Abstract Rationale The diagnosis of interstitial lung disease (ILD) requires a multidisciplinary discussion (MDD), in which high-resolution computed tomography (HRCT) and histopathology play key roles. Genomic classifiers have recently been introduced for clinical use, in which lung tissue obtained via transbronchial forceps biopsy undergoes whole-transcriptome RNA sequencing followed by gene expression analysis. These molecular tools are particularly valuable in establishing a diagnosis of idiopathic pulmonary fibrosis (IPF) in patients without a definite usual interstitial pneumonia (UIP) pattern on imaging. Although genomic classifiers are increasingly utilized in clinical practice, data on their diagnostic performance continue to evolve, warranting an updated analysis of the current evidence. Methods A systematic review and meta-analysis were conducted in accordance with PRISMA guidelines. Comprehensive search of PubMed, MEDLINE, Embase, Scopus and the Cochrane Library were performed through October 2025 using predefined terms including “genomic classifier,” “Envisia,” “UIP,” and “interstitial lung disease.” Eligible studies were which enrolled adult patients with ILD of uncertain etiology in whom genomic classifiers were compared with histopathologic or MDD based reference standards. True positive, false positive, false negative, and true negative data were extracted to calculate pooled estimates of sensitivity, specificity and the area under the receiver-operating characteristic curve (AUROC) using a random-effects bivariate model. Results Six studies comprising 347 patients met inclusion criteria, with sample sizes ranging from 24 to 98 participants. Across studies, sensitivity ranged from 59% to 85% and specificity from 75% to 100%. The pooled sensitivity was 68% (95% CI, 60-76%; P 0.001) and specificity 77% (95% CI, 70-85%; P 0.001), with an estimated AUROC of 0.73 (95% CI, 0.65-0.81) indicating discriminative performance. In two studies evaluating clinical impact, incorporation of genomic classifier data into MDD increased diagnostic confidence in ILD subtyping by 30-50%. No major adverse events related to transbronchial tissue acquisition were reported. Conclusions Genomic classifiers represent a promising, less invasive adjunct for identifying UIP patterns in ILD, demonstrating good overall diagnostic accuracy. Incorporating classifier results within MDD frameworks enhances diagnostic confidence and may reduce the need for surgical lung biopsy in appropriately selected patients. However, small study sizes, potential funding bias and limited accessibility highlight the need for larger, independently conducted prospective studies to further define their role in future IPF diagnostic algorithms. This abstract is funded by: None
Singh et al. (2026) studied this question.