Scientists at ARUP Laboratories have developed an artificial intelligence (AI) tool that detects intestinal parasites in stool samples more quickly and accurately than traditional methods, potentially transforming how labs diagnose parasitic infections around the world.<\/p>\n
Identifying parasites under the microscope has long been a painstaking task requiring highly trained experts to manually scour each sample for telltale cysts, eggs or larva. Now, a deep-learning model, known as a convolutional neural network (CNN), achieves that work with a high degree of precision, according to a study published Tuesday in the Journal of Clinical Microbiology<\/a>.<\/p>\n The researchers demonstrated that the AI system can detect parasites in wet mounts of stool with greater sensitivity than human observers, even those with years of experience hunting for these signs.<\/p>\n \u201cIt has been a groundbreaking effort, and what we\u2019ve accomplished is remarkable,\u201d said lead author Blaine Mathison<\/a>, ARUP\u2019s technical director of parasitology and an adjunct lecturer in the University of Utah\u2019s Department of Pathology. \u201cOur validation studies have demonstrated the AI algorithm has better clinical sensitivity, improving the likelihood that a pathogenic parasite may be detected.\u201d<\/p>\n A leading national reference lab, ARUP<\/a> is an independent nonprofit enterprise of the University of Utah and the School of Medicine\u2019s Department of Pathology<\/a>, where Mathison is an adjunct instructor.<\/p>\n Training the AI on thousands of samples<\/p>\n To build and test the system, ARUP and its partner, a Utah tech firm called Techcyte<\/a>, trained the AI using more than 4,000 parasite-positive samples collected from laboratories across the United States, Europe, Africa and Asia. These samples represented 27 classes of parasites, including rare species, such as Schistosoma japonicum and Paracapillaria philippinensis from the Philippines, and Schistosoma mansoni from Africa.<\/p>\n \u201cThis was really a robust study when you consider the number of organisms and positive specimens used to validate the AI algorithm,\u201d Mathison said.<\/p>\n After discrepancy analysis, the positive agreement between AI and manual review was 98.6%. The tool also picked up 169 additional organisms that had been missed in earlier manual reviews.<\/p>\n \u201cWe are identifying more organisms than we would without the AI, which improves diagnosis and treatment for patients who are affected,\u201d said Adam Barker, ARUP\u2019s chief operations officer.<\/p>\n Furthermore, a limit of detection study found AI consistently found more parasites than the technologists did, even when the samples were highly diluted, suggesting the system can detect infections at earlier stages or when parasite levels are low.<\/p>\n From innovation to implementation<\/p>\n ARUP has pioneered the use of AI in clinical parasitology for years. In 2019, it became the world\u2019s first lab to apply AI to the trichrome portion of the ova and parasite test. In March 2025, it expanded that capability to include the wet-mount analysis\u2014becoming the first laboratory to use AI for the entire testing process.<\/p>\n That timing proved propitious: in August, ARUP received a record number of specimens for parasite testing. The efficiency gained through AI enabled the lab to meet demand without compromising quality.<\/p>\n \u201cAn AI algorithm is only as good as the personnel inputting the data,\u201d Barker said. \u201cWe 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.\u201d<\/p>\n ARUP and Techcyte plan to continue expanding AI\u2019s role in diagnostic testing. Beyond parasitology, ARUP has already implemented AI to assist with Pap testing and is developing other tools to streamline lab operations and improve diagnostic accuracy.<\/p>\n The research was published under the title, \u201cDetection of protozoan and helminth parasites in concentrated wet mounts of stool using a deep convolutional neural network<\/a>,\u201d appearing Oct. 21 in the Journal of Clinical Microbiology. Co-authors include several other scientists at ARUP and Techcyte. Until recently, senior author Marc Couturier<\/a> served as ARUP\u2019s head of medical operations for microbiology and immunology and was a U professor of pathology. He is now the medical director of clinical microbiology at NorDx, Maine\u2019s top clinical lab.<\/p>\n