CRC Data Mining and Predictive Analytics 2

Question 1

An MA plan uses predictive modeling to identify patients with suspected undocumented conditions. Which data source combination is most effective?

Accepted Answer

Claims combined with pharmacy data to identify conditions suggested by medication patterns

Answer

Claims data only

Answer

EHR data only

Answer

Survey data combined with demographics

Question 2

A provider group's mental health HCC capture rate increased 300% year-over-year. What analytical approach should be used?

Accepted Answer

Compare against peer trends, evaluate for staffing changes or new screening programs

Answer

Immediately flag as fraud

Answer

Accept the increase if patient volume increased

Answer

Discount as normal variation

Question 3

Which technique is most appropriate for estimating future healthcare costs using historical risk adjustment data?

Accepted Answer

Gradient boosted trees incorporating HCCs, demographics, utilization, and pharmacy data

Answer

Simple linear regression using RAF scores

Answer

K-means clustering by cost similarity

Answer

Logistic regression for high-cost vs low-cost prediction

Question 4

Data mining reveals 8% of HCC revenue comes from diagnoses captured only during annual wellness visits. What risk does this represent?

Accepted Answer

Moderate RADV audit risk if documentation lacks clinical depth

Answer

No risk, as wellness visits are valid encounter types

Answer

High fraud risk requiring immediate OIG reporting

Answer

Administrative risk only

Question 5

Which feature would be the strongest predictor for a model predicting HCC gaps?

Accepted Answer

HCCs captured in prior year not yet appearing in current year claims

Answer

Member age and gender

Answer

Number of unique providers seen

Answer

Total medical expenditure

Question 6

Data mining reveals providers consistently coding cerebrovascular sequelae without prior stroke documentation. What technique identified this?

Accepted Answer

Anomaly detection identifying deviations from peer norms

Answer

Supervised classification

Answer

Association rule mining

Answer

Time series analysis