Sample Selection for Medicare Risk Adjustment Due to Systematically Missing Data.

Savannah L BergquistThomas G McGuireTimothy J Layton Sherri Rose

Published in: Health services research (2018)

Fitting MA risk adjustment formulas on a random sample versus a matched sample yields little difference in MA plan payments. This does not rule out potential improvements via the matching method should reliable MA encounter data and additional variables become available for risk adjustment.

Keyphrases

big data
healthcare
risk assessment
artificial intelligence
data analysis
breast cancer risk