AI Revolutionizes Parasite Detection, Promising Faster, More Accurate Diagnoses
Table of Contents
A new artificial intelligence (AI) tool is poised to transform the diagnosis of intestinal parasitic infections globally, offering a significantly faster and more accurate method for identifying parasites in stool samples than traditional microscopic analysis. The breakthrough, developed by scientists at ARUP Laboratories, utilizes a deep-learning model – specifically a convolutional neural network (CNN) – to automate a process historically reliant on the expertise of highly trained specialists.
The painstaking task of manually examining stool samples for parasite cysts, eggs, or larva has long been a bottleneck in diagnostic labs. Now, according to a study published Tuesday in the Journal of Clinical Microbiology, the AI system achieves a comparable level of precision with dramatically increased speed.
“It has been a groundbreaking effort, and what we’ve accomplished is remarkable,” stated Blaine Mathison, ARUP’s technical director of parasitology and an adjunct lecturer in the University of Utah’s Department of Pathology. “Our validation studies have demonstrated the AI algorithm has better clinical sensitivity, improving the likelihood that a pathogenic parasite may be detected.”
Training the AI with a Global Dataset
To build and rigorously test the system, ARUP partnered with Techcyte, a Utah-based technology firm. The collaboration involved training the AI using over 4,000 parasite-positive samples sourced from laboratories across the United States, Europe, Africa, and Asia. This diverse dataset encompassed 27 classes of parasites, including rare species like Schistosoma japonicum and Paracapillaria philippinensis from the Philippines, and Schistosoma mansoni from Africa.
“This was really a robust study when you consider the number of organisms and positive specimens used to validate the AI algorithm,” Mathison explained.
The AI demonstrated impressive accuracy, achieving 98.6% agreement with manual review after discrepancy analysis. Notably, the tool identified 169 additional organisms that had been previously missed by human observers. “We are identifying more organisms than we would without the AI, which improves diagnosis and treatment for patients who are affected,” said Adam Barker, ARUP’s chief operations officer.
Further studies revealed that the AI consistently detected parasites even in highly diluted samples, suggesting its ability to identify infections at earlier stages or when parasite levels are low.
From Innovation to Widespread Implementation
ARUP has been a pioneer in applying AI to clinical parasitology for several years. In 2019, the lab became the first globally to utilize AI for the trichrome portion of the ova and parasite test. This capability was expanded in March 2025 to encompass wet-mount analysis, marking the first instance of AI being used for the entire parasite testing process.
The timing of this expansion proved fortuitous. In August, ARUP experienced a record influx of specimens for parasite testing. The increased efficiency afforded by the AI allowed the lab to meet the surge in demand without compromising the quality of results.
“An AI algorithm is only as good as the personnel inputting the data,” Barker emphasized. “We have phenomenal staff who have used their extensive knowledge and skills to build an exceptional AI solution that benefits not just the laboratory, but also patients.”
ARUP and Techcyte are committed to further expanding the role of AI in diagnostic testing. Beyond parasitology, ARUP has already implemented AI to assist with Pap testing and is actively developing additional tools to streamline lab operations and enhance diagnostic accuracy.
The research, titled “Detection of protozoan and helminth parasites in concentrated wet mounts of stool using a deep convolutional neural network,” was published on October 21 in the Journal of Clinical Microbiology. Co-authors include scientists from both ARUP and Techcyte. Marc Couturier, formerly ARUP’s head of medical operations for microbiology and immunology, now serves as the medical director of clinical microbiology at NorDx, Maine’s leading clinical lab.
Techcyte, Inc., founded in 2013 as a university startup in Orem, Utah, was born from the discoveries of Mohamed Salama, then an ARUP medical director and University of Utah pathology professor. The company has since emerged as a leader in AI-powered digital diagnostics.
