Literature DB >> 31070985

Classifying Stage IV Lung Cancer From Health Care Claims: A Comparison of Multiple Analytic Approaches.

Gabriel A Brooks1, Savannah L Bergquist2, Mary Beth Landrum3, Sherri Rose3, Nancy L Keating3.   

Abstract

PURPOSE: Cancer stage is a key determinant of outcomes; however, stage is not available in claims-based data sources used for real-world evaluations. We compare multiple methods for classifying lung cancer stage from claims data.
METHODS: Our study used the linked SEER-Medicare data. The patient samples included fee-for-service Medicare beneficiaries diagnosed with lung cancer from 2010 to 2011 (development cohort) and 2012 to 2013 (validation cohort) who received chemotherapy. Classification algorithms considered Medicare Part A and B claims for care in the 3 months before and after chemotherapy initiation. We developed a clinical algorithm to predict stage IV (v I to III) cancer on the basis of treatment patterns (surgery, radiotherapy, chemotherapy). We also considered an ensemble of claims-based machine learning algorithms. Classification methods were trained in the development cohort, and performance was measured in both cohorts. The SEER data were the gold standard for cancer stage.
RESULTS: Development and validation cohorts included 14,760 and 14,620 patients with lung cancer, respectively. Validation analyses assessed clinical, random forest, and simple logistic regression algorithms. The best performing classifier within the development cohort was the random forests, but this performance was not replicated in validation analysis. Logistic regression had stable performance across cohorts. Compared with the clinical algorithm, the 14-variable logistic regression algorithm demonstrated higher accuracy in both the development (77% v 71%) and validation cohorts (77% v 73%), with improved specificity for stage IV disease.
CONCLUSION: Machine learning algorithms have potential to improve lung cancer stage classification but may be prone to overfitting. Use of ensembles, cross-validation, and external validation can aid generalizability. Degradation of accuracy between development and validation cohorts suggests the need for caution in implementing machine learning in research or care delivery.

Entities:  

Mesh:

Year:  2019        PMID: 31070985      PMCID: PMC6873980          DOI: 10.1200/CCI.18.00156

Source DB:  PubMed          Journal:  JCO Clin Cancer Inform        ISSN: 2473-4276


  15 in total

1.  Overview of the SEER-Medicare data: content, research applications, and generalizability to the United States elderly population.

Authors:  Joan L Warren; Carrie N Klabunde; Deborah Schrag; Peter B Bach; Gerald F Riley
Journal:  Med Care       Date:  2002-08       Impact factor: 2.983

2.  Super learner.

Authors:  Mark J van der Laan; Eric C Polley; Alan E Hubbard
Journal:  Stat Appl Genet Mol Biol       Date:  2007-09-16

3.  Limited validity of diagnosis codes in Medicare claims for identifying cancer metastases and inferring stage.

Authors:  Neetu Chawla; K Robin Yabroff; Angela Mariotto; Timothy S McNeel; Deborah Schrag; Joan L Warren
Journal:  Ann Epidemiol       Date:  2014-07-03       Impact factor: 3.797

4.  Pembrolizumab for the treatment of non-small-cell lung cancer.

Authors:  Edward B Garon; Naiyer A Rizvi; Rina Hui; Natasha Leighl; Ani S Balmanoukian; Joseph Paul Eder; Amita Patnaik; Charu Aggarwal; Matthew Gubens; Leora Horn; Enric Carcereny; Myung-Ju Ahn; Enriqueta Felip; Jong-Seok Lee; Matthew D Hellmann; Omid Hamid; Jonathan W Goldman; Jean-Charles Soria; Marisa Dolled-Filhart; Ruth Z Rutledge; Jin Zhang; Jared K Lunceford; Reshma Rangwala; Gregory M Lubiniecki; Charlotte Roach; Kenneth Emancipator; Leena Gandhi
Journal:  N Engl J Med       Date:  2015-04-19       Impact factor: 91.245

