Predictive analytics tools, long used in other industries like retail to forecast the likelihood of an event, are one of the critical tools for reducing healthcare waste and improving patient care and outcomes. A 2017 survey by the Society of Actuaries looked at the trends in use and future use of predictive analytics in healthcare:

• 57% of executives (providers and payers) forecast predictive analytics will save their organization 15% or more over the next 5 years, with 26% forecasting saving 25% or more over the next five years.
• 47% of providers currently use predictive analytics.
• 93% say predictive analytics is important to the future of their business.
• Providers cite patient satisfaction as the most valuable outcome for using predictive analytics.
• Payers cite controlling costs as the most valuable outcome for use of predictive analytics.
• Despite what seems like strong support from this data, there are major barriers to the adoption of predictive analytics in healthcare.

Challenges to Using Predictive Analytics in Healthcare

The top 5 challenges for implementing predictive analytics from the Society of Actuaries study are:

• Lack of budget – 16%
• Regulatory issues (e.g. HIPAA) – 13%
• Incomplete data – 12%
• Lack of skilled employees – 11%
• Lack of sufficient technology – 10%

In addition, a recent Harvard Business Review article notes that the success of predictive analytics in healthcare depends less on the tool used and more on the buy-in at all levels of an organization from the start. The authors cite the following major challenges:

• Engaging the right people from the outset – Whether the tool is developed in-house or purchased off-the-shelf, the right people should be involved in the process, with a multi-disciplinary team comprised of clinical, analytics, data science, information technology and behavior change skill sets.
• Change agents and clinical champions – Change agents are essential to successfully implementing predictive analytics, particularly for sustaining its usage. These individuals often work alongside clinicians to map workflows and identify changes and new processes. In addition, clinical champions are a must to promote the tool among their clinical peers.
• C-suite commitment – Frontline buy-in is essential, but without the full commitment of the C-suite, predictive analytics won’t take off or be fully utilized. Identifying measures that resonate with management is important, such as financial penalties associated with hospitals readmissions.

Why Implement Predictive Analytics in Healthcare?

As noted in the HBR article, “Implementing predictive analytics is a means to an end – where the end should represent an improvement in health or health care outcomes, including lower costs.”

Additional major reasons as noted in Hospitals & Health Networks include:

• Success in the shift from fee-for-service to value-based care, which may be impossible without the use of predictive analytics, along with data warehousing and integration.
• Being able to understand a healthcare system’s current state is a must for being able to forecast a desired future state and associated plan to get there.
• The ability to get in front of healthcare consumer trends.
• Supporting population health initiatives.
• Improving patient care: reducing hospital readmissions, reducing hospital stays, anticipate staff needs and more.

Ultimately, predictive analytics in healthcare is about translating data and science into practical applications to solve complex clinical and business problems that improve care and control costs. The end game? Strategic, cost-effective high-value care.