# Evaluation of the Diagnostic Performance and Validation of an AI-Assisted Fluorescence Imaging Device for Fecal Egg Counts Against the Manual McMaster Reference Method in Kiko Male Goats

## TL;DR

An AI-based device for counting parasite eggs in goat feces was tested and found to reliably rank infection levels but undercounts compared to traditional methods.

## Contribution

The study evaluates and validates an AI-assisted fluorescence imaging device for fecal egg counts in goats, highlighting its potential with adjusted thresholds.

## Key findings

- The AI device reliably ranks animals by parasite burden but underestimates egg counts compared to manual methods.
- The system shows excellent discrimination for identifying animals above the treatment threshold with an AUC of 0.90–0.96.
- Regression analyses revealed linear or curvilinear associations between AI and manual counts depending on egg levels.

## Abstract

Gastrointestinal parasites are a major concern for goats and other grazing animals, resulting in poor growth, anemia, and in severe cases even death. Farmers have traditionally measured parasite levels by counting parasite eggs in feces under a microscope, but this procedure is slow, requires training, and is susceptible to individual variation. New automated technologies that use artificial intelligence have been developed to make this procedure faster and more consistent, but they need to be thoroughly evaluated before they can be adopted in daily practice. In this study, fecal parasite egg counts from male goats maintained under identical management conditions were used to compare an artificial intelligence–based egg-counting technique with the conventional microscopy method. The agreement between the two approaches, the accuracy of the automated device in identifying animals requiring treatment, and diagnostic performance of the automated system were assessed. The automated system successfully ranked animals by level of infection and showed excellent ability to detect animals above the treatment threshold, but it consistently counted fewer eggs than the manual method. This means the device can be useful, but the treatment threshold must be adjusted. With proper calibration, this technology could improve parasite control and reduce drug resistance.

Gastrointestinal parasites are a major health and economic concern in small ruminants. The classic microscopic approach using the manual McMaster method serves to quantitatively count parasite eggs, which are labor-intensive and prone to variation. Artificial intelligence-based systems (Parasight®, powered by Fecalsight AI™) could provide quicker and more objective alternatives; therefore, independent validation is necessary before clinical implementation. The objective of this study was to evaluate the agreement, classification consistency, and diagnostic performance of Parasight® relative to the manual McMaster method, with a focus on its suitability as a screening and decision-support tool. Fecal samples from 44 Kiko goats over 3 sampling times were analyzed using both methods, with manual counts performed independently by 2 observers. Agreement between methods was assessed using Lin’s concordance correlation coefficient, Bland–Altman analysis, and Cohen’s Kappa for categorical classification. Diagnostic performance for identifying animals exceeding the clinical treatment threshold (>1000 eggs per gram) was evaluated using receiver operating characteristic (ROC) analysis, and regression modeling was used to characterize associations between methods. Manual observers showed high reliability, confirming the suitability of the McMaster method as a reference. Compared with manual counts, Parasight® consistently underestimated egg counts, resulting in poor-to-moderate absolute agreement; however, it reliably ranked animals by parasite burden and showed excellent discrimination for identifying animals above the treatment threshold (AUC = 0.90–0.96). Regression analyses further demonstrated linear or curvilinear associations depending on egg counts. Overall, the Parasight® device reliably captured relative parasite burden but required a lower operational threshold to match manual treatment decisions.