This system supports diagnosis in bacterial infectious diseases.
Although it is important to accurately identify bacterial species and prescribe appropriate antimicrobial agents at an early stage of a bacterial infection, this is often not conducted because it is time-consuming to identify bacterial species by culture tests and so on without equipment (usually very
expensive) such as mass spectrometers. Hence, it relies on the experience of physicians and technicians (empiric therapy) and the antibiotics may be prescribed inappropriately. .
This lack of proper diagnosis and inappropriate prescription of antibiotics is one of the causes of antibiotics resistance (AMR: Antimicrobial Resistance).
BiTTE is an application that solves these problems by using AI image analysis technology to accurately estimate bacterial species, and by supporting the selection of appropriate antimicrobial agents in conjunction with antibiograms (antimicrobial susceptibility charts).
A smartphone is attached to an optical microscope via an attachment. Gram-stained images are captured with the smartphone’s camera. By uploading the image to the cloud, the results of the bacterial species estimation and the candidate antimicrobial agents to be prescribed are presented.
For the estimation of bacterial species, an image recognition AI model is built based on the gram-stained images of approximately 10,000 urine specimens from 1,000 cases and the bacterial species identification result of culture tests.
With regard to antibiotics suggestions, the system also displays information on spectrum scores, WHO’s AWaRe classification, and over-the-counter drugs information to enable
selection of more narrow-spectrum antibiotics.
Specimens are currently limited to urine, but will be expanded to blood and sputum in the future.
The system is also used in conjunction with medical equipment (under development) that automates the staining process in order to maintain consistent specimen staining quality and stabilize diagnostic imaging accuracy.
・Citations and References
Diagnosing bacterial infections using smartphones” Nature