TY - JOUR
T1 - Improving risk adjustment with machine learning
T2 - accounting for service-level propensity scores to reduce service-level selection
AU - Park, Sungchul
AU - Basu, Anirban
N1 - Funding Information:
We would like to thank Sherri Rose and James Lomas for providing expert support in statistical software and related documentation.
Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.
PY - 2021/9
Y1 - 2021/9
N2 - The hierarchical condition category (HCC) risk adjustment model tends to produce over-predictions of health care expenditures for individuals who need less costly services and under-predictions of health care expenditures for those who need costlier services. This tendency leads health plans to effectuate service-level selection to attract profitable individuals and avoid unprofitable individuals. In this study, we propose an alternative model using machine learning (ML) techniques to reduce service-level selection by accounting for demographic and diagnostic characteristics as well as service-level propensity scores (SPS) that capture each individual’s need for each service (the HCC + SPS model). Using the 2013–2014 Truven MarketScan database, we compare the performance of the HCC model (the HCC-only model) and the HCC + SPS model. We first fit both models with ordinary least squares (OLS) because traditional risk adjustment models rely on OLS. We also fit these models with ridge regression, which is a regularized ML algorithm, in order to examine whether the performance of the HCC + SPS model improves when combined with ML techniques. We evaluate prediction performance at three levels: group-level, tail distribution, and individual-level. We find that the HCC + SPS model more accurately estimated health care expenditures when combined with ridge regression, especially for individuals with high expenditures. However, we found limited improvements when the HCC-only model was used with ridge regression or the HCC + SPS model was used with OLS. Our findings suggest that accounting for SPS in risk adjustment using ML has the potential to reduce service-level selection.
AB - The hierarchical condition category (HCC) risk adjustment model tends to produce over-predictions of health care expenditures for individuals who need less costly services and under-predictions of health care expenditures for those who need costlier services. This tendency leads health plans to effectuate service-level selection to attract profitable individuals and avoid unprofitable individuals. In this study, we propose an alternative model using machine learning (ML) techniques to reduce service-level selection by accounting for demographic and diagnostic characteristics as well as service-level propensity scores (SPS) that capture each individual’s need for each service (the HCC + SPS model). Using the 2013–2014 Truven MarketScan database, we compare the performance of the HCC model (the HCC-only model) and the HCC + SPS model. We first fit both models with ordinary least squares (OLS) because traditional risk adjustment models rely on OLS. We also fit these models with ridge regression, which is a regularized ML algorithm, in order to examine whether the performance of the HCC + SPS model improves when combined with ML techniques. We evaluate prediction performance at three levels: group-level, tail distribution, and individual-level. We find that the HCC + SPS model more accurately estimated health care expenditures when combined with ridge regression, especially for individuals with high expenditures. However, we found limited improvements when the HCC-only model was used with ridge regression or the HCC + SPS model was used with OLS. Our findings suggest that accounting for SPS in risk adjustment using ML has the potential to reduce service-level selection.
KW - Health care expenditures
KW - Machine learning
KW - Risk adjustment
KW - Risk selection
KW - Service-level selection
UR - http://www.scopus.com/inward/record.url?scp=85100113890&partnerID=8YFLogxK
U2 - 10.1007/s10742-020-00239-z
DO - 10.1007/s10742-020-00239-z
M3 - Article
AN - SCOPUS:85100113890
SN - 1387-3741
VL - 21
SP - 363
EP - 388
JO - Health Services and Outcomes Research Methodology
JF - Health Services and Outcomes Research Methodology
IS - 3
ER -