AI Enhances Lung Ultrasound Interpretation Across Clinicians with Varying Expertise Levels
Diagnostics · 25.08.2025 · 15 (17) · 2145
DOI: 10.3390/diagnostics15172145 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 25.08.2025. Verfasst von Seyed Ehsan Seyed Bolouri und 7 weiteren Autor:innen. Beteiligte Einrichtung: Exo Imaging, Santa Clara, CA 95054, USA. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Exo.
Abstract (Originalsprache)
Background/Objective: Lung ultrasound (LUS) is a valuable tool for detecting pulmonary conditions, but its accuracy depends on user expertise. This study evaluated whether an artificial intelligence (AI) tool could improve clinician performance in detecting pleural effusion and consolidation/atelectasis on LUS scans.
Methods
In this multi-reader, multi-case study, 14 clinicians of varying experience reviewed 374 retrospectively selected LUS scans (cine clips from the PLAPS point, obtained using three different probes) from 359 patients across six centers in the U.S. and Canada. In phase one, readers scored the likelihood (0–100) of pleural effusion and consolidation/atelectasis without AI. After a 4-week washout, they re-evaluated all scans with AI-generated bounding boxes. Performance metrics included area under the curve (AUC), sensitivity, specificity, and Fleiss’ Kappa. Subgroup analyses examined effects by reader experience.
Results
For pleural effusion, AUC improved from 0.917 to 0.960, sensitivity from 77.3% to 89.1%, and specificity from 91.7% to 92.9%. Fleiss’ Kappa increased from 0.612 to 0.774. For consolidation/atelectasis, AUC rose from 0.870 to 0.941, sensitivity from 70.7% to 89.2%, and specificity from 85.8% to 89.5%. Kappa improved from 0.427 to 0.756.
Conclusions
AI assistance enhanced clinician detection of pleural effusion and consolidation/atelectasis in LUS scans, particularly benefiting less experienced users.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Exo Imaging, Santa Clara, CA 95054, USA.
- Department of Critical Care Medicine, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, AB T6G 2B7, Canada.
- Department of Radiology and Diagnostic Imaging, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, AB T6G 2R3, Canada.
- Alameda Health System, Highland Hospital, University of California San Francisco, San Francisco, CA 94143, USA.
- Department of Diagnostic Imaging, National University of Singapore, Singapore 119074, Singapore.
ORCID-Profile: Seyed Ehsan Seyed Bolouri, Jacob L Jaremko
Förderung
- Exo
Zitieren
APA
Seyed Bolouri, S. E., Dehghan, M., Nekoui, M., Buchanan, B., Jaremko, J. L., Zonoobi, D., Nagdev, A., & Kapur, J. (2025). AI Enhances Lung Ultrasound Interpretation Across Clinicians with Varying Expertise Levels. Diagnostics, 15(17), 2145. https://doi.org/10.3390/diagnostics15172145
Vancouver
Seyed Bolouri SE, Dehghan M, Nekoui M, Buchanan B, Jaremko JL, Zonoobi D, et al. AI Enhances Lung Ultrasound Interpretation Across Clinicians with Varying Expertise Levels. Diagnostics. 2025;15(17):2145. doi:10.3390/diagnostics15172145
BibTeX
@article{SeyedBolouri2025,
author = {Seyed Bolouri, Seyed Ehsan and Dehghan, Masood and Nekoui, Mahdiar and Buchanan, Brian and Jaremko, Jacob L and Zonoobi, Dornoosh and Nagdev, Arun and Kapur, Jeevesh},
title = {AI Enhances Lung Ultrasound Interpretation Across Clinicians with Varying Expertise Levels},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {17},
pages = {2145},
doi = {10.3390/diagnostics15172145}
}
EUVIMED