Journal Article

Evaluating the pathological and clinical implications of errors made by an artificial intelligence colon biopsy screening tool

Snead, David, Patel, Abhilasha, Sivakumar, Naveen, Graham, Simon, Bhanderi, Shivam, Robinson, Andrew, Evans, Harriet

2025

Overview

ObjectiveArtificial intelligence (AI) tools for histological diagnosis offer great potential to healthcare, yet failure to understand their clinical context is delaying adoption. IGUANA (Interpretable Gland-Graphs using a Neural Aggregator) is an AI algorithm that can effectively classify colonic biopsies into normal versus abnormal categories, designed to automatically report normal cases. We performed a retrospective pathological and clinical review of the errors made by IGUANA.MethodsFalse negative (FN) errors were the primary focus due to the greatest propensity for harm. Pathological evaluation involved assessment of whole slide image (WSI) quality, precise diagnoses for each missed entity and identification of factors impeding diagnosis. Clinical evaluation scored the impact of each error on the patient and detailed the type of impact in terms of missed diagnosis, investigations or treatment.ResultsAcross 5054 WSIs from 2080 UK National Health Service patients there were 220 FN errors across 164 cases (4.4% of WSI, 7.9% of cases). Diagnostic errors varied from cases of adenocarcinoma to mild inflammation. 88.4% of FN errors would have no impact on patient care, with only one error causing major patient harm. Factors that protected against harm included biopsies being low-risk polyps or diagnostic features were detected in other biopsies.ConclusionMost FN errors would not result in patient harm, suggesting that even with a 7.9% case-level error rate, this AI tool might be more suitable for adoption than statistics portray. Consideration of the clinical context of AI tool errors is essential to facilitate safe implementation.

• Publisher: BMJ Publishing Group Ltd,BMJ Publishing Group LTD,BMJ Publishing Group
• Subject: Adenocarcinoma - diagnosis / Adenocarcinoma - pathology / Adult / Aged / Algorithms / Artificial Intelligence / Automation / Biopsy / Biopsy - methods / Biopsy - statistics & numerical data / Colon / Colon - pathology / Colonoscopy - methods / Colonoscopy - statistics & numerical data / Colorectal Disease / COLORECTAL DISEASES / COLORECTAL PATHOLOGY / COMPUTERISED IMAGE ANALYSIS / Datasets / Diagnostic Errors - prevention & control / Diagnostic Errors - statistics & numerical data / Early Detection of Cancer - methods / False Negative Reactions / Female / Humans / Male / Middle Aged / Morbidity / Mortality / Original Research / Pathology / Patients / Retrospective Studies / Surveillance / United Kingdom - epidemiology