Abstract
Purpose
We sought to develop and validate an incident non-small cell lung cancer (NSCLC) algorithm for United States (US) healthcare claims data. Diagnoses and procedures, but not medications, were incorporated to support longer-term relevance and reliability.
Methods
Patients with newly diagnosed NSCLC per Surveillance, Epidemiology, and End Results (SEER) served as cases. Controls included newly diagnosed small-cell lung cancer and other lung cancers, and two 5% random samples for other cancer and without cancer. Algorithms derived from logistic regression and machine learning methods used the entire sample (Approach A) or started with a previous algorithm for those with lung cancer (Approach B). Sensitivity, specificity, positive predictive values (PPV), negative predictive values, and F-scores (compared for 1000 bootstrap samples) were calculated. Misclassification was evaluated by calculating the odds of selection by the algorithm among true positives and true negatives.
Results
The best performing algorithm utilized neural networks (Approach B). A 10-variable point-score algorithm was derived from logistic regression (Approach B); sensitivity was 77.69% and PPV = 67.61% (F-score = 72.30%). This algorithm was less sensitive for patients ≥80 years old, with Medicare follow-up time <3 months, or missing SEER data on stage, laterality, or site and less specific for patients with SEER primary site of main bronchus, SEER summary stage 2000 regional by direct extension only, or pre-index chronic pulmonary disease.
Conclusion
Our study developed and validated a practical, 10-variable, point-based algorithm for identifying incident NSCLC cases in a US claims database based on a previously validated incident lung cancer algorithm.
Data Sharing Statement
The dataset used for the current study is not publicly available due to SEER-Medicare Data Use Agreement restrictions. However, researchers may obtain access to SEER-Medicare data by submitting a proposal (details for submitting proposals are available at https://healthcaredelivery.cancer.gov/seermedicare/obtain/).
Ethics Statement
The protocol was reviewed and considered exempt by Quorum Review IRB prior to National Cancer Institute approval of the SEER‐Medicare data for this study.
Acknowledgments
The authors thank Elaine Yanisko of IMS, Inc. for support in triaging data-related questions with staff at the National Cancer Institute, Shannon Gardell and Colleen Dumont of Evidera for their expert writing and editorial reviews of the manuscript, and Yushi Liu of Eli Lilly and Company for statistical peer review. For feasibility analysis and creating the analytic dataset, the authors thank Tim Ellington of Delisle Associates LTD. For validation of analytic programs, the authors thank Jessica Mitroi of Eli Lilly and Company. For quality review of the final manuscript, the authors thank Nancy Hedlund of MedNavigate LLC. .JB and DRN are joint senior authors for this study.
Author Contributions
All authors made a significant contribution to the work reported, whether that is in the conception, study design, execution, acquisition of data, analysis and interpretation, or in all these areas; took part in drafting, revising or critically reviewing the article; gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agree to be accountable for all aspects of the work.
Disclosure
JB, DRN, KMS, and YJH are employees and shareholders of Eli Lilly and Company. YKL was an employee of Eli Lilly and Company during the conduct of the study. ALH is an employee of the University of Cincinnati and reports grants from Eli Lilly during the conduct of the study. The authors report no other conflicts of interest in this work.