# Portable Electronic Olfactometer for Non-Invasive Screening of Canine Ehrlichiosis: A Proof-of-Concept Study Using Machine Learning

## TL;DR

A portable electronic device can detect canine ehrlichiosis non-invasively by analyzing saliva samples using machine learning.

## Contribution

This is the first proof-of-concept study exploring electronic olfactometry for non-invasive screening of canine ehrlichiosis.

## Key findings

- Saliva samples provided the most accurate discrimination between infected and control dogs.
- SVM achieved 94.7% accuracy in detecting ehrlichiosis from saliva samples.
- Breath and hair samples showed lower performance compared to saliva.

## Abstract

Tick-borne diseases represent a significant challenge for veterinary clinics, particularly in regions with limited access to laboratory diagnostics. Canine ehrlichiosis is one such disease and may lead to severe outcomes if not properly identified and managed. Conventional diagnostic approaches rely mainly on blood-based tests that require trained personnel, laboratory infrastructure, and invasive sampling procedures. In this pilot and exploratory study, we evaluated the feasibility of a portable electronic olfactometer as a non-invasive screening approach based on the analysis of volatile organic compounds (VOCs) collected from breath, saliva, and hair samples from dogs. The device incorporates an array of eight gas sensors, and the recorded signals are processed using computational data analysis and machine-learning techniques to identify chemical fingerprint patterns associated with infected and control animals. The results suggest that saliva samples provided the most consistent discrimination between groups. Although limited by sample size and exploratory in nature, this study indicates that electronic olfactometry may represent a complementary, low-cost tool to support non-invasive screening of canine ehrlichiosis in future veterinary research, particularly in low-resource settings.

Canine ehrlichiosis, caused by Ehrlichia canis, represents a relevant challenge in veterinary medicine, particularly in resource-limited settings where access to laboratory-based diagnostics may be constrained. This pilot and exploratory study aimed to evaluate the feasibility of a portable electronic olfactometer as a non-invasive screening approach, based on the analysis of volatile organic compounds (VOCs) present in breath, saliva, and hair samples from dogs. Signals were acquired using an array of eight metal-oxide (MOX) gas sensors (MQ and TGS series). After preprocessing, principal component analysis (PCA) was applied for dimensionality reduction, and the resulting features were analyzed using supervised machine-learning classifiers, including AdaBoost, support vector machines (SVM), k-nearest neighbors (k-NN), and Random Forests (RF). A total of 38 dogs (19 PCR-confirmed infected cases and 19 controls) were analyzed, generating 114 samples evenly distributed across the three biological matrices. Among the evaluated models, SVM showed the most consistent performance, particularly for saliva samples, achieving an accuracy, sensitivity, and precision of 94.7% (AUC = 0.964). In contrast, breath and hair samples showed lower discriminative performance. Given the limited sample size and the exploratory nature of the study, these results should be interpreted as preliminary; nevertheless, they suggest that electronic olfactometry may represent a complementary, low-cost, non-invasive screening tool for future research on canine ehrlichiosis, rather than a standalone diagnostic method.