商业AI用于肺栓塞检测的多中心真实世界表现研究
Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection
本研究回顾性评估了17家学术医疗中心中Aidoc平台两款FDA批准AI算法的真实世界表现,包括肺动脉CT血管造影筛查(n=30,678)和常规增强CT incidental肺栓塞检测(n=37,191)。
- Article
- Open access
- Published: 21 October 2026
- Aawez Mansuri ORCID: orcid.org/0009-0006-7017-43581 na1,
- Mohammadreza Chavoshi1 na1,
- Theodorus Dapamede ORCID: orcid.org/0000-0002-6264-22821,
- Wasif Bala1,
- Beatrice Brown-Mulry1,
- Rohan Satya Isaac1,
- Bardia Khosravi2,
- Hanzhou Li1,
- Frank Li ORCID: orcid.org/0000-0002-8205-33971,
- John T. Moon1,
- Chad Robichaux3,
- Dan I. G. Cohen-Addad1,
- Ninad V. Salastekar1,
- Janice Newsome1,
- Judy W. Gichoya ORCID: orcid.org/0000-0002-1097-316X1 &
- …
- Hari Trivedi1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Pulmonary embolism (PE) is a leading cause of cardiovascular mortality, yet the real-world performance of FDA-cleared AI detection models remains incompletely characterized. We retrospectively evaluated two FDA-cleared AI algorithms from a single commercial platform (Aidoc Medical BriefCase)—one for PE triage on dedicated CT pulmonary angiography (CTPA; n = 30,678) and one for incidental PE (iPE) detection on routine contrast-enhanced CTs (n = 37,191), across a 17-facility academic health system. Reference-standard labels were extracted from radiology reports using a validated LLM pipeline (97% accuracy, κ = 0.94). The PE model achieved 86.8% sensitivity and 99.1% specificity, with sensitivity declining from 99.3% for saddle emboli to 72.9% for subsegmental PE, and from 89.7% for acute to 65.3% for non-acute PE. The iPE model achieved 73.5% sensitivity and 99.8% specificity. Both models demonstrated lower sensitivity than FDA-clearance benchmarks while exceeding cleared specificity, with diminishing performance for peripheral and non-acute emboli mirroring known human reader limitations and underscoring the need for standardized post-market surveillance of AI-enabled medical devices.
Acknowledgements
The authors thank Aidoc Medical for providing the aggregated prediction outputs used in this analysis. Aidoc Medical had no role in the study design, data analysis, interpretation of results, or preparation of the manuscript.
Funding
The authors received no specific funding for this work.
Author information
Author notes
These authors contributed equally: Aawez Mansuri, Mohammadreza Chavoshi.
Authors and Affiliations
Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, USA
Aawez Mansuri, Mohammadreza Chavoshi, Theodorus Dapamede, Wasif Bala, Beatrice Brown-Mulry, Rohan Satya Isaac, Hanzhou Li, Frank Li, John T. Moon, Dan I. G. Cohen-Addad, Ninad V. Salastekar, Janice Newsome, Judy W. Gichoya & Hari Trivedi
Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA
Bardia Khosravi
Department of Biomedical Informatics, Emory University, Atlanta, GA, USA
Chad Robichaux
Authors
- Aawez Mansuri
- Mohammadreza Chavoshi
- Theodorus Dapamede
- Wasif Bala
- Beatrice Brown-Mulry
- Rohan Satya Isaac
- Bardia Khosravi
- Hanzhou Li
- Frank Li
- John T. Moon
- Chad Robichaux
- Dan I. G. Cohen-Addad
- Ninad V. Salastekar
- Janice Newsome
- Judy W. Gichoya
- Hari Trivedi
Corresponding author
Correspondence to Hari Trivedi.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Mansuri, A., Chavoshi, M., Dapamede, T. et al. Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03418-3
Received: 26 March 2026
Accepted: 05 October 2026
Published: 21 October 2026
DOI: https://doi.org/10.1038/s41746-026-03418-3
来源:Nature 健康护理主题 · nature.com