AI triage of duodenal biopsies improves workflow.
Artificial intelligence triage cut coeliac disease biopsy reporting time from 10 to 6 days.
AI triage of duodenal biopsies improves workflow.
To develop, deploy and evaluate artificial intelligence (artificial intelligence) for triaging duodenal biopsies within a National Health Service (National Health Service) histopathology laboratory, with the aim of improving reporting turnaround times for clinically significant diagnoses.
The pathway was developed in the UK in an National Health Service laboratory.
Artificial intelligence triage reported coeliac disease biopsies faster than routine reporting
313 cases (517 duodenal slides) were processed by the routine pathway, and 329 cases (533 duodenal slides) were processed by the artificial intelligence triage pathway.
Artificial intelligence processing took about 70 s per slide.
The artificial intelligence classifier had a sensitivity and positive predictive value (positive predictive value) as follows: normal small bowel: 99.6%, 95.7%; coeliac disease: 86.7%, 100%; gastric heterotopia: 84.6%, 95.7%; adenoma: 88.9%, 88.9%; adenocarcinoma: 50.0%, 100%.
The cost of deployment and operation was reasonable.
An National Health Service histopathology laboratory successfully developed and implemented an artificial intelligence-based triage system for duodenal biopsies, achieving high diagnostic accuracy and significantly improving turnaround times for coeliac disease and non-neoplastic abnormalities as a group.
This study demonstrates the feasibility and clinical value of locally developed artificial intelligence tools within routine diagnostic practice.