Coupling Machine Learning and High Throughput Multiplex Digital PCR Enables Accurate Detection of Carbapenem-Resistant Genes in Clinical Isolates

Abstract

Rapid and accurate identification of patients colonised with carbapenemase-producing organisms (CPOs) is essential to adopt prompt prevention measures to reduce the risk of transmission. Recent studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex PCR assays when using synthetic DNA templates. We sought to determine if this novel methodology could be applied to improve identification of the five major carbapenem-resistant genes in clinical CPO-isolates, which would represent a leap forward in the use of PCR-based data-driven diagnostics for clinical applications. We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex PCR assay for detection of blaIMP, blaKPC, blaNDM, blaOXA-48, and blaVIM. Combining the recently reported ML method “Amplification and Melting Curve Analysis” (AMCA) with the abovementioned multiplex assay, we assessed the performance of the AMCA methodology in detecting these genes. The improved classification accuracy of AMCA relies on the usage of real-time data from a single-fluorescent channel and benefits from the kinetic/thermodynamic information encoded in the thousands of amplification events produced by high throughput real-time dPCR. The 5-plex showed a lower limit of detection of 10 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 160,041 positive amplification events), which represents a 7.9% increase (p-value <0.05) compared to conventional melting curve analysis. This work demonstrates the use of the AMCA method to increase the throughput and performance of state-of-the-art molecular diagnostic platforms, without hardware modifications and additional costs, thus potentially providing substantial clinical utility on screening patients for CPO carriage.

REASSURED Multiplex Diagnostics: A Critical Review and Forecast

“…This platform represents a low-cost device that can be adapted for molecular diagnostics at the POC and low resource settings. Machine-learning-assisted dPCR has also improved diagnostic outcomes as demonstrated by Liu [ 109 ] and Miglietta [ 110 ].…”

Adaptive Filtering Framework to Remove Nonspecific and Low-Efficiency Reactions in Multiplex Digital PCR Based on Sigmoidal Trends

“…As a case study, data from Miglietta et al were used in this work. 26 Data from synthetic DNA (gBlocks gene fragments, IDT) containing bla NDM (N = 18,480), bla IMP (N = 17,710), and bla OXA-48 (N = 17,710) gene sequences were used as the training data set. From the original study, a total of 198 clinical isolates labeled with these three targets were used as the testing samples to maintain a balanced data set and due to their high prevalence and clinical significance in U.K. hospitals.…”

“…This represents a step forward to incorporate ACA in clinical applications and ensure that by filtering in correct amplification curves, higher diagnosis reliability is delivered to the patient. These concepts were explored using data obtained from qdPCR experiments reported by Miglietta et al 26 As a case study, three of the "The big 5" Our vision is that by sharing this new approach we can significantly improve the quality of data from qdPCR instruments and enhance the sensitivity and accuracy of ML-based multiplexing methods relying only on amplification curves. Moreover, extending this framework to other amplification chemistries and real-time platforms will improve the multiplexing capabilities of existing diagnostic workflows and platforms.…”

“…The AMCA couples both ACA and MCA coefficients from the classifier to improve classification accuracy. This has been demonstrated through the detection of nine mobilized colistin resistance genes and clinical isolates containing five common carbapenemase resistance genes. , Moreover, multiplex PCR (coupled with innovative approaches such as ACA or AMCA) is bringing about a change of paradigm in molecular diagnostics by enabling faster, more accurate, and higher-throughput detection of several biomarkers in one reaction. Its applications are wide ranging, including precision medicine in cancer, genetic testing, and syndromic testing in clinical microbiology and infectious diseases, where it enables precise multitarget identification of multiple pathogens and antimicrobial resistance genes.…”

“…This represents a step forward to incorporate ACA in clinical applications and ensure that by filtering in correct amplification curves, higher diagnosis reliability is delivered to the patient. These concepts were explored using data obtained from qdPCR experiments reported by Miglietta et al . As a case study, three of the “The big 5” carbapenemase genes ( bla NDM , bla IMP , and bla OXA‑48 ) were considered in this study.…”