Rapid and accurate screening of cystic echinococcosis in sheep based on serum Fourier‐transform infrared spectroscopy combined with machine learning algorithms

Abstract

Cystic echinococcosis (CE) in sheep is a serious zoonotic parasitic disease caused by Echinococcus granulosus sensu stricto (s.s.). Presently, the screening technology for CE in sheep is time-consuming and inaccurate, and novel screening technology is urgently needed. In this work, we combined machine-learning algorithms with Fourier transform infrared (FT-IR) spectroscopy of serum to establish a quick and accurate screening approach for CE in sheep. Serum samples from 77 E. granulosus s.s.-infected sheep to 121 healthy control sheep were measured by FT-IR spectrometer. To optimize the classification accuracy of the serum FI-TR method for the E. granulosus s.s.-infected sheep and healthy control sheep, principal component analysis (PCA), linear discriminant analysis, and support vector machine (SVM) algorithms were used to analyze the data.Among all the bands, 1500-1700 cm À1 band has the best classification effect; its diagnostic sensitivity, specificity, and accuracy of PCA-SVM were 100%, 95.74%, and 96.66%, respectively. The study showed that serum FT-IR spectroscopy combined with machine learning algorithms has great potential for rapid and accurate screening methods for the CE in sheep.

Acute Cholecystitis Diagnosis in the Emergency Department: An Artificial Intelligence-based Approach

“…Previous studies have rarely addressed the timely diagnosis of acute cholecystitis. One study utilized serum uorescence spectroscopy to differentiate patients with acute cholecystitis from healthy subjects with an accuracy of 96.55%, employing an SVM algorithm [19]. However, this study focused solely on distinguishing patients from healthy volunteers rather than other abdominal emergencies.…”

Rapid and non‐invasive detection of cystic echinococcosis in sheep based on serum fluorescence spectrum combined with machine learning algorithms

“…In this study, according to the exclusion and inclusion criteria [10], we collected 63 E. granulosus s.s.-infected sheep and 60 uninfected E. granulosus s.s. sheep blood samples. All the blood samples were centrifuged at 4 C, 3000 rpm/min for 10 min.…”

“…Pipetted 100 μL serum samples transfer into a 96-well plate, and used SkanIt software (version 2.4.5) to read the fluorescence data of each serum sample on a fluorescence scanning multimode reader (Variouskan Flash, Thermo Scientific). Measuring condition: excitation wavelength was 405 nm; wavelength range was 430-750 nm [33]. The width of the emission was 5 nm; the width of excitation slits was 5 nm; the integration duration was 100 ms, while the acquisition interval was 1 nm.…”

“…Imaging technology needs to be equipped with professional imaging technicians, and the procedures for dealing with sheep are laborious and time-consuming. Meanwhile, before the imaging detection, the sheep's wool was trimmed by scissors, and the diagnosis process and time are also complicated [9,10]. The main method of sheep serological detection is ELISA (enzyme-linked immunosorbent assay); however, it has a limited sensitivity, a lengthy detection time, and difficulty standardizing results between product batches [11].…”

“…Fluorescence spectroscopy is a non‐destructive, selective, convenient, and sensitive optical detection technique, and compared with Infrared and Raman spectroscopy, which explore the absorption and scattering phenomena of molecular spectroscopy [12]. It can be utilized as a method to find interactions in intricate substrate samples, such as changes in cell and tissue function and serum [13–16].…”