AI tool revolutionizes intestinal parasite detection in stool samples
Scientists at ARUP Laboratories have developed an artificial intelligence (AI) tool that detects intestinal parasites in stool samples more accurately and swiftly than traditional methods, potentially transforming how labs diagnose parasitic infections worldwide. This breakthrough technology, a deep-learning model known as a convolutional neural network (CNN), outperforms human experts in identifying parasites, marking a significant advancement in parasitology.
The challenge of parasite detection has long been a tedious task, requiring highly trained experts to manually examine each stool sample for cysts, eggs, or larvae under a microscope. However, the new AI system, as demonstrated in a study published in the Journal of Clinical Microbiology, excels in this area with remarkable precision. It can detect parasites in wet mounts of stool with greater sensitivity than even experienced human observers.
Blaine Mathison, lead author and technical director of parasitology at ARUP, expressed the groundbreaking nature of the achievement. "Our validation studies have shown that the AI algorithm has better clinical sensitivity, enhancing the likelihood of detecting pathogenic parasites."
The development was made possible through a collaboration between ARUP and Techcyte, a Utah-based tech firm. The AI was trained on a vast dataset of over 4,000 parasite-positive samples from various global locations, representing 27 classes of parasites, including rare species. This extensive training enabled the AI to identify a wide range of parasites, from Schistosoma japonicum and Paracapillaria philippinensis to Schistosoma mansoni.
The results were impressive. After discrepancy analysis, the AI and manual review showed a positive agreement of 98.6%. Moreover, the AI tool identified 169 additional organisms that were previously missed in manual reviews, showcasing its superior ability to detect parasites.
Adam Barker, ARUP's chief operations officer, highlighted the AI's impact on diagnosis and treatment. "The AI helps us identify more organisms, improving diagnosis and treatment for affected patients."
The AI's sensitivity was further demonstrated in a limit of detection study, where it consistently found more parasites than technologists, even in highly diluted samples. This suggests that the system can detect infections at earlier stages or when parasite levels are low.
ARUP's pioneering role in AI-based parasitology is notable. In 2019, they became the first lab to apply AI to the trichrome portion of the ova and parasite test. In March 2025, they expanded this capability to include wet-mount analysis, becoming the first laboratory to use AI for the entire testing process.
This timely innovation came as ARUP received a record number of parasite testing specimens in August. The AI's efficiency allowed the lab to meet demand without compromising quality, thanks to the skilled personnel who inputted data.
Looking ahead, ARUP and Techcyte plan to expand AI's role in diagnostic testing. Beyond parasitology, ARUP has already implemented AI for Pap testing and is developing tools to streamline lab operations and enhance diagnostic accuracy. This technology has the potential to revolutionize various diagnostic areas, not just parasitology.
Source: Journal of Clinical Microbiology, doi.org/10.1128/jcm.01062-25
