Know about Risk Adjustment Model

Risk adjustment model means an actuarial tool used to predict health care costs based on the relative actuarial risk of enrollees in risk adjustment covered plans.

Each enrollee risk score is based on the individual’s demographic and health status information. A risk score is calculated as the sum of these demographic and health factors weighted by their estimated marginal contributions to total risk. It is calculated based on the relative to average expenditures.

For example:
–Average = $1,000
–Female, 57 = $500 = .5 risk factor
–Condition A = $700 = .7 risk factor
–Risk Score = 0.5 + 0.7 = 1.2

There are many different model available in the health care arena-
1. Age/Sex risk model
2. Rx Risk model
3. Institutional Utilization Risk model
4. Combination of Rx and Institutional Utilization Risk Model
5. Demography base risk model

All these model also can be classified under 2 major category- Concurrent and Prospective.

For any kind of risk adjustment it is not just the data that matters but, as importantly, how do you use the data. Interpretation of the risk data is also important. To get a true picture of your selected population you also need to normalized the score.

one way to reduce the risk for comparing composite indices made up of apples with oranges is to use normalization. Normalization serves the purpose of bringing the indicators into the same level.

The most common method to normalized the risk score is Standardization.  It converts all indicators to a common scale with an average of zero and standard deviation of one.

The average of zero means that it avoids introducing aggregation distortions stemming from differences in indicators’ means. The scaling factor is the standard deviation of the indicator across.

how is it done
The rankings are calculated using ‘z-scores‘ (calculated for each criterion as the actual value minus the mean of the criterion, divided by the standard deviation of the criterion).

The raw score on each measure is converted to a z-score ((‘score’-‘mean score’)/’standard
deviation of scores’)

By taking account of the standard deviation within any one criterion, this method aims to provide a more sophisticated analysis of the differences, and indeed the similarities in some measures, between blogs or webpages.

The z-score of any one criterion is calculated as = (actual value – mean of criterion)/standard deviation of criterion.
(will be continued)