Journal article · 2026 · Open access

Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection

Aawez Mansuri, Mohammadreza Chavoshi, Theo Dapamede, Wasif Bala, Beatrice Brown-Mulry, Rohan Isaac, Bardia Khosravi, Hanzhou Li, Frank Li, John Timothy Moon, Chad J. Robichaux, Dan I. G. Cohen-Addad and 4 more

npj Digital Medicine · Published 21 October 2026 · DOI 10.1038/s41746-026-03418-3

Open PDFView at the publisherCite this paper

In brief

“Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection” is a 2026 journal article by Aawez Mansuri and 15 co-authors, published in npj Digital Medicine. OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at npj Digital Medicine.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.02
References
26
Authors
16

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Mansuri, A., Chavoshi, M., Dapamede, T., Bala, W., Brown-Mulry, B., Isaac, R., Khosravi, B., Li, H., Li, F., Moon, J. T., Robichaux, C. J., Cohen-Addad, D. I. G., Salastekar, N. V., Newsome, J. M., Gichoya, J. W., & Trivedi, H. (2026). Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03418-3

MLA 9

Mansuri, Aawez, et al. “Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection.” npj Digital Medicine, 2026. https://doi.org/10.1038/s41746-026-03418-3.

Chicago

Mansuri, Aawez, Mohammadreza Chavoshi, Theo Dapamede, Wasif Bala, Beatrice Brown-Mulry, Rohan Isaac, Bardia Khosravi, et al. 2026. “Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection.” npj Digital Medicine. https://doi.org/10.1038/s41746-026-03418-3.

Harvard

Mansuri, A. et al. (2026) ‘Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection’, npj Digital Medicine. doi:10.1038/s41746-026-03418-3.

IEEE

A. Mansuri et al., “Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection,” npj Digital Medicine, 2026, doi: 10.1038/s41746-026-03418-3.

BibTeX

@article{mansuri2026multi,
  title     = {{Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection}},
  author    = {Mansuri, Aawez and Chavoshi, Mohammadreza and Dapamede, Theo and Bala, Wasif and Brown-Mulry, Beatrice and Isaac, Rohan and Khosravi, Bardia and Li, Hanzhou and Li, Frank and Moon, John Timothy and Robichaux, Chad J. and Cohen-Addad, Dan I. G. and Salastekar, Ninad V. and Newsome, Janice M. and Gichoya, Judy Wawira and Trivedi, Hari},
  journal   = {npj Digital Medicine},
  year      = {2026},
  doi       = {10.1038/s41746-026-03418-3},
  url       = {https://doi.org/10.1038/s41746-026-03418-3}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • pulmonary embolism
  • incidental pulmonary embolism
  • artificial intelligence detection
  • CT pulmonary angiography
  • contrast-enhanced CT
  • real-world performance
  • sensitivity and specificity
  • post-marketing surveillance

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Mansuri, A., Chavoshi, M., Dapamede, T., Bala, W., Brown-Mulry, B., Isaac, R., Khosravi, B., Li, H., Li, F., Moon, J. T., Robichaux, C. J., Cohen-Addad, D. I. G., Salastekar, N. V., Newsome, J. M., Gichoya, J. W., & Trivedi, H. (2026). Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism detection. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03418-3

How many times has this paper been cited?

1 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Aawez Mansuri, Mohammadreza Chavoshi, Theo Dapamede, Wasif Bala, Beatrice Brown-Mulry, Rohan Isaac, Bardia Khosravi, Hanzhou Li, Frank Li, John Timothy Moon, Chad J. Robichaux, Dan I. G. Cohen-Addad and 4 more.

What is the DOI of this paper?

10.1038/s41746-026-03418-3, permanently at https://doi.org/10.1038/s41746-026-03418-3. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.