{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T02:29:22Z","timestamp":1789439362365,"version":"build-2803163510"},"reference-count":42,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100027426","name":"Schmidt Futures","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100027426","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Health Services Research"],"published-print":{"date-parts":[[2026,4]]},"abstract":"ABSTRACT<\/jats:title>\n \n Objective<\/jats:title>\n 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\u2010adjust payments for >\u200965 million Americans.<\/jats:p>\n <\/jats:sec>\n \n Study Design and Setting<\/jats:title>\n \n Prognostic study using Medicare claims data to train \u201cFranklin\u201d, an ML algorithm predicting one\u2010year costs, trained using identical data to HCC. Predictive accuracy was evaluated using\n R<\/jats:italic>\n 2<\/jats:sup>\n log cost, Spearman rho, and sensitivity and specificity.\n <\/jats:p>\n <\/jats:sec>\n \n Data Sources and Analytic Sample<\/jats:title>\n Random sample of 2018\u20132019 Part A and B claims from aged, community\u2010based enrollees in Traditional Medicare who were not dually eligible and did not have end\u2010stage renal disease.<\/jats:p>\n <\/jats:sec>\n \n Principal Findings<\/jats:title>\n \n The sample consisted of 4,176,666 Medicare beneficiaries (mean [SD] age 74.9 [7.2] years, 55.9% women; 85.9% Non\u2010Hispanic white, 5.6% African\u2010American, 3.4% Hispanic). Franklin was more accurate than HCC (\n R<\/jats:italic>\n 2<\/jats:sup>\n log cost 0.44 vs. 0.15; Spearman rho 0.61 vs. 0.41,\n p<\/jats:italic>\n \u2009<\u20090.001 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;\n p<\/jats:italic>\n \u2009<\u20090.001 for both). Franklin outperformed HCC in detecting the 20% lowest\u2010cost beneficiaries (sensitivity 0.60 vs. 0.34, specificity 0.90 vs. 0.83;\n p<\/jats:italic>\n \u2009<\u20090.001 for both). Franklin improved accuracy over HCC for racial\/ethnic minorities and rural\u2010dwelling beneficiaries (\n R<\/jats:italic>\n 2<\/jats:sup>\n log cost Black 0.48 vs. 0.14, Hispanic 0.55 vs. 0.09, rural 0.36 v. 0.11;\n p<\/jats:italic>\n \u2009<\u20090.001 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.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Franklin is an ML risk adjustment model that significantly improves risk\u2010adjustment 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.<\/jats:p>\n <\/jats:sec>","DOI":"10.1111\/1475-6773.70093","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T10:55:02Z","timestamp":1772967302000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare"],"prefix":"10.1111","volume":"61","author":[{"given":"Daniel K.","family":"Shenfeld","sequence":"first","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsay","family":"Warrenburg","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eli","family":"Silvert","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Guido","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maggie","family":"Makar","sequence":"additional","affiliation":[{"name":"Division of Computer Science & Engineering University of Michigan Ann Arbor Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3779-8653","authenticated-orcid":false,"given":"Karen","family":"Joynt Maddox","sequence":"additional","affiliation":[{"name":"Washington University School of Medicine St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amol S.","family":"Navathe","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi Bharat","family":"Parikh","sequence":"additional","affiliation":[{"name":"Emory University School of Medicine Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-5735","authenticated-orcid":false,"given":"Ezekiel J.","family":"Emanuel","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"e_1_2_11_2_1","unstructured":"CMS \u201cInnovation Center Strategy Refresh \u201d2021 https:\/\/www.cms.gov\/priorities\/innovation\/strategic\u2010direction\u2010whitepaper."},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhealeco.2019.05.005"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.12830"},{"key":"e_1_2_11_5_1","unstructured":"Duke \u201cModernizing Medicare Risk Adjustment and Performance Measurement \u201d2024 https:\/\/healthpolicy.duke.edu\/publications\/modernizing\u2010medicare\u2010risk\u2010adjustment\u2010and\u2010performance\u2010measurement."},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2020.01764"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2022.00916"},{"key":"e_1_2_11_8_1","volume-title":"Medicare Advantage in 2024: Enrollment Update and Key Trends","author":"Freed M.","year":"2024"},{"key":"e_1_2_11_9_1","unstructured":"\u201cParticipation Continues to Grow in CMS' Accountable Care Organization Initiatives in 2024 | CMS \u201daccessed November 6 2024 https:\/\/www.cms.gov\/newsroom\/press\u2010releases\/participation\u2010continues\u2010grow\u2010cms\u2010accountable\u2010care\u2010organization\u2010initiatives\u20102024."},{"key":"e_1_2_11_10_1","unstructured":"\u201cHistoric 21.3 Million People Choose ACA Marketplace Coverage | CMS \u201daccessed November 6 2024 https:\/\/www.cms.gov\/newsroom\/press\u2010releases\/historic\u2010213\u2010million\u2010people\u2010choose\u2010aca\u2010marketplace\u2010coverage."},{"key":"e_1_2_11_11_1","unstructured":"\u201c2023 Annual Report of the Boards of Trustees of the Federal Hospital Insurance and Federal Supplementary Medical Insurance Trust Funds \u201dhttps:\/\/www.cms.gov\/oact\/tr\/2023."},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhealeco.2016.01.007"},{"key":"e_1_2_11_13_1","unstructured":"\u201cMedicare & Medicaid Statistical Supplement | CMS \u201daccessed October 2 2025 https:\/\/www.cms.gov\/data\u2010research\/statistics\u2010trends\u2010and\u2010reports\/archives\/medicare\u2010medicaid\u2010statistical\u2010supplement."