MedPath

Biomarker Platform (Virtual Nodule Clinic) for the Management of Indeterminate Pulmonary Nodules

Not Applicable
Recruiting
Conditions
Lung Neoplasm
Registration Number
NCT06638398
Lead Sponsor
Vanderbilt-Ingram Cancer Center
Brief Summary

This clinical trial studies whether a biomarker platform, the Virtual Nodule Clinic, can be used for the management of lung (pulmonary) nodules that are not clearly non-cancerous (benign) or clearly cancerous (malignant) (indeterminate pulmonary nodules \[IPNs\]). The management of IPNs is based on estimating the likelihood that the observed nodule is malignant. Many things, such as age, smoking history, and current symptoms, are considered when making a prediction of the likelihood of malignancy. Radiographic imaging characteristics are also considered. Lung nodule management for IPNs can result in unnecessary invasive procedures for nodules that are ultimately determined to be benign, or potential delays in treatment when results of tests cannot be determined or are falsely negative. The Virtual Nodule Clinic is an artificial intelligence (AI) based imaging software within the electronic health record which makes certain that identified pulmonary nodules are screened by clinicians with expertise in nodule management. The Virtual Nodule Clinic also features an AI based radiomic prediction score which designates the likelihood that a pulmonary nodule is malignant. This may improve the ability to manage IPNs and lower unnecessary invasive procedures or treatment delays. Using the Virtual Nodule Clinic may work better for the management of IPNs.

Detailed Description

PRIMARY OBJECTIVES:

I. To test the hypothesis that usual care plus a radiomic prediction score impacts patient management compared to usual care alone.

II. To conduct a multicenter pragmatic randomized controlled platform trial using a validated biomarker, the radiomic prediction score.

III. To conduct a biomarker study that will evaluate the first necessary (but not sufficient) step to show clinical utility.

IV. To assess the magnitude of change in patient management with use of the radiomic prediction score.

V. To develop a platform that can be used as framework for future larger biomarker studies.

OUTLINE: Patients are randomized to 1 of 2 arms.

ARM I: Patients undergo standard of care (SOC) computed tomography (CT) evaluation and receive a Virtual Nodule Clinic radiomic prediction score on study. Patients then receive SOC lung nodule management on study.

ARM II: Patients undergo SOC CT evaluation on study. Patients then receive SOC lung nodule management on study.

Recruitment & Eligibility

Status
RECRUITING
Sex
All
Target Recruitment
400
Inclusion Criteria
  • Adults 35-year-old and older with undiagnosed IPN(s) 8-30mm referred for evaluation

    • Referral includes direct in-basket messages in the electronic healthcare record (EHR) to study providers, telehealth visits or clinic visit
    • For multiple nodules, we will obtain the score from the dominant or most suspicious nodule based on providers or radiologist impression
  • Available CT scan with slice thickness of 3 mm or less with the nodule of interest present. Nodules identified during screening low dose computed tomography of the chest (LDCT) that have had a conventional, follow-up CT performed are eligible for inclusion

Exclusion Criteria
  • Pure ground glass nodule
  • Patients known to be a prisoners
  • Patients known to be pregnant
  • Known active malignancy within the last 5 years at time of enrollment (excluding non-melanoma skin cancers)
  • More than 5 IPNs present on imaging
  • Nodules referred after initial LDCT for screening with only one LDCT available. The Lung Cancer Prediction Convolutional Neural Network (LCP CNN) algorithm is not currently validated for screening studies
  • Thoracic implants that impact the image appearance of the nodule
  • Clinician determines that use of the LCP CNN model is required or contraindicated for the optimal care of the patient

Study & Design

Study Type
INTERVENTIONAL
Study Design
PARALLEL
Primary Outcome Measures
NameTimeMethod
Appropriate nodule managementUp to 1 Year

Will be defined as referral for imaging surveillance for ultimately benign nodules, and biopsy, positron emission tomography scan, surgery or empiric stereotactic body radiation therapy for malignant nodules. Standard consort diagram will be created. Descriptive statistics including means, standard deviations, and median and interquartile ranges for continuous parameters, as well as percentages and frequencies for categorical parameters will be presented. Will compare the proportion with appropriate management across the two arms using a two-sided Z-test of proportions with pooled variances.

Secondary Outcome Measures
NameTimeMethod
Change in managementUp to 2 years

Change in management Will be based on intervention probability curve (IPC) assessment. Standard consort diagram will be created. Descriptive statistics including means, standard deviations, and median and interquartile ranges for continuous parameters, as well as percentages and frequencies for categorical parameters will be presented. Will fit an intervention probability curve to both arms independently, using the method described by Kammer et al., by using the bootstrap-resample-with-dither approach. Then, will test the hypothesis that the slope of the IPC in the intervention arm is different from the slope of the IPC in the control arm by using the analysis of covariance, with a significance level of 0.05.

Unnecessary invasive proceduresUp to 2 years

Unnecessary invasive procedures Will be defined as: 1) invasive procedure with definite benign findings on biopsy or 2) non-diagnostic findings on biopsy but stable follow up imaging, evaluated over two years of follow-up. Standard consort diagram will be created. Descriptive statistics including means, standard deviations, and median and interquartile ranges for continuous parameters, as well as percentages and frequencies for categorical parameters will be presented. Any invasive procedures will be compared across arms using a two-sided Z-test with pooled variances.

Time to diagnosis in patients with malignant nodulesFrom the time of expert provider evaluation to the time of final diagnosis in days, assessed up to 2 years

Standard consort diagram will be created. Descriptive statistics including means, standard deviations, and median and interquartile ranges for continuous parameters, as well as percentages and frequencies for categorical parameters will be presented. Will be compared across arms using a logrank test

Trial Locations

Locations (1)

Vanderbilt University/Ingram Cancer Center

🇺🇸

Nashville, Tennessee, United States

© Copyright 2025. All Rights Reserved by MedPath