INF ECTION P R EVENTION
AI becoming ‘weapon’ in fight against HCAIs
John Langton, PhD, argues that AI holds huge potential in infection prevention. The technology could have a major impact on identifying patients at most risk of infections, as well as improving patient outcomes – from the management of sepsis, to reducing rates of C.difficile.
A huge amount has been claimed about the power of artificial intelligence (AI) in medicine, much of it sounding more like science fiction than real-world healthcare. One of the problems has been a misalignment between the two main camps in the debate – technologists and the doctors. I have always argued that you need a connector between the two, experts who can harness the power of big data and advanced analytics and apply it in a real clinical setting, with a tangible impact. When AI first came into our lives, some feared that daily tasks, and perhaps even our doctors, would one day be replaced by robots. Now, we can step back and make a more informed assessment. The truth is that many of the most interesting and impactful areas where AI is making a difference in healthcare are not all futuristic. They are often ingenious solutions that work away in the background, using the power of modern data analytics to solve some of the most doggedly stubborn problems.
The battle against infection Fighting hospital infection is a case in point. For years, hospitals across the world have battled against the hidden but deadly enemy of healthcare-associated infections (HCAIs). Figures from 2016/171
show that NHS
hospitals in England (with the addition of specialist hospitals) encountered 834,000 HCAIs in 2016/2017, costing the NHS £2.7 billion. These infections caused 28,500 patient deaths and accounted for 7.1 million occupied hospital bed days. This is equivalent to 21% of the annual number of bed days across all NHS hospitals in England. As if this was not bad enough, HCAIs also strike down hospital front- line staff, accounting for 79,700 days of absenteeism per year. Of course, the COVID-19 pandemic has taken the issue of infection control to a new crisis level, increasing the urgency even more to find new, impactful solutions. Luckily, infection prevention plays
perfectly into the work that AI does best – spotting patterns in vast amounts of seemingly unconnected data, with the potential to save billions in healthcare costs. The application of AI to infection prevention also addresses a wider culture shift occurring in medical research. A traditional approach to finding the solution to a hospital infection problem may have been to conduct randomised control trials, where you might compare results among 30 people. With big data, you can analyse the data from Electronic Medical Records (EMRs) of 800 hospitals, finding patterns in data from millions of patients. It is a fundamentally different approach that is disrupting established methods of research and producing transformational results.
How does it work? So, how can AI be used to combat hospital infections? By analysing multiple variables and connecting the dots across data taken from EMRs, AI can provide an early warning of the patients most at risk of infection. This allows clinicians to proactively prevent infections before they start to spread. The power of machine learning is that it deals with more than the binary risk assessment that humans commonly perform in their heads. The human brain can only look at a small set of variables and how they might factor with the other. This means we are naturally limited in terms of the complexity of situations we can address. In contrast, AI can interrogate a huge number of inputs: lab results, white blood cell count, bilirubin, neutrophils, vital signs, medicine administration, concentrations and durations of meds, duration in hospital, demographics about the patients and demographics on a hospital – to name a few. Machine learning can look at hundreds of these things – and the hundreds of correlations among them – which can point
62 l
WWW.CLINICALSERVICESJOURNAL.COM MAY 2021
©maxsim -
stock.adobe.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80
