Technology
Role of AI in tackling sepsis and AMR
Dr. Mark Gostock and Dr. Iain Miller discuss the potential for artificial intelligence and machine learning technology to support early diagnosis of sepsis and reduce antimicrobial resistance.
In a world where our healthcare services face rising demand, and where our healthcare workforce is struggling to meet the needs of its patients, technology is a critical solution to bettering our healthcare system. We are fortunate to be living in a period of rapidly advancing medical science, and labs all around the world are brimming with promising innovation that has huge potential to continue to make major breakthroughs that will improve the way patients are treated, and how staff in the sector carry out their jobs.
AI and machine learning in healthcare Some of the latest technological advances that have exploded into the public sphere are Artificial Intelligence (AI) and Machine Learning (ML), and they are set to be crucial when it comes to improving our healthcare practices: the World Economic Forum recently named AI-facilitated healthcare one of the top 10 emerging technologies of the past year.1 After COVID-19 revealed many of the pressure points in our healthcare systems, we’re seeing Governments invest in AI for healthcare to help improve efficiencies, as well as tackle some of the biggest health challenges of our generation. The UK Government has made it clear that AI, and pioneering technology in general, is an area of keen interest, having hosted the world’s first global AI Summit last year and designating AI as a critical technology in last year’s Science and Technology Framework. This has been reflected in the healthcare sector, with Rishi Sunak announcing a £100m fund to accelerate the use of AI in life sciences and healthcare at the end of 2023.
AI and ML can have an impact across many
different areas, including clinical decision support, self-care, chronic care management, and care delivery: all identified by McKinsey as areas where these technologies could have the most beneficial impact directly on patients.2
medical professionals to efficiently identify or rule out life changing illnesses, so that the correct care can be given.
But
one of the most exciting - and life-saving - areas of impact is on triage and diagnosis, enabling
Infection and sepsis diagnosis through advanced technology AI and ML technology is currently being developed to support the diagnosis of sepsis. According to the UK Sepsis Trust, every three seconds, someone in the world loses their life to sepsis, the ultimate cause of infection-related mortality. In the UK alone, 245,000 people are affected by sepsis, with at least 48,000 people losing their lives due to sepsis-related illnesses every year. This is more than breast, bowel and prostate cancer combined. The current standard of diagnostic care for infections and sepsis in particular is slow, taking up to three days, and lacks accuracy, with only 50-70% of diagnoses being accurate. Given early detection is ultimately crucial for initiating the appropriate interventions, the delay and imprecision in diagnosis can lead to poor patient outcomes and increased mortality rates. Late and imprecise diagnosis
can also cause clinicians to prescribe broad- spectrum antibiotics on suspicion, rather than confirmation of infection. However, up to 50% of patients initially managed as sepsis in the emergency department (ED) do not have a final diagnosis of sepsis and often do not have an infection, and it is predicted that 20-79% of antibiotics in diverse inpatient, Emergency Department and ICU populations are inappropriate or unnecessary.3 This can contribute to antibiotic overuse, leading to Anti-Microbial Resistance (AMR), which has been declared by the World Health Organization (WHO) as one of the top 10 global public health threats, currently contributing to 5 million deaths annually. Unnecessary antibiotic use also costs the NHS £329 million per year.4 Presymptom Health recognised that enhanced infection and sepsis diagnosis was a critical pressure point in our healthcare systems; and its AI technology, currently undergoing clinical trials, aims to better support early diagnosis, and empower clinicians to be more confident in their diagnoses, saving lives, and reducing unnecessary prescription of
June 2024 I
www.clinicalservicesjournal.com 69
t
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 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88
