Predictive analytics is becoming a mainstream term in the regular business arena. As it applies to health care, could you flesh out the meaning?
Predictive analytics is an advanced analytics combining data mining, statistics, artificial intelligence, algorithms and modeling. Essentially, it’s the use of historical and current data to make predictions about the future.
In health care, predictive analytics can be used to identify patients who are at higher risk of being readmitted to the hospital. Once identified, these patients can receive targeted support to navigate the continuum of care, with the goal of lowering readmission rates and avoiding readmission rate financial penalties.
Another example is using predictive analytics to identify patients who are at high risk of becoming septic in the hospital. Comparing biological parameters from patients against an established algorithm can indicate risk for becoming septic, allowing clinicians to focus on prevention, potentially saving lives.
Talk about the role of predictive analytics in Delaware’s health care landscape and how Delaware Health Information Network (DHIN) is a funnel for this type of information.
Predictive analytics is very new in health care. Most organizations are still normalizing data so that different codes with the same meanings can all be recognized in the same category of information and cleaning up data standardization issues.
DHIN receives data on patients throughout the continuum of care, and the more data available on a patient, the more accurate the predictive capabilities. We are continually improving our data quality and ability to normalize the data from many different data senders.
How is predictive analytics benefitting the health care community and Delaware patients?
Predictive analytics can be used to help achieve the triple aim in health care: improving the patient experience, improving the health of populations and reducing the cost of health care.
What is the feedback that you’re getting from the medical community?
Most providers understand the benefits to predictive analytics, but it isn’t always part of a provider’s usual workflow. As a result, many systems are cumbersome to use in daily clinical decision making. The changes in reimbursement models are likely to be the biggest drivers to adopting predictive analytics, as more and more reimbursements are tied to improving patient outcomes while reducing cost of care.
What are the possibilities in the next five years, 10 years?
As standardization of data in health care becomes more mandated, the ability to use data to make predictions will grow. Additionally, as the algorithms for making data-based predictions become more fine-tuned, we could see acceleration in the development of other areas, such as precision medicine based on genetic and molecular profiling.
