Algorithms for immunochromatographic assay: review and impact on future application

Area of Science:

• Biomedical Engineering
• Analytical Chemistry
• Computational Biology

Background:

• Lateral flow immunoassay (LFIA) is a versatile tool for point-of-care testing (POCT).
• Traditional analytical methods for LFIA face limitations with small data quantities and hardware constraints.
• Signal and image processing strategies have been developed to enhance LFIA sensitivity.

Purpose of the Study:

• To review artificial intelligence (AI) and machine learning (ML) models for LFIA detection.
• To highlight signal processing strategies utilizing AI and ML in LFIA.
• To discuss the application and future research directions of AI and deep learning in LFIA technology.

Main Methods:

• Review of existing literature on AI, ML, and deep learning applied to LFIA.
• Analysis of signal and image processing techniques for LFIA data.
• Focus on analytical mechanisms, procedural flow, and assay results.

Main Results:

• AI and deep learning offer advanced solutions for LFIA detection, improving accuracy.
• These technologies address limitations of traditional methods and hardware.
• Various AI/ML models show potential for enhanced LFIA performance.

Conclusions:

• AI and deep learning are promising for advancing LFIA in POCT.
• Further research is needed to fully explore the potential and address limitations.
• Integration of AI/ML can lead to more reliable and sensitive diagnostic tools.