Jump to main content
Jump to site search

Issue 21, 2020
Previous Article Next Article

Diagnosis of inaccessible infections using infrared microscopy of white blood cells and machine learning algorithms

Author affiliations

Abstract

Physicians diagnose subjectively the etiology of inaccessible infections where sampling is not feasible (such as, pneumonia, sinusitis, cholecystitis, peritonitis), as bacterial or viral. The diagnosis is based on their experience with some medical markers like blood counts and medical symptoms since it is harder to obtain swabs and reliable laboratory results for most cases. In this study, infrared spectroscopy with machine learning algorithms was used for the rapid and objective diagnosis of the etiology of inaccessible infections and enables an assessment of the error for the subjective diagnosis of the etiology of these infections by physicians. Our approach allows for diagnoses of the etiology of both accessible and inaccessible infections as based on an analysis of the innate immune system response through infrared spectroscopy measurements of white blood cell (WBC) samples. In the present study, we examined 343 individuals involving 113 controls, 89 inaccessible bacterial infections, 54 accessible bacterial infections, 60 inaccessible viral infections, and 27 accessible viral infections. Using our approach, the results show that it is possible to differentiate between controls and infections (combined bacterial and viral) with 95% accuracy, and enabling the diagnosis of the etiology of accessible infections as bacterial or viral with >94% sensitivity and > 90% specificity within one hour after the collection of the blood sample with error rate <6%. Based on our approach, the error rate of the physicians’ subjective diagnosis of the etiology of inaccessible infections was found to be >23%.

Graphical abstract: Diagnosis of inaccessible infections using infrared microscopy of white blood cells and machine learning algorithms

Back to tab navigation

Associated articles

Supplementary files

Article information


Submitted
15 Apr 2020
Accepted
19 Aug 2020
First published
25 Aug 2020

Analyst, 2020,145, 6955-6967
Article type
Paper

Diagnosis of inaccessible infections using infrared microscopy of white blood cells and machine learning algorithms

A. H. Agbaria, G. Beck, I. Lapidot, D. H. Rich, J. Kapelushnik, S. Mordechai, A. Salman and M. Huleihel, Analyst, 2020, 145, 6955
DOI: 10.1039/D0AN00752H

Social activity

Search articles by author

Spotlight

Advertisements