Evaluating the efficacy of bioelectrical impedance analysis using machine learning models for the classification of goats exposed to haemonchosis

Authors: SIDDIQUE, AFTAB - Fort Valley State University; BATCHU, PHANEENDRA - Fort Valley State University; SHAIK, ARSHAD - Fort Valley State University; GURRAPU, PRIYANKA - Fort Valley State University; TEJ ERUKULLA, THARUN - Fort Valley State University; BROWN, DAVIA - Fort Valley State University; MAHAPATRA, AJIT - Fort Valley State University; PANDA, SUDHANSHU - University Of North Georgia; MORGAN, ERIC - Queen'S University Belfast; VAN WYK, JAN - University Of Pretoria; Shapiro Ilan, David; KANNAN, GOVIND - Auburn University; TERRILL, THOMAS - Fort Valley State University

Submitted to: Frontiers in Veterinary Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/15/2025
Publication Date: 5/30/2025
Citation: Siddique, A., Batchu, P., Shaik, A., Gurrapu, P., Tej Erukulla, T., Brown, D., Mahapatra, A., Panda, S., Morgan, E., Van Wyk, J., Shapiro Ilan, D.I., Kannan, G., Terrill, T. 2025. Evaluating the efficacy of bioelectrical impedance analysis using machine learning models for the classification of goats exposed to haemonchosis. Frontiers in Veterinary Science. 12. https://doi.org/10.3389/fvets.2025.1584828.
DOI: https://doi.org/10.3389/fvets.2025.1584828

Interpretive Summary: Ruminants, such as goats, are susceptible to various internal parasites. These parasites (such as the barber's pole worm) are found in the ruminant's stomach. They can cause severe reductions in growth and health, which may lead to death in goats or other livestock that are infected. Therefore, it is critical to monitor parasitism levels in goats and other livestock. The standard approach to monitoring parasites in goats through blood or fecal samples. These methods are costly, time-consuming and can cause stress in the goats. Therefore, more efficient methods to monitor parasitism are needed. In this study, we tested the ability of bioelectrical impedance analysis to measure parasitism in goats. Bioelectrical impedance analysis is a non-invasive technology that measures electrical properties in the animals. These electrical properties are disrupted when the animals are parasitized. Additionally, this study explored bioelectrical impedance analysis in combination with machine learning techniques to classify goats as either parasitized or healthy. The results indicated that bioelectrical impedance analysis in combination with machine learning can be highly accurate and efficient in monitoring parasitism in goats. Thus, this new monitoring system could improve herd management, reduce productivity losses, and enhance animal welfare.

Technical Abstract: Rapid identification and assessment of animal health are critical for livestock productivity, especially for small ruminants like goats, which are highly susceptible to blood-feeding gastrointestinal nematodes, such as Haemonchus contortus. This study aimed to establish proof of concept for using bioelectrical impedance analysis (BIA) as a non-invasive diag-nostic tool to distinguish parasite-infected goats from healthy ones. A cohort of 94 intact male Spanish goats (58 healthy; 36 parasitized) was selected to evaluate the efficacy of BIA through the measurement of resistance (Rs) and reactance (Xc). Data were collected from live goats using the CQR 3.0 device over multiple time points. The study employed several machines learning models, including Support Vector Machines (SVM), Backpropagation Neural Networks (BPNN), k-Nearest Neighbors (K-NN), XGBoost, and Keras deep learning models to classify goats based on their bioelectrical properties. Among the classification models, SVM demonstrated the highest accuracy (95%) and F1-score (96%), while K-NN showed the lowest accuracy (90%). For regression tasks, BPNN outperformed other models with a nearly perfect R² value of 99.9% and a minimal mean squared error (MSE) of 1.25e-04, followed by SVR with an R² of 96.9%. The BIA data revealed significant differ-ences in Rs and Xc between healthy and parasitized goats, with parasitized goats exhibit-ing elevated resistance values, likely due to dehydration and tissue changes caused by parasitic infection. These findings highlight the potential of BIA combined with machine learning to develop a scalable, rapid, and non-invasive diagnostic tool for monitoring small ruminant health, particularly in detecting parasitic infections like Haemonchus con-tortus. This approach could improve herd management, reduce productivity losses, and enhance animal welfare.