Accurate and rapid antibiotic susceptibility testing using a machine learning-assisted nanomotion technology platform.

Antimicrobial resistance (AMR) is a major public health threat, reducing treatment options for infected patients. AMR is promoted by a lack of access to rapid antibiotic susceptibility tests (ASTs). Accelerated ASTs can identify effective antibiotics for treatment in a timely and informed manner. We describe a rapid growth-independent phenotypic AST that uses a nanomotion technology platform to measure bacterial vibrations. Machine learning techniques are applied to analyze a large dataset encompassing 2762 individual nanomotion recordings from 1180 spiked positive blood culture samples covering 364 Escherichia coli and Klebsiella pneumoniae isolates exposed to cephalosporins and fluoroquinolones. The training performances of the different classification models achieve between 90.5 and 100% accuracy. Independent testing of the AST on 223 strains, including in clinical setting, correctly predict susceptibility and resistance with accuracies between 89.5% and 98.9%. The study shows the potential of this nanomotion platform for future bacterial phenotype delineation.

Nanomotion technology in combination with machine learning: a new approach for a rapid antibiotic susceptibility test for Mycobacterium tuberculosis.

Nanomotion technology is a growth-independent approach that can be used to detect and record the vibrations of bacteria attached to cantilevers. We have developed a nanomotion-based antibiotic susceptibility test (AST) protocol for Mycobacterium tuberculosis (MTB). The protocol was used to predict strain phenotype towards isoniazid (INH) and rifampicin (RIF) using a leave-one-out cross-validation (LOOCV) and machine learning techniques. This MTB-nanomotion protocol takes 21 h, including cell suspension preparation, optimized bacterial attachment to functionalized cantilever, and nanomotion recording before and after antibiotic exposure. We applied this protocol to MTB isolates (n = 40) and were able to discriminate between susceptible and resistant strains for INH and RIF with a maximum sensitivity of 97.4% and 100%, respectively, and a maximum specificity of 100% for both antibiotics when considering each nanomotion recording to be a distinct experiment. Grouping recordings as triplicates based on source isolate improved sensitivity and specificity to 100% for both antibiotics. Nanomotion technology can potentially reduce time-to-result significantly compared to the days and weeks currently needed for current phenotypic ASTs for MTB. It can further be extended to other anti-TB drugs to help guide more effective TB treatment.

Metrological 2iOF fibre-optic system for position and displacement measurement with 31 pm resolution.

In the present paper, we describe a high sensitivity intensity fibre-optic displacement sensor with tens of picometre resolution combined with a sub-picometre resolution interferometric calibration system. Both integrated components form the so-called "2 in one ferrule" system 2iOF. The design and construction of the presented device depend on integrating two sensors' systems within one fibre-optic measuring head, which allows performing in situ calibration process with no additional time-consuming adjustment procedure. The resolution of the 2iOF system is 31 pm/Hz1/2 obtained with an interferometric Fabry-Perot based calibration system-providing accuracy better than tens of fm/Hz1/2 within 1 MHz bandwidth in the measurement range of up to 100 µm. The direct response from the intensity sensor is then the 2iOF output one. It is faster and more convenient to analyze in comparison, with much better resolution (3 orders of magnitude higher) but on the other hand also more time consuming and dependent on the absolute sample position interferometer. The proposed system is flexible and open to various applications. We will present the results of the piezoelectrical actuator displacement measurements, which were performed using the developed system.

High-resolution and wide-bandwidth light intensity fiber optic displacement sensor for MEMS metrology.

We report on the design, properties, and applications of a high-resolution and wide-bandwidth light intensity fiber optic displacement sensor for microelectromechanical system (MEMS) metrology. There are two types of structures that the system is dedicated to: vibrating with both high and low frequencies. In order to ensure high-frequency and high-resolution measurements, frequency down mixing and selective signal processing were applied. The obtained effective measuring bandwidth ranges from single hertz to 1 megahertz. The achieved resolution presented here is 116 pm/Hz1/2 and 138 pm/Hz1/2 for low-frequency and high-frequency operation modes, respectively, whereas the measurement of static displacement is 100 µm.