A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare
Health Services Research · 2026
DOI: 10.1111/1475-6773.70093 ↗Kurz gefasst
Fachartikel in der Zeitschrift Health Services Research, 2026. Verfasst von Daniel K Shenfeld und 8 weiteren Autor:innen. Beteiligte Einrichtung: Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. Hauptthemen laut MEDLINE: Medicare, Risk Adjustment, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schmidt Futures.
Abstract (Originalsprache)
Objective
To develop a machine learning (ML) algorithm that improves accuracy compared to the Hierarchical Condition Category (HCC) score used by the Centers for Medicare and Medicaid Services to risk‐adjust payments for > 65 million Americans. Study Design and Setting Prognostic study using Medicare claims data to train “Franklin”, an ML algorithm predicting one‐year costs, trained using identical data to HCC. Predictive accuracy was evaluated using R 2 log cost, Spearman rho, and sensitivity and specificity. Data Sources and Analytic Sample Random sample of 2018–2019 Part A and B claims from aged, community‐based enrollees in Traditional Medicare who were not dually eligible and did not have end‐stage renal disease. Principal Findings The sample consisted of 4,176,666 Medicare beneficiaries (mean [SD] age 74.9 [7.2] years, 55.9% women; 85.9% Non‐Hispanic white, 5.6% African‐American, 3.4% Hispanic). Franklin was more accurate than HCC ( R 2 log cost 0.44 vs. 0.15; Spearman rho 0.61 vs. 0.41, p < 0.001 for both). Accuracy improved for the 47% of beneficiaries with 0 HCCs and the 27% of beneficiaries with one HCC (Spearman rho 0.59 vs. 0.08 and 0.46 vs. 0.16, respectively; p < 0.001 for both). Franklin outperformed HCC in detecting the 20% lowest‐cost beneficiaries (sensitivity 0.60 vs. 0.34, specificity 0.90 vs. 0.83; p < 0.001 for both). Franklin improved accuracy over HCC for racial/ethnic minorities and rural‐dwelling beneficiaries ( R 2 log cost Black 0.48 vs. 0.14, Hispanic 0.55 vs. 0.09, rural 0.36 v. 0.11; p < 0.001 for all), although Franklin disproportionately classified Black (15.8% vs. 10.1%) and Hispanic (22.9% vs. 12.2%) beneficiaries in the lowest predicted cost decile.
Conclusions
Franklin is an ML risk adjustment model that significantly improves risk‐adjustment accuracy for Medicare beneficiaries compared to HCC. Franklin could generate improvement in payment accuracy, reduction in selection incentives, and financial savings to Medicare. Clarifying the equity impacts of more accurate risk adjustment is necessary.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
- Division of Computer Science & Engineering, University of Michigan, Ann Arbor, Michigan, USA.
- Washington University School of Medicine, St. Louis, Missouri, USA.
- Emory University School of Medicine, Atlanta, Georgia, USA.
ORCID-Profile: Karen Joynt Maddox, Ezekiel J Emanuel
Förderung
- Schmidt Futures
Zitieren
APA
Shenfeld, D. K., Warrenburg, L., Silvert, E., Guido, M., Makar, M., Joynt Maddox, K., Navathe, A. S., Parikh, R. B., & Emanuel, E. J. (2026). A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare. Health Services Research. https://doi.org/10.1111/1475-6773.70093
Vancouver
Shenfeld DK, Warrenburg L, Silvert E, Guido M, Makar M, Joynt Maddox K, et al. A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare. Health Services Research. 2026. doi:10.1111/1475-6773.70093
BibTeX
@article{Shenfeld2026,
author = {Shenfeld, Daniel K and Warrenburg, Lindsay and Silvert, Eli and Guido, Matthew and Makar, Maggie and Joynt Maddox, Karen and Navathe, Amol S and Parikh, Ravi Bharat and Emanuel, Ezekiel J},
title = {A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare},
journal = {Health Services Research},
year = {2026},
doi = {10.1111/1475-6773.70093}
}
EUVIMED