Literature DB >> 33188949

Random survival forests using linked data to measure illness burden among individuals before or after a cancer diagnosis: Development and internal validation of the SEER-CAHPS illness burden index.

Lisa M Lines1, Julia Cohen2, Justin Kirschner2, Michael T Halpern3, Erin E Kent4, Michelle A Mollica3, Ashley Wilder Smith3.   

Abstract

PURPOSE: To develop and internally validate an illness burden index among Medicare beneficiaries before or after a cancer diagnosis.
METHODS: Data source: SEER-CAHPS, linking Surveillance, Epidemiology, and End Results (SEER) cancer registry, Medicare enrollment and claims, and Medicare Consumer Assessment of Healthcare Providers and Systems (Medicare CAHPS) survey data providing self-reported sociodemographic, health, and functional status information. To generate a score for everyone in the dataset, we tabulated 4 groups within each annual subsample (2007-2013): 1) Medicare Advantage (MA) beneficiaries or 2) Medicare fee-for-service (FFS) beneficiaries, surveyed before cancer diagnosis; 3) MA beneficiaries or 4) Medicare FFS beneficiaries surveyed after diagnosis. Random survival forests (RSFs) predicted 12-month all-cause mortality and drew predictor variables (mean per subsample = 44) from 8 domains: sociodemographic, cancer-specific, health status, chronic conditions, healthcare utilization, activity limitations, proxy, and location-based factors. Roughly two-thirds of the sample was held out for algorithm training. Error rates based on the validation ("out-of-bag," OOB) samples reflected the correctly classified percentage. Illness burden scores represented predicted cumulative mortality hazard.
RESULTS: The sample included 116,735 Medicare beneficiaries with cancer, of whom 73 % were surveyed after their cancer diagnosis; overall mean mortality rate in the 12 months after survey response was 6%. SEER-CAHPS Illness Burden Index (SCIBI) scores were positively skewed (median range: 0.29 [MA, pre-diagnosis] to 2.85 [FFS, post-diagnosis]; mean range: 2.08 [MA, pre-diagnosis] to 4.88 [MA, post-diagnosis]). The highest decile of the distribution had a 51 % mortality rate (range: 29-71 %); the bottom decile had a 1% mortality rate (range: 0-2 %). The error rate was 20 % overall (range: 9% [among FFS enrollees surveyed after diagnosis] to 36 % [MA enrollees surveyed before diagnosis]).
CONCLUSIONS: This new morbidity measure for Medicare beneficiaries with cancer may be useful to future SEER-CAHPS users who wish to adjust for comorbidity.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Cancer registry data; Claims data; Morbidity; Mortality; Random survival forests; Survey data

Mesh:

Year:  2020        PMID: 33188949      PMCID: PMC7736519          DOI: 10.1016/j.ijmedinf.2020.104305

Source DB:  PubMed          Journal:  Int J Med Inform        ISSN: 1386-5056            Impact factor:   4.046


  39 in total

1.  Disability and Medicare costs of elderly persons.

Authors:  K Liu; S Wall; D Wissoker
Journal:  Milbank Q       Date:  1997       Impact factor: 4.911

2.  Can comorbidity be measured by questionnaire rather than medical record review?

Authors:  J N Katz; L C Chang; O Sangha; A H Fossel; D W Bates
Journal:  Med Care       Date:  1996-01       Impact factor: 2.983

3.  Novel head and neck cancer survival analysis approach: random survival forests versus Cox proportional hazards regression.

Authors:  Frank R Datema; Ana Moya; Peter Krause; Thomas Bäck; Lars Willmes; Ton Langeveld; Robert J Baatenburg de Jong; Henk M Blom
Journal:  Head Neck       Date:  2011-02-14       Impact factor: 3.147

4.  Antidepressant use: concordance between self-report and claims records.

Authors:  Anne Kwon; Kathleen M Bungay; Yu Pei; William H Rogers; Ira B Wilson; Qi Zhou; David A Adler
Journal:  Med Care       Date:  2003-03       Impact factor: 2.983

5.  All-cause 1-, 5-, and 10-year mortality in elderly people according to activities of daily living stage.

Authors:  Margaret G Stineman; Dawei Xie; Qiang Pan; Jibby E Kurichi; Zi Zhang; Debra Saliba; John T Henry-Sánchez; Joel Streim
Journal:  J Am Geriatr Soc       Date:  2012-02-21       Impact factor: 5.562

6.  An outcome prediction model for patients with clear cell renal cell carcinoma treated with radical nephrectomy based on tumor stage, size, grade and necrosis: the SSIGN score.

Authors:  Igor Frank; Michael L Blute; John C Cheville; Christine M Lohse; Amy L Weaver; Horst Zincke
Journal:  J Urol       Date:  2002-12       Impact factor: 7.450

Review 7.  Assessment of comorbidities in surgical oncology outcomes.

Authors:  Parul Sinha; Dorina Kallogjeri; Jay F Piccirillo
Journal:  J Surg Oncol       Date:  2014-08-06       Impact factor: 3.454

8.  The Cancer of the Bladder Risk Assessment (COBRA) score: Estimating mortality after radical cystectomy.

Authors:  Christopher J Welty; Thomas H Sanford; Jonathan L Wright; Peter R Carroll; Matthew R Cooperberg; Maxwell V Meng; Sima P Porten
Journal:  Cancer       Date:  2017-09-07       Impact factor: 6.860

9.  Upcoding: Evidence from Medicare on Squishy Risk Adjustment.

Authors:  Michael Geruso; Timothy Layton
Journal:  J Polit Econ       Date:  2020-01-29

10.  Risk adjustment of Medicare capitation payments using the CMS-HCC model.

Authors:  Gregory C Pope; John Kautter; Randall P Ellis; Arlene S Ash; John Z Ayanian; Lisa I Lezzoni; Melvin J Ingber; Jesse M Levy; John Robst
Journal:  Health Care Financ Rev       Date:  2004
View more
  1 in total

1.  Associations between illness burden and care experiences among Medicare beneficiaries before or after a cancer diagnosis.

Authors:  Lisa M Lines; Julia Cohen; Justin Kirschner; Daniel H Barch; Michael T Halpern; Erin E Kent; Michelle A Mollica; Ashley Wilder Smith
Journal:  J Geriatr Oncol       Date:  2022-03-07       Impact factor: 3.929

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.