},{"key":"e_1_2_11_14_1","unstructured":"\u201c2024 Annual Report of the Boards of Trustees of the Federal Hospital Insurance and Federal Supplementary Medical Insurance Trust Funds.\u201d"},{"key":"e_1_2_11_15_1","unstructured":"\u201cNational Health Expenditure Data | CMS \u201daccessed October 2 2025 https:\/\/www.cms.gov\/data\u2010research\/statistics\u2010trends\u2010and\u2010reports\/national\u2010health\u2010expenditure\u2010data."},{"key":"e_1_2_11_16_1","unstructured":"\u201cReport to Congress: Risk Adjustment in Medicare Advantage \u201d2021 https:\/\/www.cms.gov\/files\/document\/report\u2010congress\u2010risk\u2010adjustment\u2010medicare\u2010advantage\u2010december\u20102021.pdf."},{"key":"e_1_2_11_17_1","unstructured":"A.Zink T. G.McGuire andS.Rose \u201cBalancing Fairness and Efficiency in Health Plan Payments \u201d2022 https:\/\/hai.stanford.edu\/sites\/default\/files\/2022\u201011\/HAI_Balancing%20Fairness%20and%20Efficiency%20in%20Health%20Plan%20Payments%20_v2.pdf."},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1111\/biom.13206"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1086\/716199"},{"key":"e_1_2_11_20_1","unstructured":"MedPAC \u201cMarch 2025 Report to the Congress: Medicare Payment Policy \u201d2025 319\u2013406 accessed December 15 2025 https:\/\/www.medpac.gov\/document\/march\u20102025\u2010report\u2010to\u2010the\u2010congress\u2010medicare\u2010payment\u2010policy\/."},{"key":"e_1_2_11_21_1","unstructured":"\u201cCMS Rolls Out Aggressive Strategy to Enhance and Accelerate Medicare Advantage Audits | CMS \u201daccessed September 26 2025 https:\/\/www.cms.gov\/newsroom\/press\u2010releases\/cms\u2010rolls\u2010out\u2010aggressive\u2010strategy\u2010enhance\u2010and\u2010accelerate\u2010medicare\u2010advantage\u2010audits."},{"key":"e_1_2_11_22_1","volume-title":"Risk Adjustment: Methodologies for Identifying Uncaptured Conditions","author":"Sun M.","year":"2025"},{"key":"e_1_2_11_23_1","volume-title":"Risk Adjustment in the Age of Artificial Intelligence","author":"Yacoubian C.","year":"2023"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167\u20106296(01)00086\u20108"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/hec.3178"},{"key":"e_1_2_11_26_1","unstructured":"Centers for Medicare & Medicaid Services \u201c2024 Medicare Advantage Ratebook and Prescription Drug Rate Information \u201daccessed November 6 2024 https:\/\/www.cms.gov\/medicare\/health\u2010plans\/medicareadvtgspecratestats\/ratebooks\u2010and\u2010supporting\u2010data\/1090981521\/2024."},{"key":"e_1_2_11_27_1","unstructured":"CMS \u201c2024 model software: ICD\u201010 mappings \u201d(2024). accessed February 19 2026 https:\/\/www.cms.gov\/medicare\/health\u2010plans\/medicareadvtgspecratestats\/risk\u2010adjustors\/2024\u2010model\u2010software\/icd\u201010\u2010mappings."},{"key":"e_1_2_11_28_1","unstructured":"CMS \u201cAnnouncement of Calendar Year (CY) 2024 Medicare Advantage (MA) Capitation Rates and Part C and Part D Payment Policies \u201d(2023) accessed February 19 2026."},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.11082"},{"key":"e_1_2_11_30_1","first-page":"755","volume-title":"Handbook of Health Economics","author":"Wynand P. M. M.","year":"2000"},{"key":"e_1_2_11_31_1","first-page":"691","volume-title":"Handbook of Health Economics","author":"Breyer F.","year":"2011"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10198\u2010024\u201001709\u20108"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax2342"},{"issue":"3","key":"e_1_2_11_34_1","first-page":"27","article-title":"More Accurate Racial and Ethnic Codes for Medicare Administrative Data","volume":"29","author":"Eicheldinger C.","year":"2008","journal-title":"Health Care Financing Review"},{"key":"e_1_2_11_35_1","unstructured":"\u201cAnnouncement of Calendar Year (CY) 2025 Medicare Advantage (MA) Capitation Rates and Part C and Part D Payment Policies \u201d2024."},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1377\/forefront.20250317.758292"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.120.006752"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1377\/forefront.20240423.744938"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamahealthforum.2025.2640"},{"key":"e_1_2_11_40_1","volume-title":"Graphics by Andrew. Exclusive | Insurers Pocketed $50 Billion From Medicare for Diseases No Doctor Treated","author":"Mollica C.","year":"2024"},{"key":"e_1_2_11_41_1","unstructured":"\u201cReport to the Congress: Medicare Payment Policy: Chapter\u00a012 the Medicare Advantage Program: Status Report \u201d2024 https:\/\/www.medpac.gov\/wp\u2010content\/uploads\/2024\/03\/Mar24_Ch12_MedPAC_Report_To_Congress_SEC\u20101.pdf."},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.08815"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1377\/forefront.20250203.949100"}],"container-title":["Health Services Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1475-6773.70093","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/1475-6773.70093","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1475-6773.70093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T07:03:23Z","timestamp":1780643003000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/1475-6773.70093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/1475-6773.70093"],"URL":"https:\/\/doi.org\/10.1111\/1475-6773.70093","archive":["Portico"],"relation":{},"ISSN":["0017-9124","1475-6773"],"issn-type":[{"value":"0017-9124","type":"print"},{"value":"1475-6773","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]},"assertion":[{"value":"2025-07-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-31","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70093"}}