Artificial intelligence (AI) can provide same-day assessments of antimicrobial resistance for patients in intensive care – critical to preventing life-threatening sepsis.
Antimicrobial resistance, the process of microorganisms developing defences against treatment, poses a huge challenge to healthcare around the world. It is estimated to cause 1.2 million deaths globally and cost the NHS at least £180 million per year.
Infections in the bloodstream can become resistant to antibiotics and lead to the life-threatening condition, sepsis. Once the infection has reached a stage of sepsis there is a high probability that patients will rapidly develop organ failure, shock, and even death.
Some patients have more antimicrobial resistance than others, due to previous exposure to antibiotics, their genetics and even diet, which can alter their microbiome.
Now, scientists are harnessing the power of AI to assess the antimicrobial resistance of patients in intensive care units (ICUs) and identify sepsis-causing bloodstream infections.
Researchers from across King's College London and clinicians at Guy's and St Thomas' NHS Foundation Trust have collaborated in this interdisciplinary study – which they hope will help to improve outcomes of critically ill patients.
Making significant steps forward in this field, the team showed how AI and machine learning can provide same-day triaging for patients in ICU, particularly in environments with limited resources. The technology is also much more cost-effective than manual testing.
Current assessments of ICU patients are time consuming and require lengthy laboratory tests, requiring bacteria to be cultured in a laboratory, taking up to five days. This can have a huge impact on care outcomes, especially given the fragility of ICU patients, who may be suffering from life-threatening illnesses.
Having access to this information sooner would enable clinicians to make quicker, more informed decisions, on care – including whether to use antibiotics. Proper use of antibiotics has a strong relationship with positive patient outcomes.
First author Davide Ferrari, King's College London, said: "Our study provides further evidence on the benefits of AI in healthcare, this time relating to the crucial issues of antimicrobial resistance and bloodstream infections. It comes at an important time, as the NHS is investing in shared data resources, helping to make patient care more collaborative and efficient.
"Our use of machine learning provides a new way of tackling the important clinical issue of antimicrobial resistance. We hope that the AI will provide a useful tool for clinicians in making important decisions, particularly in relation to ICU."
Dr Lindsey Edwards, expert in microbiology at King's College London added: "An important way to tackle the grave threat of antimicrobial resistance is to protect the antibiotics we already have, which goes hand in hand with the urgent need for fast diagnostics. Often patients with a drug-resistant infection will present to ICU in a critical condition and may not survive long enough for the current gold standards of diagnostics to determine what they are infected with. So, clinicians are faced with a difficult situation where they must prescribe 'in a blinded fashion' a broad-spectrum antibiotic to save the patient.
"However, this will also kill many of the beneficial microbes in the patient's microbiome, without killing the harmful pathogen. It could even make the pathogen more resistant to the drug.
"The findings of this study are incredibly promising as using AI to speed up the diagnostics of infection to allow for prescription of the correct antibiotic could not only have a huge impact on the patient's survival and their care outcomes; but could help to preserve the antibiotics we already have developed and prevent the development of further antibiotic resistance."
Data from 1,142 patients at Guy's and St Thomas' NHS Foundation Trust were used in this study, which has paved the way for further ongoing research using datasets of more than 20,000 individuals. It is hoped that a more advanced approach to this study, particular within a multi-hospital setting through the popular technology of Federated Machine Learning, could fulfil the regulatory requirements for an actual deployment of this AI approach in the front line of the NHS.
Professor Yanzhong Wang, expert in population health at King's College London, added: "The simplicity and scalability of this innovative machine learning approach indicate its potential for widespread implementation, offering a robust solution to address these critical healthcare issues on a larger scale and ultimately improve patient outcomes.
