Research Article

Optomagnetic Imaging Spectroscopy (OMIS) for in situ detection of bacteria in blood – feasibility study

¹ Wound Infections Department, Walter Reed Army Institute of Research, 503 Robert Grant Avenue, Silver Spring, MD 20910-7500, USA
² NanoWorld Lab, Vojvode Vlahovica 21Dj, 11041 Belgrade, Serbia
³ Armed Forces Research Institute of Medical Sciences (AFRIMS), US Army Medical Component, 315/6 Rajvithi Rd, Bangkok 10400, Thailand
⁴ US Army Medical Research and Development Command, 1403 Ditto Ave, 2nd Floor, Fort Detrick, MD 21702, USA
⁵ Bacterial Disease Branch, Walter Reed Army Institute of Research, 503 Robert Grant Avenue, Silver Spring, MD 20910-7500, USA

^* Corresponding authors: alexander.g.bobrov.ctr@mail.mil; djuro.koruga@gmail.com

Received: 13 January 2022
Accepted: 15 March 2022

Abstract

Introduction: Sepsis is one of the leading causes of death in military and civilian hospitals. Rapid identification of involved pathogens is a key step for appropriate diagnosis, treatment and ultimately survival. Current diagnostics tools are either very bulky and not deployment ready, or require a long time to provide results. Given these obstacles, new solutions are urgently needed. Optomagnetic Imaging Spectroscopy (OMIS) is novel technology successfully used for the detection of cancer cells and viruses. OMIS has high sensitivity due to recording the unpaired and paired electrons of sample material. Furthermore, machine learning that uses the algorithms random forest (RF) classifier and artificial neural network (ANN) is integrated into the technology to enhance detection. Here we evaluated the feasibility of OMIS for the detection of bacteria in blood. Methods: We used commercially available human blood spiked with a defined concentration multidrug resistant Staphylococcus aureus derived from a clinical isolate. Final concentrations of bacteria of 1 × 10⁶, 1 × 10⁵ and 1 × 10⁴ CFU/mL corresponding to High (H), Medium (M) and Low (L) concentrations respectively. A total of 240 samples (60 samples per concentration as well as 60 samples of sterile blood (N)) was imaged, and the data were analyzed using random forest classifier and artificial neural network. Images for the training set and validation sets were separately obtained and used for comparison against true positive values (confirmatory plating on the nutrient agar). Results: The average score of classification samples in the correct category (N, L, M, H) one-by-one was 94% for the ANN algorithm, while for the RF algorithm accuracy was 93% (average means that three times different 40 samples (of 240 samples) were chosen, and each prediction test had different sample mixtures). The closeness of the two values of accuracy strongly indicates that the input data (interaction of light with paired and unpaired electrons) and output data (classification N, L, M, H concentration of bacteria) are correlated.