A mobile based antimicrobial susceptibility testing device - prototype development and validation

Area of Science:

• Medical Microbiology
• Digital Health
• Antimicrobial Resistance

Background:

• Antimicrobial resistance (AMR) poses a significant global health threat.
• Multidrug-resistant pathogens necessitate innovative diagnostic solutions.
• Smartphone technology offers potential for digitizing antimicrobial susceptibility testing (AST).

Purpose of the Study:

• To develop and validate an in-house, semi-automated smartphone application for AST measurement and interpretation.
• To assess the accuracy and reliability of the app in comparison to manual methods.

Main Methods:

• An in-house app was developed using an AI-assisted coding workflow.
• A digital calibration algorithm correlated pixel dimensions with millimeters.
• AST was performed using the Kirby-Bauer disk diffusion method on Escherichia coli and Staphylococcus aureus isolates.
• Zone diameters were measured manually and by the app, with subsequent interpretation using CLSI guidelines.

Main Results:

• The app demonstrated high categorical agreement (90.4%) with manual AST interpretation.
• Unweighted Cohen's Kappa was 0.836, indicating substantial agreement.
• Major error rates were below 1% (0.83%), with no very major errors, supporting safety for resistance detection.

Conclusions:

• The developed smartphone app provides reliable interpretation of AST results.
• It offers a user-friendly and safe alternative for resistance detection.
• This digital approach is suitable for routine use in busy, resource-limited settings.