Potential Impact of an Artificial Intelligence–based Mammography Triage Algorithm on Performance and Workload in a Population-based Screening Sample
Journal of Breast Imaging · 2025
DOI: 10.1093/jbi/wbae056 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Breast Imaging, 2025. Verfasst von Alyssa T Watanabe und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Keck School of Medicine, University of Southern California (USC), Los Angeles, CA, USA. Hauptthemen laut MEDLINE: Mass Screening, Artificial Intelligence, Mammography, Workload. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
Objective
To evaluate potential screening mammography performance and workload impact using a commercial artificial intelligence (AI)–based triage device in a population-based screening sample.
Methods
In this retrospective study, a sample of 2129 women who underwent screening mammograms were evaluated. The performance of a commercial AI-based triage device was compared with radiologists’ reports, actual outcomes, and national benchmarks using commonly used mammography metrics. Up to 5 years of follow-up examination results were evaluated in cases to establish benignity. The algorithm sorted cases into groups of “suspicious” and “low suspicion.” A theoretical workload reduction was calculated by subtracting cases triaged as “low suspicion” from the sample.
Results
At the default 93% sensitivity setting, there was significant improvement (P <.05) in the following triage simulation mean performance measures compared with actual outcome: 45.5% improvement in recall rate (13.4% to 7.3%; 95% CI, 6.2-8.3), 119% improvement in positive predictive value (PPV) 1 (5.3% to 11.6%; 95% CI, 9.96-13.4), 28.5% improvement in PPV2 (24.6% to 31.6%; 95% CI, 24.8-39.1), 20% improvement in sensitivity (83.3% to 100%; 95% CI, 100-100), and 7.2% improvement in specificity (87.2% to 93.5%; 95% CI, 92.4-94.5). A theoretical 62.5% workload reduction was possible. At the ultrahigh 99% sensitivity setting, a theoretical 27% workload reduction was possible. No cancers were missed by the algorithm at either sensitivity.
Conclusion
Artificial intelligence–based triage in this simulation demonstrated potential for significant improvement in mammography performance and predicted substantial theoretical workload reduction without any missed cancers.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Keck School of Medicine, University of Southern California (USC), Los Angeles, CA, USA.
- CureMetrix Incorporated, San Diego, CA, USA.
- Cornice Health Ventures, LLC, Miami Beach FL, USA.
- Department of Radiology, University of California San Diego (UCSD), La Jolla, CA, USA.
- Department of Breast Imaging, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
ORCID-Profile: Alyssa T Watanabe, Tara Retson, Ray C Mayo
Zitieren
APA
Watanabe, A. T., Vu, H., Chim, C. Y., Litt, A. W., Retson, T., & Mayo, R. C. (2025). Potential Impact of an Artificial Intelligence–based Mammography Triage Algorithm on Performance and Workload in a Population-based Screening Sample. Journal of Breast Imaging. https://doi.org/10.1093/jbi/wbae056
Vancouver
Watanabe AT, Vu H, Chim CY, Litt AW, Retson T, Mayo RC. Potential Impact of an Artificial Intelligence–based Mammography Triage Algorithm on Performance and Workload in a Population-based Screening Sample. Journal of Breast Imaging. 2025. doi:10.1093/jbi/wbae056
BibTeX
@article{Watanabe2025,
author = {Watanabe, Alyssa T and Vu, Hoanh and Chim, Chi Y and Litt, Andrew W and Retson, Tara and Mayo, Ray C},
title = {Potential Impact of an Artificial Intelligence–based Mammography Triage Algorithm on Performance and Workload in a Population-based Screening Sample},
journal = {Journal of Breast Imaging},
year = {2025},
doi = {10.1093/jbi/wbae056}
}
EUVIMED