Predictive Health Analytics in the Workplace: Observation, Prediction, and Control

“Knowledge is Power, Power provides Information; Information leads to Education, Education breeds Wisdom; Wisdom is Liberation.” – Israelmore Ayivor

Who hasn’t watched world-class cyclists aggressively competing in the Tour de France? Cycling at high speed in tight packs on winding roads, they have an uncanny ability to quickly identify opportunities to gain an edge, predict the response of their competitors and the pack as they make their move, and effectively gain control and take the lead (and hopefully the yellow jersey). How do they do that?

Observation, Prediction, and Control

The scientific method includes generating hypotheses from observations of the world, which are then deployed to test their reliability or accuracy. The best way to test reliability is to predict an effect before it occurs. If we can manipulate the independent variables (the efficient causes) that make it occur, then the ability to predict makes it possible to control. Such control helps to isolate the relevant variables. Control also refers to a comparison condition, conducted to see what would have happened if we had not deployed the key ingredient of the hypothesis: scientific knowledge only accrues when we compare what happens in one condition against what happens in another.

Using Predictive Analytics to Improve Healthcare

The past century’s advancements in healthcare have resulted in an ever-increasing knowledge base of biomedical data for healthcare providers to access while diagnosing and treating their patients. Multi-platform interoperability and artificial intelligence (AI) are helping to corral those living and growing databases of biometrics and health outcomes.

According to a study by the American Medical Informatics Association (AMIA) on “The Future State of Clinical Data Capture and Documentation,” global healthcare data added up to around 500 petabytes in the year 2012 and was expected to reach around 25,000 petabytes by the year 2020. Despite this wealth of information, it also creates a problem: accessibility. The main purpose of documentation should be to support patient care and improved outcomes for individuals and populations according to an AMIA Health Policy Meeting. This is where predictive analytics come into play, allowing the healthcare community to focus on finding innovative ways to enhance people and population health without having to manually examine a large amount of unwieldy data.

Observation: Gather and monitor demographic, biometric, and health outcome data.
Prediction: Identify relevant, high-yield opportunities to impact employee health, well-being, productivity, and business success.
Control: Implement focused interventions while continuously monitoring preferred impacts on your population and business; monitor and adjust as appropriate.

Here are a few examples of focused, IT-budget friendly excursions into the world of predictive healthcare analytics which can be applied in a corporate setting:

1. Identify key readily available attributes of your population’s demographics (age, gender, dependents, ethnicity, median income, etc.) to design targeted health information newsletters and resources relevant to your business.
2. Using data gleaned from indemnity and workers’ compensation claims, identify opportunities to modify health benefits plans to proactively address high-risk behaviors or diagnoses. In other words, focus on primary and secondary prevention interventions.
3. Using a Health Risk Assessment (HRA) tool, confidentially survey your population for their healthcare challenges, both personal and work-related. Does the data match up with your benefits plans and claims data? Recruitment and retention?

7 Ways Predictive Analytics Can Improve Healthcare

1. Increased accuracy of diagnoses.
2. Improved preventive medicine and public health.
3. Provide physicians with answers they are seeking for individual patients.
4. Provide employers and hospitals with predictions concerning insurance product costs.
5. Allow researchers to develop prediction models that do not require thousands of cases and that can become more accurate over time.
6. Pharmaceutical companies can use predictive analytics to best meet the needs of the public for medications.
7. Patients have the potential benefit of better outcomes due to predictive analytics.

If you’re interested in learning more, consider these resources for additional reading:

1. Caitlin M. Cusack. “The future state of clinical data capture and documentation: a report from AMIA’s 2011 Policy Meeting.” Journal of the American Medical Informatics Association, Volume 20, Issue 1, January 2013, Pages 134–140.
2. Nghi Tran-Hoang-Phuong. “7 Ways Predictive Analysis Can Improve Healthcare.” July 15, 2021.
3. Shantanu Chaturvedi. “7 Ways Predictive Analysis Can Improve Healthcare.” Digital Health Today. November 8, 2017.

__________________________________________________________________________________________

About the Author

Dr. Joe Mignogna is Acuity’s Chief Medical Officer.  Connect with him at jmignogna@acuityinternational.com