Skip to main content

ORIGINAL RESEARCH article

Front. Oncol.
Sec. Thoracic Oncology
Volume 14 - 2024 | doi: 10.3389/fonc.2024.1358562
This article is part of the Research Topic Applications of AI, Machine Learning, Computational Medicine, and Bioinformatics in Respiratory Pharmacology View all 3 articles

Development of an Algorithm to Identify Small Cell Lung Cancer Patients in Claims Databases

Provisionally accepted
Mark Danese Mark Danese 1*Akhila Balasubramanian Akhila Balasubramanian 2Gwyn Bebb Gwyn Bebb 2Xerxes Pundole Xerxes Pundole 2
  • 1 Outcomes Insights, Inc., Calabasas, United States
  • 2 Amgen (United States), Thousand Oaks, California, United States

The final, formatted version of the article will be published soon.

    1.1 Introduction The treatment landscape of small cell lung cancer (SCLC) is evolving. Evidence generated from administrative claims is needed to characterize real-world SCLC patients. However, the current ICD-10 coding system cannot distinguish SCLC from non-small cell lung cancer (NSCLC). We developed and estimated the accuracy of an algorithm to identify SCLC in claims-only databases. 1.2 Methods We performed a cross-sectional study of lung cancer patients diagnosed from 2016-2017 using the Surveillance, Epidemiology and End Results (SEER), linked with Medicare database. The analysis included two phases – data exploration (utilizing a 25% random sample) and data validation (remaining 75% sample). The SEER definition of SCLC and NSCLC were used as the gold standard. Claims-based algorithms were identified and evaluated for their sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). 1.3 Results The eligible cohort included 31,912 lung cancer patients. The mean age was 76.3 years, 44.6% were male, with 9.4% having SCLC and 90.6% identified as NSCLC using SEER. The exploration analysis identified potential algorithms based on treatment data. In the validation analysis of 7,438 lung cancer patients who received systemic treatment in the outpatient setting, an etoposide-based algorithm (etoposide use in 180 days following lung cancer diagnosis) to identify SCLC showed: sensitivity 95%, specificity 95%, PPV 82% and NPV 99%. 1.4 Discussion An etoposide treatment-based algorithm showed good accuracy in identifying SCLC patients. Such algorithms can facilitate analyses of treatment patterns, outcomes, healthcare resource and costs among treated SCLC patients, thereby bolstering the evidence-base for best patient care.

    Keywords: Small Cell Lung Cancer, algorithm, Claims, Medicare, Immunotherapy

    Received: 20 Dec 2023; Accepted: 29 Jul 2024.

    Copyright: © 2024 Danese, Balasubramanian, Bebb and Pundole. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Mark Danese, Outcomes Insights, Inc., Calabasas, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.