Rapid diagnosis of infection etiology in febrile pediatric oncology patients using infrared spectroscopy of leukocytes

Abstract

Rapid diagnosis of the etiology of infection is highly important for an effective treatment of the infected patients. Bacterial and viral infections are serious diseases that can cause death in many cases. The human immune system deals with many viral and bacterial infections that cause no symptoms and pass quietly without treatment. However, oncology patients undergoing chemotherapy have a very weak immune system caused by leukopenia, and even minor pathogen infection threatens their lives. For this reason, physicians tend to prescribe immediately several types of antibiotics for febrile pediatric oncology patients (FPOPs). Uncontrolled use of antibiotics is one of the major contributors to the development of resistant bacteria. Therefore, for oncology patients, a rapid and objective diagnosis of the etiology of the infection is extremely critical. Current identification methods are time‐consuming (>24 h). In this study, the potential of midinfrared spectroscopy in tandem with machine learning algorithms is evaluated for rapid and objective diagnosis of the etiology of infections in FPOPs using simple peripheral blood samples. Our results show that infrared spectroscopy enables the diagnosis of the etiology of infection as bacterial or viral within 70 minutes after the collection of the blood sample with 93% sensitivity and 88% specificity.

Potential of infrared microscopy to differentiate between dementia with Lewy bodies and Alzheimer’s diseases using peripheral blood samples and machine learning algorithms

“…The potential of the SVM and RF algorithms for classification purposes in similar cases has been previously well established. 51,74,75 Here although the spectral differences were subtle, they were still repeatable enough to achieve a good classification, as is shown below.…”

“…We considered a binary classification problem with spectra from blood components being grouped based on their categories as dementias or controls using SVM and RF. 51,55,56,58,59 For this analysis, we focused on the low-wavenumber spectral region (950 to 1760 cm −1 ); LOGOCV was used for the optimization of the parameters of the classifiers and estimation of their performances.…”

“…As has been found in previous works, 51,52 the second derivative of the raw feature vector is much more informative and leads to a much better classification, so the feature selection was performed on those vectors.…”

“…Some of these wavenumbers do not carry any additional specific information to other wavenumbers for the classification task; thus different methods are used for efficient feature selection to exclude these wavenumbers from the original features vectors before training the classifiers. [47][48][49][50][51] The aim is to find a low-dimensional representation of the data to increase classifier performance.…”

Determination of Klebsiella pneumoniae Susceptibility to Antibiotics Using Infrared Microscopy

“…We performed feature selection on the second derivative of the IR absorption spectra (feature vectors). In our previous studies, 59,60 these feature vectors are much more separative and lead to much better classification on these vectors.…”