Related Experiment Video
Updated: Jul 15, 2026

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules
Published on: October 13, 2023
Recent advances in artificial intelligence across interventional pulmonology: a narrative review
Shaheen Rizly1, Anthony Saleh1,2, Keerthana Keshava1,2
1Department of Medicine, New York Presbyterian Brooklyn Methodist Hospital, Brooklyn, NY, USA.
Artificial intelligence (AI) shows promise in interventional pulmonology (IP) for improving lung cancer screening, bronchoscopy, and pleural disease management. However, AI applications require further validation for widespread clinical adoption.
Area of Science:
- Interventional Pulmonology
- Medical Artificial Intelligence
- Diagnostic Imaging
Background:
- Artificial intelligence (AI) is increasingly integrated into interventional pulmonology (IP).
- The clinical utility of AI in IP is still evolving, transitioning from technical development to practical patient benefit.
- Key AI subtypes like machine learning (ML), deep learning (DL), and radiomics are being explored across various IP domains.
Purpose of the Study:
- To review the current evidence on AI applications in interventional pulmonology.
- To examine the roles of ML, DL, and radiomics in major IP areas.
- To assess the transition of AI innovations into tangible clinical benefits.
Main Methods:
- A comprehensive literature search was conducted across major scientific databases (PubMed/MEDLINE, Embase, Web of Science, Scopus, ScienceDirect, Google Scholar).
- Studies published between April 2006 and January 2026 were included, encompassing preclinical, retrospective, prospective, and translational research.
- Findings were qualitatively synthesized due to the heterogeneity of study designs and AI methodologies.
Main Results:
- AI enhances lung cancer screening (nodule detection, risk stratification) and radiomics aids in lesion characterization and staging.
- AI improves bronchoscopy (airway interpretation, navigation) and endobronchial ultrasound (EBUS) (lymph node characterization, ROSE).
- AI tools aid pleural disease diagnosis and therapeutic interventions like bronchoscopic lung volume reduction (BLVR), but most applications remain investigational.
Conclusions:
- AI demonstrates significant potential to advance diagnosis and procedural guidance in interventional pulmonology.
- Prospective multicenter validation, standardized data, workflow integration, and cost-effectiveness studies are crucial for routine clinical utility.
- Current AI in IP should be considered a supportive tool for interventional pulmonologists, not a replacement.
Related Concept Videos
Cardiopulmonary Resuscitation V: Advanced Airway Management Techniques
Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Chronic Obstructive Pulmonary Disease-V: Management
Smoking Cessation
Chronic Obstructive Pulmonary Disease-I: Introduction
Pulmonary Embolism I: Introduction