Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis: A comparative paired reader analysis
Journal of Pathology Informatics · 2026-11 · 23 · 100748
DOI: 10.1016/j.jpi.2026.100748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Pathology Informatics, 2026-11. Verfasst von J Parry und 10 weiteren Autor:innen. Beteiligte Einrichtung: Healius Limited, Western Diagnostic Pathology, Perth, Australia. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: AstraZeneca.
Abstract (Originalsprache)
Evidence on the real-world impact of artificial intelligence (AI) decision support on diagnostic efficiency and workflow outcomes in primary breast cancer pathology remains limited. This retrospective, single-site, paired reader, two-arm study evaluated the impact of AI-assisted digital pathology (DP + AI) versus standard DP on workflow efficiency and diagnostic performance in digitized consecutive breast biopsy cases. Primary endpoints were pathologist review time, lab turnaround time (TAT), and usability (survey-based). Secondary endpoints included diagnostic performance of pathologists across both arms and standalone AI against adjudicated reference standard. Analyses included descriptive statistics, paired t-test, and diagnostic performance metrics with 95% confidence intervals (CIs). The study included 194 digitized breast biopsies. The mean pathologist overall review time was reduced by 43.5% in DP + AI (40.18 [95% CI: 36.20-44.16] s) versus DP (71.12 [95% CI: 64.39-77.84] s) (p < 0.0001). Diagnostic agreement was 97.42% with DP and 99.48% with DP + AI, with 100% sensitivity observed in the DP + AI workflow. The standalone AI showed high diagnostic accuracy, with area under the curve values ≥0.99 across cancer subtypes. Usability survey showed high satisfaction, ease of use, and perceived clinical utility. Baseline TAT analysis of 3298 cases, independent of study cohort, showed longer TAT for cases requiring immunohistochemistry (IHC; 3.73 days) than for those not requiring (1.17 days). Retrospective workflow modelling suggested that AI-guided IHC pre-ordering could potentially reduce TAT by approximately 2.5 days for patients. DP + AI showed improvements in workflow efficiency while maintaining diagnostic performance. These findings suggest that integration of AI into routine breast pathology workflows may support faster diagnosis, optimized laboratory operations, and improved scalability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Healius Limited, Western Diagnostic Pathology, Perth, Australia.
- Healius Limited, Brisbane, Australia.
- AstraZeneca, Cambridge, United Kingdom.
- AstraZeneca, Dubai, United Arab Emirates.
- Ibex Medical Analytics, Tel Aviv, Israel.
- Ibex Medical Analytics, Boston, MA, USA.
Förderung
- AstraZeneca
Zitieren
APA
Parry, J., Jindal, S., Blackmur, T., Channathodiyil, P., Raiber-Moreau, E. A., Lee, J., Mevorach, D., Mallel, G., Broderick, R., Ambrogio, S., & Vecsler, M. (2026). Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis: A comparative paired reader analysis. Journal of Pathology Informatics, 23, 100748. https://doi.org/10.1016/j.jpi.2026.100748
Vancouver
Parry J, Jindal S, Blackmur T, Channathodiyil P, Raiber-Moreau EA, Lee J, et al. Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis: A comparative paired reader analysis. Journal of Pathology Informatics. 2026;23:100748. doi:10.1016/j.jpi.2026.100748
BibTeX
@article{Parry2026,
author = {Parry, J and Jindal, S and Blackmur, T and Channathodiyil, P and Raiber-Moreau, E-A and Lee, J and Mevorach, D and Mallel, G and Broderick, R and Ambrogio, S and Vecsler, M},
title = {Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis: A comparative paired reader analysis},
journal = {Journal of Pathology Informatics},
year = {2026},
volume = {23},
pages = {100748},
doi = {10.1016/j.jpi.2026.100748}
}
EUVIMED