An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study

Lisa Browning; Richard T Colling; Jon Oxley; Jacqueline Birks; Nasullah Khalid Alham; Stefano Malacrino; Chuer Zhang; Abhisek Ghosh; Rosalin Cooper; Monica Dolton; Margaret Horton; Juan A Retamero; Andrew Protheroe; Leila Bibi Ahmed; Nahida Banu; Anastasios Chatzitolios; Irini Danial; Samir Al-Hyassat; Bidisa Sinha; Pallavi Borkar; Pelvender Gill; Richard J Bryant; Jonathan Aning; Kieron White; Richard Scheffer; Ewart Stanislaus; James Crofts; David J Snead; Nasir Rajpoot; Kate Hutton; Davina Hewitt; Clare Dunstan; Rob Procter; Clare Verrill

doi:10.1038/s41746-026-02592-8

An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study

Lisa Browning
, Richard T Colling
, Jon Oxley
, Jacqueline Birks
, Nasullah Khalid Alham
, Stefano Malacrino
, Chuer Zhang
, Abhisek Ghosh
, Rosalin Cooper
, Monica Dolton
, Margaret Horton
, Juan A Retamero
, Andrew Protheroe
, Leila Bibi Ahmed
, Nahida Banu
, Anastasios Chatzitolios
, Irini Danial
, Samir Al-Hyassat
, Bidisa Sinha
, Pallavi Borkar

Pelvender Gill, Richard J Bryant, Jonathan Aning, Kieron White, Richard Scheffer, Ewart Stanislaus, James Crofts, David J Snead, Nasir Rajpoot, Kate Hutton, Davina Hewitt, Clare Dunstan, Rob Procter, Clare Verrill

Oxford University Hospitals NHS Foundation Trust
University of Oxford
Department of Cellular Pathology, North Bristol NHS Trust, Bristol, UK.
Paige. AI Ltd, New York, NY, USA.
University Hospitals Coventry and Warwickshire NHS Trust
Bristol Urological Institute
University of Bristol
University of Warwick
Alan Turing Institute for Data Science and AI

Research output: Contribution to journal › Article › peer-review

Abstract

Prospective evidence on clinical utility of AI in histopathology is limited. We conducted a prospective study across three National Health Service specialist centres in England to evaluate a commercially available AI system for assistance in prostate biopsy reporting. Of 1613 cases, 1049 were reported with AI-assistance. Endpoints evaluated diagnostic impact, clinical impact and workflow. Staged AI assistance (second-read) prompted case review and changed the initial diagnosis or Grade Group of 21/386(5.4%) patients, 5 of these (1.3%) potentially affecting clinical management. AI-assisted workflows showed significantly reduced mean turnaround time with concurrent-read compared to unassisted-read by 30.1 h (p < 0.0001) at one site with significant reductions in cases requiring immunohistochemistry in all sites (Odds Ratios 0.50,0.43,0.33, p < 0.0001, p = 0.01, p = 0.001). This first prospective, multi-centric evaluation demonstrates AI can enhance diagnostic accuracy, shorten turnaround times and reduce unnecessary testing. Scaled across the NHS, such improvements could improve patient care, deliver faster diagnoses and optimise laboratory efficiency, supporting adoption.

Original language	English
Article number	537
Journal	NPJ Digit Med
Volume	9
Issue number	1
DOIs	https://doi.org/10.1038/s41746-026-02592-8
Publication status	Published - 22 May 2026
Externally published	Yes

Access to Document

10.1038/s41746-026-02592-8Licence: CC BY

Cite this

Browning, L., Colling, R. T., Oxley, J., Birks, J., Alham, N. K., Malacrino, S., Zhang, C., Ghosh, A., Cooper, R., Dolton, M., Horton, M., Retamero, J. A., Protheroe, A., Ahmed, L. B., Banu, N., Chatzitolios, A., Danial, I., Al-Hyassat, S., Sinha, B., ... Verrill, C. (2026). An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study. NPJ Digit Med, 9(1), Article 537. https://doi.org/10.1038/s41746-026-02592-8

@article{b3efc3a66be94648a00d0d77c140f3a0,

title = "An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study",

abstract = "Prospective evidence on clinical utility of AI in histopathology is limited. We conducted a prospective study across three National Health Service specialist centres in England to evaluate a commercially available AI system for assistance in prostate biopsy reporting. Of 1613 cases, 1049 were reported with AI-assistance. Endpoints evaluated diagnostic impact, clinical impact and workflow. Staged AI assistance (second-read) prompted case review and changed the initial diagnosis or Grade Group of 21/386(5.4\%) patients, 5 of these (1.3\%) potentially affecting clinical management. AI-assisted workflows showed significantly reduced mean turnaround time with concurrent-read compared to unassisted-read by 30.1 h (p < 0.0001) at one site with significant reductions in cases requiring immunohistochemistry in all sites (Odds Ratios 0.50,0.43,0.33, p < 0.0001, p = 0.01, p = 0.001). This first prospective, multi-centric evaluation demonstrates AI can enhance diagnostic accuracy, shorten turnaround times and reduce unnecessary testing. Scaled across the NHS, such improvements could improve patient care, deliver faster diagnoses and optimise laboratory efficiency, supporting adoption.",

