Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases

Area of Science:

• Medical Microbiology
• Computational Pathology
• Infectious Diseases

Background:

• Infectious diseases pose a significant global health challenge, particularly in resource-limited regions.
• Accurate and timely microbial identification is crucial for effective patient and public health management.
• Current manual microscopic examination for microbe identification is labor-intensive and requires specialized expertise.

Purpose of the Study:

• To systematically review the application of artificial intelligence (AI) in the identification of microorganisms from pathology specimens.
• To assess the efficacy and scope of AI-based methods in microbiological diagnostics.
• To identify trends and challenges in the adoption of AI for microbial detection.

Main Methods:

• A systematic literature search was conducted across electronic databases for studies on AI applications in pathology microbiology.
• 110 studies were included from 4596 retrieved articles.
• Analysis focused on AI applications for malaria, bacteria, nematodes, and other protozoa, primarily using cytological images from microscopes and smartphones.

Main Results:

• AI applications were most prominent in malaria (54 studies), followed by bacteria (28), nematodes (14), and other protozoa (11).
• The majority of studies (86%) analyzed cytological material, with images captured via microscope cameras (59%) or smartphones (15%).
• Deep learning strategies demonstrated highly satisfactory results in analyzing digital images for microorganism detection.

Conclusions:

• Artificial intelligence shows reliable potential for assisting pathologists in microorganism detection.
• Further technological advancements and accessible training datasets are essential for broader AI adoption, especially in developing countries.
• AI can significantly improve diagnostic accuracy and efficiency in infectious disease management.