Clinical Identification Algorithm

Question 1

Questions to answer when building a clinical identification algorithm (7)

Answer 1

1. Where are the diagnoses?
2. What is the source of the diagnosis (claims, medical charts)?
3. If the source is claims, what claims should be considered (IP, OP, labs)?
4. If the claim contains more than one diagnosis, how many diagnoses will be conisdered for identification?
5. Over what time span, and how oftem, will a diagnosis have to appeaar in claims for that diagnosis to be incorporated?
6. What procedures may be useful for detremining severity of a diagnosis?
7. What prescription drugs may be used to identify conditions?

Question 2

Clinical Identification Algorithm definition (2)

Answer 2

1. A set of rules that is applied to a claims data set to identify the conditions present in the population.
2. Correlations between claim costs and medical conditions can then be used to estimate future cost.

Question 3

Challenges when constructing a condition-based model (6)

Answer 3

1. Large number of procedure and drug codes.
2. Deciding the severity level at which to recognize the condition.
3. The impact of co-morbidities for conditions that are often found together.
4. The degree of certainty with which the diagnosis has been identified.
5. The extent of the data (claims data will cover all members, but self-reported data will not)
6. The type of benefit design that underlies the data

Question 4

sources of data for a clinical identification algorithm (5)

Answer 4

1. Diagnosis in a medical record - is highly reliable, but is seldom available for actuarial work
2. Medical claims - one of the most common sources
3. Drug claims - the other most common source
4. Laboratory values
5. Self-reported data

Question 5

Definitions of sensitivity and specificity (2)

Answer 5

When building clinical identification algoriths, the proper balance between sensitivity and specificty must be found:

1. Sensitivity - the % of members correctly identified as having a condition (true positive)
2. Specifcity - the % of members correctly identified as not have a condition (true negative)

Specifcity may be more important for underwriting while sensitivity more important for care management.

Question 6

External sources of clinical identification algorithms (4)

Answer 6

1. HEDIS (from the NCQA) has algorithms for identifying some conditions (i.e. asthma, high blood pressure, and diabetes).
2. Disease Management Association of America developed algorithms for identifying chronic diseases.
3. Grouper models - commercially available models that identify member conditions and score them for relative risk and cost.
4. Literature - articles will sometimes report the codes that are used for analysis.