- Predictive analytics have the potential to enhance care delivery, improve patient outcomes, and reduce care costs, enticing more healthcare executives to explore the implementation of data-driven tools.
According to a recent survey from the Society of Actuaries (SOA), emailed to journalists, eighty-five percent of healthcare payers and providers are currently using predictive analytics or plan to do so in the next five years.
Eighty-seven percent of survey respondents said that predictive analytics tools will be important to the future of their business.
“Most executives are very interested in using predictive analytics tools to increase cost saving, improve patient satisfaction, and satisfy their staffing and workforce needs,” Lillian Dittrick, Fellow of the Society of Actuaries, told HealthITAnalytics.com.
However, she added, organizations will need to take a hard look at some perceived barriers before they can take advantage of a new generation of predictive tools.
Predictive analytics adoption requires access to timely, accurate data, as well as adequate funding, two resources that many entities feel that they lack.
Fourteen percent of respondents stated that incomplete data is one of the biggest barriers they face when trying to implement predictive tools. Yet six percent said they have too much data, indicating that many organizations simply don’t know where to begin when assessing their data assets.
Both providers and payers may have more – and better – data at their fingertips than they think, said Dittrick.
“You don't need to wait until you have perfect data to use predictive analytics. There are methods to help fill in data gaps, and organizations can do a lot of great predictive modeling using what they have,” she said.
“Both payers and providers have a wealth of information that they can use to build models. Healthcare providers can also acquire some other sources, like the social determinants of health, for example, that will really help the strength and accuracy of their models.”
Dittrick, who has worked on both the payer and provider sides of healthcare, said that organizations can use social determinants data to tailor patient risk stratification and refine their predictive capabilities.
“We tend to identify quite a few people who have different chronic conditions or other issues that call for enhanced management,” she said.
“When we use predictive models to look at all the variables, it helps us prioritize those patients who are really going to be receptive to changing something in their lifestyle, such as nutrition or exercise.”
In addition to data challenges, survey participants named budgetary restrictions as a main concern, with 14 percent of executives saying lack of funding is their biggest challenge to implementation.
Once again, the respondents may be mistaken. “There are probably some misperceptions around the kind of budget you need,” Dittrick observed.
“Most providers don’t need to start from scratch. Most of the larger electronic health record (EHR) systems already have predictive models embedded in them, and that can be a great resource so that executives don’t have to spend a lot to start seeing results.”
Organizations should also keep in mind that the return on an initial investment in predictive analytics is likely to be significant. More than a third of current predictive analytics users stated that they saw overall cost reductions – while improving outcomes and patient satisfaction at the same time.
Sixty percent of organizations believe that predictive analytics will help them save more than 15 percent over the next five years, which will likely offset the costs of developing infrastructure and analyzing data.
Providers and payers who invest in these tools will have an edge over their peers in terms of automating processes, leveraging machine learning techniques, and ensuring data security, the survey said.
“We're seeing more and more, across all industries, that automation and machine learning tools really help with sorting through and processing very large amounts of data. We've made some good progress with automating processes that were once very manual using these tools,” Dittrick said.
In order to share these results clearly, organizations should focus on creating meaningful data visualizations, she advised.
“Organizations will often develop great analytics solutions, but they have trouble communicating that information in an effective manner,” she said.
“There are great visualization tools out there now that can help organizations tell that compelling story and translate it into easy-to-digest, actionable information.”
Predictive analytics will play a key role in the future of care delivery, providing clinicians with the insights needed to deliver quality, cost-effective care.
Organizations that can overcome data issues, budgetary concerns, and regulatory standards to adopt predictive tools will experience improved patient outcomes and advanced data analytics.
“There is some kind of predictive modeling that could help improve processes in just about any facet of healthcare,” Dittrick concluded. “And if you have actuaries on staff, don’t forget that they are very well suited to do this kind of work. They have the training and the education that can help with this invaluable work for the healthcare industry.”