UK, China scientists develop AutoEnricher to curb AMR

95 pc accuracy in rapid diagnosis of multiple infections

A new technique AutoEnricher, has been developed by engineers and clinicians from the United Kingdom and China, to diagnose multiple infections in 20 minutes, which can curb the spread of antimicrobial resistance (AMR).

In a development that is likely to curb the spread of AntiMicrobial Resistance (AMR), engineers and clinicians from the United Kingdom and China have developed a new technique called AutoEnricher to diagnose multiple infections in 20 minutes. 

In a press release, the University of Glasgow says that the newly developed technique combines microfluidic technology with sophisticated analysis and machine learning to enable the diagnosis of pathogens. 

The statement adds that in a paper published in the Nature Communications journal, researchers show how the effectiveness of the system has been validated on real patient samples and has delivered diagnoses with 95 pc accuracy, even in samples with low concentrations of pathogens, it says.

It adds that the system could also become a tool to solve antimicrobial resistance, a rapidly-accelerating global threat to human health which caused over five million deaths in 2019 and is projected to kill over 10 million people by a year in 2050. 

Also Read Artificial Intelligence transforming disease diagnosis

“One of the major drivers of antibiotic resistance is the misuse or overuse of drugs to treat infections. Currently, it can take days or even weeks to culture microbes taken from patient samples in the lab to enable diagnosis. That means doctors often have to act urgently and use antibiotics to treat patients suffering from life-threatening conditions like sepsis or pneumonia without knowing for sure if they actually have a bacterial infection,” says Jiabao Xu, first author of the paper, University of Glasgow. 

“AutoEnricher advances personalised medicine by compressing diagnostic timelines and enhancing antimicrobial decision-making. This new instrument will help enable doctors to match the right antibiotic to an infection at the right time, improving patient outcomes while reducing the potential for the emergence of antimicrobial resistance. The team’s system combines innovative hardware and software to enable a rapid two-stage diagnosis. In the first stage, the system uses a microfluidic device developed by the team to scrub human cells from samples of patients’ blood, urine or spinal fluid, leaving behind only pathogen cells,” says Jon Cooper, a corresponding author. 

The statement adds that in the second stage, the chemical fingerprint of pathogen cells is identified using a technique called Raman spectroscopy. The finger is analysed by a machine learning tool trained on a database of 324 clinical isolates from 36 species of bacteria and fungi. It can provide a diagnosis by analysing as few as 10 pathogen cells in less than 20 minutes. 

It adds that AutoEnricher’s performance was validated by three hospitals in China, which were also tested using conventional lab methods to culture the bacteria to enable diagnosis. Autoenricher’s diagnosis method matched the conventional lab method’s outcomes 95 pc of the time, it says. 

“These are really encouraging results from the largest study of its kind conducted on real patient samples. We have shown that this single-cell approach to diagnosis can rapidly deliver remarkably accurate results, and even pick out multiple infections which are much harder to spot using conventional lab culture methods,” says Professor Wei Huang, co-investor on the project, University of Oxford. 

“The next step is to apply AutoEnricher to a much larger cohort of patient samples in a proper clinical study. We are already working on the first steps towards making that happen, and we hope that AutoEnricher will make a real difference in addressing the spread of antimicrobial resistance in the years to come,” says Professor Huabing Yin, senior author of the paper, University of Glasgow. 

The statement adds that the paper Rapid culture-free diagnosis of clinical pathogens via integrated microfluidic-Raman micro spectroscopy, has been published in Nature Communications journal.