Assessing a Biomarker’s Ability to Reduce Invasive Procedures in Patients With Benign Lung Nodules: Results From the Oracle Study

Michael A. Pritchett , Barry Sigal, Mark R. Bowling, Jonathan S. Kurman, Trevor Pitcher, Steven C. Springmeyer , for the ORACLE Study Investigators


A blood-based integrated classifier (IC) has been clinically validated to improve accuracy in assessing probability of cancer risk (pCA) for pulmonary nodules (PN). This study evaluated the clinical utility of this biomarker for its ability to reduce invasive procedures in patients with pre-test pCA ≤ 50%. This was a propensity score matching (PSM) cohort study comparing patients in the ORACLE prospective, multicenter, observational registry to control patients treated with usual care. This study enrolled patients meeting the intended use criteria for IC testing: pCA ≤ 50%, age ≥40 years, nodule diameter 8–30 mm, and no history of lung cancer and/or active cancer (except for non-melanomatous skin cancer) within 5 years.


With the increasing use of chest computed tomography (CT) for a myriad of clinical indications, pulmonary nodules (PNs) have become an increasingly common clinical problem encountered by clinicians. By current estimates, over 1.5 million lung nodules are detected in the United States (US) annually and the evaluation of nodules represents a significant burden to the healthcare system [1].

Material and methods

The prospective ORACLE observational research registry (October 2018 to March 2020) is a multicenter cohort assembled to evaluate the impact of an IC on physician decision-making when used in the clinical management of a recently identified PNs with Mayo SPN pCA ≤ 50% as compared to a historical control population from the same institutions. A total of 15 community and academic pulmonary practices covering a wide geographic area participated in the study and the institutional review boards at each site or centrally approved the study. Written consent was obtained from all eligible patients and patient follow-up was continued until all eligible patients had completed at least one year.


Of the 197 IC group patients evaluated with the IC test, 162 (82%) were benign and 35 (18%) were malignant. Following testing, 37% (72/197) of patients were classified as “Likely Benign” by the IC test, resulting in 92% (66/72) of patients with a Likely Benign result being reclassified to <5% pCA category from the 5–65% pCA risk category (Fig 3). Additionally, of the 72 patients with a Likely Benign test result, 89% (64/72) were directed to CT surveillance as the next action.


Lung nodules often pose a diagnostic challenge for clinicians. When presented with a newly observed nodule, the goal of the clinician is to avoid invasive procedures in those nodules that are ultimately found to be benign, and in those nodules that are malignant, move patients towards treatment with curative intent without delay. The decision on management is usually based on physician or model derived pre-test pCA, the local availability and expertise of the imaging test or procedure, and patient preference [2, 16]. In most cases it is recommended that those with a low pCA (< 5%) be followed with CT surveillance for 2 years to confirm benignity and those with a high pCA (> 65%) undergo biopsy and surgical resection. In the group in between (pCA 5% - 65%) further testing with either PET scan, bronchoscopy or TTNB is recommended. By current estimates ~84% of PN’s fall into this intermediate range where the tools and invasive procedures to aid in distinguishing benign from malignant disease have remained largely unchanged for at least the last decade [17].


The authors thank James R. Jett MD for reviewing the manuscript. Additionally, the authors thank Stat4ward LLC. Pittsburgh, PA, for providing the statistical analysis.

Citation: Pritchett MA, Sigal B, Bowling MR, Kurman JS, Pitcher T, Springmeyer SC, et al. (2023) Assessing a biomarker’s ability to reduce invasive procedures in patients with benign lung nodules: Results from the ORACLE study. PLoS ONE 18(7): e0287409.

Editor: Ming-Ching Lee, Taichung Veterans General Hospital, TAIWAN

Received: February 13, 2023; Accepted: June 5, 2023; Published: July 11, 2023

Copyright: © 2023 Pritchett et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All relevant data are within the manuscript and its Supporting Information files.

Funding: MAP, BS, MRB and JSK are study investigators in the Biodesix ( sponsored study ORACLE. Biodesix Inc funded and sponsored the ORACLE (NCT03766958) observational registry study. TP and SCS are employees of Biodesix inc. The sponsor was involved in the design of the study, data collection and analysis, decision to publish and preparation of the manuscript.

Competing interests: The authors have reported the following: M.A.P. discloses immediate family member employment (Medtronic, Philips), honoraria (Medtronic, Philips, Astra Zeneca), consulting (Medtronic, Philips, Intuitive, Johnson & Johnson, Pfizer, Noah Medical), research funding (Medtronic, Philips, Biodesix, Inc.), speaker’s bureau (Johnson & Johnson, United Therapeutics, Biodesix, Inc.), and travel/accommodations/expenses (Intuitive, Johnson & Johnson, Astra Zeneca, Pfizer, Noah Medical). B S. reports nothing to disclose. M.R. B. discloses consulting (Medtronic). J.S.K. discloses consulting/advisory (Ambu, Biodesix, Inc., Boston Scientific, Cook, Intuitive, Level Ex, Medtronic, Pulmonx), research funding (Lung Therapeutics, PrognomiQ), honoraria (Pinnacle Biologics), speaker’s bureau (Biodesix, Inc., Veracyte), stock ownership (Doximity), and travel/accommodations/expenses (Auris, Pinnacle Biologics). T.P. reports employment (Biodesix, Inc.). S.C.S. reports employment and leadership (Biodesix, Inc.). There are no patents or products in development associated with this research to declare. The IC (Nodify XL2) is marketed by Biodesix, Inc. in Boulder, Colorado. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

National Healthcare CMO Summit USANational Healthcare CNO Summit USA