Clinical evaluation of the APAS® Independence: Automated imaging and interpretation of urine cultures using artificial intelligence with composite reference standard discrepant resolution.

This study reports the outcome of the first evaluation of the APAS® Independence for automated reading and preliminary interpretation of urine cultures in the routine clinical microbiology laboratory. In a 2-stage evaluation involving 3000 urine samples, two objectives were assessed; 1) the sensitivity and specificity of the APAS® Independence compared to microbiologists using colony enumeration as the primary determinant, and 2) the variability between microbiologists in enumerating bacterial cultures using traditional culture reading techniques, performed independently to APAS® Independence interpretation.

When evaluating new technologies with an evidence and risk-based approach, clinical sensitivity is a key determinant for procurement and implementation. In this study the clinical sensitivity availed by full implementation option with LIS integration and use of custom flags was 0.998 which indicates the risk of false negatives is extremely low and should provide confidence in the clinical performance of the technology. However, other strategic considerations are also important when laboratories assess the need for implementing new technologies, such as availability of specialist microbiology staff, reducing workload and manual handling, and the benefits of process standardization and optimisation.

Journal: Journal of Microbiological Methods

Date: October 2020

Authors: Brenton L, Waters M.J, Stanford T, Giglio S.

Citation: Brenton, L, Waters, M.J, Stanford, T, Giglio, S,. 2020. Evaluation of an image analysis device (APAS) for screening urine cultures. Journal of Microbiological Methods p.106047

doi: 10.1016/J.mimet.2020.106047.