need them the most.
I have provided some great resources for predictive analytics below, enjoy:
1. How Care Teams Are Using Predictive Analytics and Comparative Data to Optimize Interventions for High-Risk Patients
2. Seton Healthcare uses IBM Content and Predictive Analytics to improve care & lower CHF readmissions .
3. reducing readmissions to improve care
Dale Gibler, MSCIS