Microfluidic-Based Analysis of Trichomonas Vaginalis Attachment and Drug Response Using AI-Based Imaging Algorithm

Area of Science:

• Parasitology
• Biotechnology
• Infectious Diseases

Background:

• Trichomonas vaginalis causes the most common non-viral sexually transmitted infection globally.
• Rising drug resistance necessitates novel therapeutic evaluation methods.
• Current drug screening methods lack efficiency for complex parasitic interactions.

Purpose of the Study:

• To develop and validate a microfluidic culture platform integrated with AI for assessing T. vaginalis drug efficacy.
• To quantify parasite attachment dynamics under various drug treatments.
• To evaluate the efficacy of single and combination therapies against T. vaginalis.

Main Methods:

• Development of a microfluidic platform for controlled T. vaginalis exposure to host cells (HeLa, BFTC905).
• Integration of an AI-based imaging algorithm for real-time parasite attachment quantification.
• Application of spatial color-coded map analysis for drug gradient assessment.

Main Results:

• Metronidazole significantly reduced T. vaginalis attachment in a dose-dependent manner.
• Combination therapy (metronidazole and paromomycin) demonstrated superior inhibitory effects compared to single drugs.
• The microfluidic-AI system provided robust and reproducible results across different cell lines.

Conclusions:

• Combination therapy holds promise for managing T. vaginalis infections due to potential synergistic interactions.
• The microfluidic-AI system is a valuable tool for high-throughput anti-parasitic drug screening and development.
• This technology advances therapeutic evaluation for sexually transmitted infections.