Automated reading of values from a breath sample analyser: development and validation of a vision-language model–based image analysis pipeline

Key Points

• This research aims to develop and validate an image analysis pipeline for breath sample analysers.
• Developed a vision-language model-based pipeline for image analysis.
• Validated the accuracy and efficiency of the AI model in reading breath samples.
• Demonstrated that the automated system reduces the time required for transcription.
• Showed improved accuracy in recording results compared to manual methods.