author = "Lisa Browning and Colling, \{Richard T\} and Jon Oxley and Jacqueline Birks and Alham, \{Nasullah Khalid\} and Stefano Malacrino and Chuer Zhang and Abhisek Ghosh and Rosalin Cooper and Monica Dolton and Margaret Horton and Retamero, \{Juan A\} and Andrew Protheroe and Ahmed, \{Leila Bibi\} and Nahida Banu and Anastasios Chatzitolios and Irini Danial and Samir Al-Hyassat and Bidisa Sinha and Pallavi Borkar and Pelvender Gill and Bryant, \{Richard J\} and Jonathan Aning and Kieron White and Richard Scheffer and Ewart Stanislaus and James Crofts and Snead, \{David J\} and Nasir Rajpoot and Kate Hutton and Davina Hewitt and Clare Dunstan and Rob Procter and Clare Verrill",

note = "{\textcopyright} 2026. The Author(s).",

year = "2026",

month = may,

day = "22",

doi = "10.1038/s41746-026-02592-8",

language = "English",

volume = "9",

journal = "NPJ Digit Med",

issn = "2398-6352",

number = "1",

}

Browning, L, Colling, RT, Oxley, J, Birks, J, Alham, NK, Malacrino, S, Zhang, C, Ghosh, A, Cooper, R, Dolton, M, Horton, M, Retamero, JA, Protheroe, A, Ahmed, LB, Banu, N, Chatzitolios, A, Danial, I, Al-Hyassat, S, Sinha, B, Borkar, P, Gill, P, Bryant, RJ, Aning, J, White, K, Scheffer, R, Stanislaus, E, Crofts, J, Snead, DJ, Rajpoot, N, Hutton, K, Hewitt, D, Dunstan, C, Procter, R & Verrill, C 2026, 'An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study', NPJ Digit Med, vol. 9, no. 1, 537. https://doi.org/10.1038/s41746-026-02592-8

TY - JOUR

T1 - An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study

AU - Browning, Lisa

AU - Colling, Richard T

AU - Oxley, Jon

AU - Birks, Jacqueline

AU - Alham, Nasullah Khalid

AU - Malacrino, Stefano

AU - Zhang, Chuer

AU - Ghosh, Abhisek

AU - Cooper, Rosalin

AU - Dolton, Monica

AU - Horton, Margaret

AU - Retamero, Juan A

AU - Protheroe, Andrew

AU - Ahmed, Leila Bibi

AU - Banu, Nahida

AU - Chatzitolios, Anastasios

AU - Danial, Irini

AU - Al-Hyassat, Samir

AU - Sinha, Bidisa

AU - Borkar, Pallavi

AU - Gill, Pelvender

AU - Bryant, Richard J

AU - Aning, Jonathan

AU - White, Kieron

AU - Scheffer, Richard

AU - Stanislaus, Ewart

AU - Crofts, James

AU - Snead, David J

AU - Rajpoot, Nasir

AU - Hutton, Kate

AU - Hewitt, Davina

AU - Dunstan, Clare

AU - Procter, Rob

AU - Verrill, Clare

PY - 2026/5/22

Y1 - 2026/5/22

N2 - Prospective evidence on clinical utility of AI in histopathology is limited. We conducted a prospective study across three National Health Service specialist centres in England to evaluate a commercially available AI system for assistance in prostate biopsy reporting. Of 1613 cases, 1049 were reported with AI-assistance. Endpoints evaluated diagnostic impact, clinical impact and workflow. Staged AI assistance (second-read) prompted case review and changed the initial diagnosis or Grade Group of 21/386(5.4%) patients, 5 of these (1.3%) potentially affecting clinical management. AI-assisted workflows showed significantly reduced mean turnaround time with concurrent-read compared to unassisted-read by 30.1 h (p < 0.0001) at one site with significant reductions in cases requiring immunohistochemistry in all sites (Odds Ratios 0.50,0.43,0.33, p < 0.0001, p = 0.01, p = 0.001). This first prospective, multi-centric evaluation demonstrates AI can enhance diagnostic accuracy, shorten turnaround times and reduce unnecessary testing. Scaled across the NHS, such improvements could improve patient care, deliver faster diagnoses and optimise laboratory efficiency, supporting adoption.

AB - Prospective evidence on clinical utility of AI in histopathology is limited. We conducted a prospective study across three National Health Service specialist centres in England to evaluate a commercially available AI system for assistance in prostate biopsy reporting. Of 1613 cases, 1049 were reported with AI-assistance. Endpoints evaluated diagnostic impact, clinical impact and workflow. Staged AI assistance (second-read) prompted case review and changed the initial diagnosis or Grade Group of 21/386(5.4%) patients, 5 of these (1.3%) potentially affecting clinical management. AI-assisted workflows showed significantly reduced mean turnaround time with concurrent-read compared to unassisted-read by 30.1 h (p < 0.0001) at one site with significant reductions in cases requiring immunohistochemistry in all sites (Odds Ratios 0.50,0.43,0.33, p < 0.0001, p = 0.01, p = 0.001). This first prospective, multi-centric evaluation demonstrates AI can enhance diagnostic accuracy, shorten turnaround times and reduce unnecessary testing. Scaled across the NHS, such improvements could improve patient care, deliver faster diagnoses and optimise laboratory efficiency, supporting adoption.

UR - https://www.scopus.com/pages/publications/105044525328

U2 - 10.1038/s41746-026-02592-8

DO - 10.1038/s41746-026-02592-8

M3 - Article

C2 - 42174106

SN - 2398-6352

VL - 9

JO - NPJ Digit Med

JF - NPJ Digit Med

IS - 1

M1 - 537

ER -

An evaluation of artificial intelligence assisted prostate biopsy reporting in the Articulate Pro study

Abstract

Access to Document

Other files and links

Fingerprint

Cite this