Trend Topic: Hands-on Experience Leads to Better Data Mining

By Andrew Webster, ASA, MAAA


Unlike life insurance or retirement, healthcare is an extremely complex area of actuarial science, because it is offered in a variety of settings by a diverse set of highly-trained professionals.  As actuaries, we are expected to model future healthcare cost and utilization with a high degree of precision.

In order to fulfill that primary duty of mathematical modeling, while simultaneously demonstrating expertise in medical care, actuaries must take a hands-on approach to data mining.

During my decade-long career in healthcare – programming at an electronic medical records (EMR) company, selling analytics software, consulting healthcare organizations – I have had the privilege of working alongside talented physicians. Through those experiences, which included working onsite in a hospital’s skilled nursing facility, I have gained invaluable firsthand knowledge of patient care delivery.

So now, I can easily recognize a sequence of patient events and care transitions when I see them in patient data.

Intimately observing how healthcare is delivered and forming professional relationships with healthcare providers is beneficial to actuarial modeling in other ways.  One way is recognizing which problems have clinical relevance to physicians.

Most clinicians want to know how data analysis will help improve patient outcomes instead of merely focusing on short-term cost reduction. Communicating the modeling results in a way that is meaningful to physicians and integrating results into physician daily workflows is essential.  While most physicians are not mathematicians, they are highly trained in the scientific method and ask insightful questions when modeling results are delivered to them.

What I’ve learned is delivering a risk adjustment model is no longer sufficient. Seeing how physicians apply it is critical. It also allows actuaries to tailor models to ensure they are adaptive to risk. Actuaries can’t do that if they are operating in isolation.

Healthcare data is not static. It is a time series. It is a patient story. To understand a patient’s healthcare journey and predict that patient’s risk, an actuary has to analyze patient EMR and claims data. The physician is an indispensable resource for translating medical codes and terminology, explaining possible root causes for patterns of care, and framing model results within a context of change.

Actuaries help to statistically analyze data while the physician can translate modeling results from paper to practice.

While physicians are used to relying on clinical research and randomized clinical trial data, the actuary is comfortable with naturally collected data. This is different from physicians who are trained to use data to diagnose and treat patients. The administrative and clinical data that actuaries use is seldom used to treat individual patients, rather it is often used to analyze population characteristics.

Actuaries who want to play with new, fun, and interesting data sets to improve the quality of risk prediction should definitely look at healthcare. There’s a huge opportunity for actuaries in a provider setting to be creative and to be heard by C-Suite level executives who haven’t heard the actuary point of view before because it wasn’t relevant before. But now it’s highly relevant. The opportunity to make an impact is much larger.

Medical and information technology is revolutionizing patient care. I encourage all actuaries to step out of the building to gain firsthand experience at healthcare organizations alongside physicians.  Claims data will never look the same.

Sharing is caring.
  • Subscribe to our feed
  • Tweet about this post
  • Share this post on Facebook
  • Share this post on Google
  • Share this post on LinkedIn


4 responses to "Trend Topic: Hands-on Experience Leads to Better Data Mining"

  • Willmer Sagastume says:

    Are there any specific visualization tools commonly used in the healthcare industry to help describe statistical insights to nurses, physicians, or c-level executives?

    • Some guy says:

      I’ve seen typical excel spreadsheets broken down in a presentation for the staff you mentioned. If you meant software tools, then I’ve also seen programs like Statit and Qlikview that break data down to the patient-physican level.

      • Willmer Sagastume says:

        I did mean software tools. It takes a while to solve really complex problems and import large data sets into excel. I do hear that tableau is being used in many different industries though. I also hear D3 is gaining popularity. Does anyone know how the software ‘Epic’ outputs visualizations (graphs, plots, and charts)?

  • Jason Rocks says:

    Tableau is the best data visualization tool for large data sets.

Leave a Comment