Early Benefits of Analyzing Your Retirement Community’s Data Base

Data Mining - The FutureIn order to preserve census in Retirement Communities (Assisted and Independent Living), a detailed knowledge of the healthcare needs of every resident would be invaluable.  The importance of this knowledge cannot be over-emphasized, since the National Center for Assisted Living tells us that 92% of residents who move out of Assisted Living Communities (ALCs) do so for health reasons.

An understanding of Chronic Health Conditions (CHCs) will improve a Retirement Community’s ability to maintain the health of its residents.  Chronic Health Conditions are those that last a year or more and require ongoing medical attention and/or limit activities of daily living.  The most common CHCs are:

  1. High Blood Pressure
  2. Alzheimer’s disease and other dementias
  3. Heart Disease
  4. Depression
  5. Arthritis
  6. Osteoporosis
  7. Diabetes
  8. COPD and allied conditions
  9. Cancer
  10. Stroke

Chronic health conditions account for more than 75% of all healthcare spending in the US and are the driving force of healthcare for older people.  Eighty percent of independently living seniors have 1 CHC, and 50% have 2 or more according to the Centers for Disease Control.  At some point, the burden of CHCs overwhelms the ability of independently living seniors to care for themselves, so many seek Assisted Living.  At this point, the typical resident has at least 2-3 of the most common CHCs.

Assisted Living Communities are charged with addressing very complex healthcare issues in addition to the challenging responsibility of providing residential care that includes a wide variety of services and amenities.  The services that ultimately have the largest impact on resident retention, however, are healthcare services.

Data mining the known information about a Retirement Community’s residents can provide extremely valuable insight that can guide and assist healthcare management.  Our experience with data mining ALCs and ILCs (Independent Living Communities) of various sizes in Boise, Idaho has enabled us to:

  • Discover which CHCs are the most common in each specific ALC or ILC.
  • Establish a ‘health risk profile’ that is specific for each resident.
  • Based on the ‘health risk profile’, design interventions that may help preserve census by reducing health related attrition.
  • For ILCs, discover which CHCs pose the highest risk for losing a resident to an ALC, and then most importantly…what to do about it.
  • Gain insight on which residents nurses, aides, and other employees should focus their time and attention based on the health risk profile.
  • Compare the health risk profile of a specific ALC to national statistics.
  • Gain marketing insight based on the health risk profile of current residents of ALC’s and ILC’s.

Our next several blogs will show specific examples of the kinds of information retrieved by data mining Retirement Communities.  We will then demonstrate how this information can be used to create the health risk profiles discussed above.  We look forward to your feedback.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>