5.  Identification of metastatic cancer in claims data.

Authors:  Beth L Nordstrom; Joanna L Whyte; Marilyn Stolar; Catherine Mercaldi; Joel D Kallich
Journal:  Pharmacoepidemiol Drug Saf       Date:  2012-05       Impact factor: 2.890

6.  Centers for medicare and medicaid services: using an episode-based payment model to improve oncology care.

Authors:  Ronald M Kline; Carol Bazell; Erin Smith; Heidi Schumacher; Rahul Rajkumar; Patrick H Conway
Journal:  J Oncol Pract       Date:  2015-02-17       Impact factor: 3.840

7.  An Evaluation of Algorithms for Identifying Metastatic Breast, Lung, or Colorectal Cancer in Administrative Claims Data.

Authors:  Joanna L Whyte; Nicole M Engel-Nitz; April Teitelbaum; Gabriel Gomez Rey; Joel D Kallich
Journal:  Med Care       Date:  2015-07       Impact factor: 2.983

8.  Potential for cancer related health services research using a linked Medicare-tumor registry database.

Authors:  A L Potosky; G F Riley; J D Lubitz; R M Mentnech; L G Kessler
Journal:  Med Care       Date:  1993-08       Impact factor: 2.983

9.  Durvalumab after Chemoradiotherapy in Stage III Non-Small-Cell Lung Cancer.

Authors:  Scott J Antonia; Augusto Villegas; Davey Daniel; David Vicente; Shuji Murakami; Rina Hui; Takashi Yokoi; Alberto Chiappori; Ki H Lee; Maike de Wit; Byoung C Cho; Maryam Bourhaba; Xavier Quantin; Takaaki Tokito; Tarek Mekhail; David Planchard; Young-Chul Kim; Christos S Karapetis; Sandrine Hiret; Gyula Ostoros; Kaoru Kubota; Jhanelle E Gray; Luis Paz-Ares; Javier de Castro Carpeño; Catherine Wadsworth; Giovanni Melillo; Haiyi Jiang; Yifan Huang; Phillip A Dennis; Mustafa Özgüroğlu
Journal:  N Engl J Med       Date:  2017-09-08       Impact factor: 91.245

10.  Classifying Lung Cancer Severity with Ensemble Machine Learning in Health Care Claims Data.

Authors:  Savannah L Bergquist; Gabriel A Brooks; Nancy L Keating; Mary Beth Landrum; Sherri Rose
Journal:  Proc Mach Learn Res       Date:  2017-08
View more
  3 in total

1.  A Systematic Review of Estimating Breast Cancer Recurrence at the Population Level With Administrative Data.

Authors:  Hava Izci; Tim Tambuyzer; Krizia Tuand; Victoria Depoorter; Annouschka Laenen; Hans Wildiers; Ignace Vergote; Liesbet Van Eycken; Harlinde De Schutter; Freija Verdoodt; Patrick Neven
Journal:  J Natl Cancer Inst       Date:  2020-10-01       Impact factor: 13.506

2.  First-Line Pharmacotherapies and Survival among Patients Diagnosed with Non-Resectable NSCLC: A Real-Life Setting Study with Gender Prospective.

Authors:  Andrea Spini; Rosa Gini; Pietro Rosellini; Allison Singier; Cristiana Bellan; Alessandra Pascucci; Lorenzo Leoncini; Clément Mathieu; Ignazio Martellucci; Folco Furiesi; Silvano Giorgi; Sandra Donnini; Giuseppe Roberto; Marina Ziche; Francesco Salvo
Journal:  Cancers (Basel)       Date:  2021-12-05       Impact factor: 6.639

3.  Uncertainty in lung cancer stage for survival estimation via set-valued classification.

Authors:  Savannah Bergquist; Gabriel A Brooks; Mary Beth Landrum; Nancy L Keating; Sherri Rose
Journal:  Stat Med       Date:  2022-06-08       Impact factor: 2.497

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.