Diagnosis Based Models

Question 1

Questions to answer when building a clinical identification algorithm (142)

Answer 1

A clinical identification algorithm is a set of rules that is applied to a claims data set to identify the conditions present in the population

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

Question 2

Challenges when constructing a condition-based model (142)

Answer 2

1. The large # 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 3

Sources of data for a clinical identification algorithm (142)

Answer 3

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 4

Definitions of sensitivity and specificity (143)

Answer 4

When building clinical identification algorithms, the proper balance between sensitivity and specificity must be found

1. Sensitivity - the % of members correctly identified as having a condition (“true positives”)
2. Specificity - the % of members correctly identified as not having a condition (“true negatives”)

Specificity may be more important for underwriting, while sensitivity may be more important for care management, since clinicians can verify the presence of a condition.

Question 5

External sources of clinical identification algorithms (144)

Answer 5

1. HEDIS (from the NCQA) has algorithms for identifying some conditions (eg, asthma, high blood pressure, diabetes)
2. Disease Management Association of America (now Care Continuum Alliance) 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

Question 6

Reasons for using commercially-available grouper models (145)

Answer 6

1. Building algorithms from scratch requires a considerable amount of work
2. Models must be maintained to accommodate new codes, which requires even more work
3. Commercially-available models are accessible to many users. Providers and plans often require that payments be based on a model that is available for review and validation

Question 7

Benefits of using ICD10 (162)

Answer 7

1. Will help fuel better care for patients
2. Will inform smarter healthcare delivery
3. Will streamline administrative processes
4. Will improve the industry’s predictive modeling capabilities
5. Will help providers keep better records of patients’ medical histories
6. Will allow providers to create more accurate info for billing and administrative purposes, which should help avoid delays in processing claims
7. Will allow for better predictions related to a patient’s overall health and likelihood of developing certain conditions
8. Will allow earlier identification and intervention for risks, which could help prevent chronic conditions from developing
9. Will help healthcare providers better grasp what the best course of care might be for a given patient
10. Will provide payers with better data to analyze in fraud and abuse detection models

Question 8

Frequently used commercially available grouper models (145)

Answer 8

1. Adjusted Clinical Groups (ACG)
   b. Case-mix adjustment for inpatient and ambulatory
   b. Assigns members into mutually exclusive ACG categories based on ADGs, age, sex and optional data (i.e. pharmacy, prior cost experience, utilization measures, procedures)
2. Diagnosis Related Groups (DRGs) – classifies diseases/conditions based on the impacted organ system, surgical procedures performed, morbidity, and sex of the member. Uses:
   a. Principal diagnosis – assigns the admission into a major diagnostic category
   b. Principal procedure – classified as a medical or surgical DRG if the member had an operating room procedure
   c. Age and Sex
   d. Member’s disposition (i.e. member died, member left facility against medical advice)
   e. Secondary diagnosis
   i. Presence or absence of co-morbidities and complications
   ii. It is used to assign the member into a higher or lower severity DRG and it is used to classify the ADRG into a single DRG
3. Chronic Illness and Disability Payment System (CDPS) – used to adjust capitation payments
4. Clinical Risk Groups (CRGs)
   a. Approach assigns a member to a single mutually exclusive risk group based on clinical criteria and demographic characteristics
   b. Each risk group represents individuals that require similar amounts and types of healthcare resources that will be required
   c. Predicts utilization/cost on a prospective or retrospective basis for both inpatient and ambulatory encounters
5. Diagnostic Cost Groups/Hierarchical Condition Category (DCG/HCC)
6. DxCG Models – can be used for used for care management interventions, risk adjustment, development of health-based and performance based payment methods, and provider reimbursement. Groupings are DxGroups - Condition Categories - Hierarchical Condition Categories - Related Condition Categories (specific diseases) - Aggregate Condition Categories
7. Episode Treatment Groups (ETGs) – groups by episode of care and not by diagnosis for the duration of the episode