Radiologic usual interstitial pneumonia (UIP) patterns and concordant clinical characteristics define a diagnosis of idiopathic pulmonary fibrosis (IPF). However, limited expert access and high inter-clinician variability challenge early and pre-invasive diagnostic sensitivity and differentiation of IPF from other interstitial lung diseases (ILDs). We investigated a machine learning-driven software system, Fibresolve, to indicate IPF diagnosis in a heterogeneous group of 300 patients with interstitial lung disease work-up in a retrospective analysis of previously and prospectively collected registry data from two US clinical sites. Fibresolve analyzed cases at the initial pre-invasive assessment. An Expert Clinical Panel (ECP) and three panels of clinicians with varying experience analyzed the cases for comparison. Ground Truth was defined by separate multi-disciplinary discussion (MDD) with the benefit of surgical pathology results and follow-up. Fibresolve met both pre-specified co-primary endpoints of sensitivity superior to ECP and significantly greater specificity (p = 0.0007) than the non-inferior boundary of 80.0%. In the key subgroup of cases with thin-slice CT and atypical UIP patterns (n = 124), Fibresolve’s diagnostic yield was 53.1% [CI: 41.3–64.9] (versus 0% pre-invasive clinician diagnostic yield in this group), and its specificity was 85.9% [CI: 76.7–92.6%]. Overall, Fibresolve was found to increase the sensitivity and diagnostic yield for IPF among cases of patients undergoing ILD work-up. These results demonstrate that in combination with standard clinical assessment, Fibresolve may serve as an adjunct in the diagnosis of IPF in a pre-invasive setting.
27 May 2022 in Journal of Bronchology & Interventional Pulmonology
Background: Endobronchial ultrasound–guided transbronchial needle aspiration (EBUS-TBNA) has become standard for the diagnosis of lung cancer, and there is an increasing need for procedural competence in trainees. We evaluate a low-cost, gelatin-based EBUS-TBNA training simulator to assess pulmonary fellows’ baseline skills and facilitate procedural development. Methods: A low-cost ($30) gelatin-based, high-fidelity simulator was created to represent the airways, major vessels, and lymph node stations essential to identify for EBUS-TBNA. Trainees had a baseline skills assessment using the simulator and were then provided a 1-hour didactic session on EBUS-TBNA and additional practice time with the simulator. Trainees then underwent a postsimulation skills assessment using a modified endobronchial ultrasound (EBUS)-Skills and Tasks Assessment Tool (STAT) performance assessment tool. Simulator fidelity and trainee procedural confidence was assessed using a 10-point scale. Results: Ten fellows received training on the EBUS-TBNA simulator. First-year trainees scored the lowest on the 18-point performance scale with a mean score of 9, while third-year trainees scored highest with a mean score of 17.5. Mean 18-point performance score improvement after simulator training and didactics was 4.31 points for all trainees with the largest change in first-year trainees amounting to 8.25 points. First-year trainees experienced the greatest improvement in EBUS procedural confidence by a mean of 2.5 points on a 10-point confidence survey. Conclusion: A low-cost EBUS simulator effectively differentiated early and advanced learners based on graded procedural performance scores. Simulation-based practice significantly improved learners’ procedural performance, and the degree of improvement correlated with learner inexperience. The simulation significantly increased early learner confidence in EBUS-TBNA technique.