# Easy Identification of Leishmania (Leishmania) amazonensis and Leishmania (Viannia) braziliensis Species by Using Fourier-Transform Infrared Spectroscopy and Machine Learning Algorithms

## TL;DR

This study shows that FTIR spectroscopy and machine learning can quickly and accurately identify two Leishmania species, offering a low-cost alternative to traditional methods.

## Contribution

The novel use of FTIR spectroscopy and SVM for rapid, accurate identification of Leishmania amazonensis and Leishmania braziliensis.

## Key findings

- PCA revealed distinct spectral clustering for the two Leishmania species based on protein, lipid, and nucleic acid bands.
- SVM models achieved over 90% accuracy, with the best model reaching 100% accuracy, sensitivity, and specificity.
- The method offers a rapid, low-cost, and scalable solution for Leishmania species classification in clinical and field settings.

## Abstract

Leishmaniasis is
a neglected tropical disease requiring accurate
species identification to ensure proper clinical management and epidemiological
surveillance. Accurate species and strain identification depends on
molecular and biochemical tools. While these conventional techniques
are effective, they are often costly, time-consuming, and inaccessible
in low-resource settings. In this study, we evaluated the potential
of Fourier-transform infrared (FTIR) spectroscopy, combined with machine
learning algorithms, for the discrimination of Leishmania
amazonensis and Leishmania braziliensis species in liquid cultures. FTIR spectra were acquired from 80 culture
samples and preprocessed using standard normal variate (SNV) correction
and Fast Fourier Transform (FFT) filtering. Principal Component Analysis
(PCA) revealed clear species-specific clustering driven by spectral
differences in protein, lipid, and nucleic acid vibrational bands.
Support Vector Machine (SVM) models were trained using PCA scores,
achieving over 90% accuracy in all tested configurations. The best
model, using a linear kernel and the first three principal components,
reached 100% accuracy, sensitivity, and specificity in external validation.
Our findings demonstrate that FTIR spectroscopy, in combination with
SVM, offers a rapid, low-cost, and scalable strategy for the screening
and classification of Leishmania species,
with promising applications for field and clinical diagnostics.