Imperial College London
Portrait Picture

Professor Pantelis Georgiou

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Biomedical Electronics
 
 
 
//

Contact

 

+44 (0)20 7594 6326pantelis Website

 
 
//

Location

 

902Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Miglietta:2021:10.1101/2021.04.16.21255464,
author = {Miglietta, L and Moniri, A and Pennisi, I and Malpartida, Cardenas K and Abbas, H and Hill-Cawthorne, K and Bolt, F and Davies, F and Holmes, AH and Georgiou, P and Rodriguez, Manzano J},
doi = {10.1101/2021.04.16.21255464},
publisher = {Cold Spring Harbor Laboratory},
title = {Coupling machine learning and high throughput multiplex digital PCR enables accurate detection of carbapenem-resistant genes in clinical isolates},
url = {http://dx.doi.org/10.1101/2021.04.16.21255464},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - <jats:p>Background: The emergence and spread of carbapenemase-producing organisms (CPO) are a significant clinical and public health concern. Rapid and accurate identification of patients colonised with CPO is essential to adopt prompt prevention measures in order to reduce the risk of transmission. Recent proof-of-concept studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex assays. From this, we sought to determine if this ML based methodology could accurately identify five major carbapenem-resistant genes in clinical CPO-isolates.Methods: We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex assay for detection of blaVIM, blaOXA-48, blaNDM, blaIMP and blaKPC. Combining the recently reported ML method "Amplification and Melting Curve Analysis" (AMCA) with the abovementioned multiplex assay, we assessed the performance of the methodology in detecting these five carbapenem-resistant genes. The classification accuracy relies on the usage of real-time data from a single fluorescent channel and benefits from the kinetic and thermodynamic information encoded in the thousands of amplification events produced by high throughput dPCR.Results: The 5-plex showed a lower limit of detection of 100 DNA copies per reaction for each primer set and no cross-reactivity with other carbapenemase genes. The AMCA classifier demonstrated excellent predictive performance with 99.6% (CI 97.8-99.9%) accuracy (only one misclassified sample out of the 253, with a total of 163,966 positive amplification events), which represents a 7.9% increase compared to the conventional ML-based melting curve analysis (MCA) method.Conclusion: This work demonstrates the utility of the AMCA method to increase the throughput and performance of state-of-the-art molecular diagnostic platforms, reducing costs without any changes
AU  - Miglietta,L
AU  - Moniri,A
AU  - Pennisi,I
AU  - Malpartida,Cardenas K
AU  - Abbas,H
AU  - Hill-Cawthorne,K
AU  - Bolt,F
AU  - Davies,F
AU  - Holmes,AH
AU  - Georgiou,P
AU  - Rodriguez,Manzano J
DO  - 10.1101/2021.04.16.21255464
PB  - Cold Spring Harbor Laboratory
PY  - 2021///
TI  - Coupling machine learning and high throughput multiplex digital PCR enables accurate detection of carbapenem-resistant genes in clinical isolates
UR  - http://dx.doi.org/10.1101/2021.04.16.21255464
ER  -
Download