Infection prevention
AI: an opportunity to strengthen IPC
In this article, Professor Tim Sandle considers how artificial intelligence could be used to tackle infection control in hospitals, the UK implementation landscape, the benefits and accuracy of the technology, and potential challenges ahead.
Healthcare-associated infections remain among the most persistent safety challenges in acute care. In England, enhanced mandatory surveillance covers Clostridioides difficile infection (CDI), methicillin-resistant Staphylococcus aureus (MRSA), methicillin- susceptible S. aureus (MSSA), E. coli, Klebsiella spp. and P
. aeruginosa, and these data inform
both local action and national benchmarking.1 Recent UKHSA reporting indicates that this burden remains substantial and, for several pathogens, is worsening rather than improving. In financial year 2024/25, E. coli bacteraemia reached 76.6 cases per 100,000 population, Klebsiella species 23.6 per 100,000, MRSA bacteraemia 1.9 per 100,000, and CDI 33.3 per 100,000, the highest CDI incidence since financial year 2011/12.2 The NHS policy response is correspondingly
strong. NHS England maintains a National Infection Prevention and Control Manual for England and sets quality requirements around minimising CDI and Gram-negative bloodstream infections;3
UKHSA provides both surveillance
dashboards and epidemiological commentary to support local and national oversight. At the same time, UKHSA’s antimicrobial-resistance and HCAI programmes explicitly identify surveillance, epidemiology and data modelling as essential tools for identifying risks and evaluating intervention impact. AI, therefore, enters not as an abstract innovation but as a candidate technology within an already data- rich policy environment.4
The case for AI in IPC derives from a practical limitation of conventional systems: infection surveillance and intervention often remain partly retrospective, labour-intensive and, often, weakly targeted. Traditional dashboards may identify that an organisation has a CDI problem, but they do not necessarily identify which ward, patient subgroup or antimicrobial-exposure pattern is driving the increase until after harm has occurred. AI is attractive because it can convert high-volume, multi-source data into earlier predictions, automated case detection, behavioural measurement and decision support for clinicians, microbiologists and IPC teams. This review examines how AI can be used
to tackle infection control in hospitals, with a primary focus on the UK. Particular attention is paid to four technical domains: AI development, data structuring, interpretation of AI outputs, and tracking measurable improvement. International examples are referenced where they clarify implementation or outcome assessment, but the principal perspective is NHS applicability.
Methods This article provides a narrative review. Sources were selected to cover: l UK regulatory and surveillance infrastructure. l Recent peer-reviewed evidence on AI in hospital infection prevention.
l UK implementation examples. l Selected international studies reporting real- world outcomes or implementation lessons.
Searches and source selection drew on contemporary UKHSA, NHS England and NHS Digital resources, together with recent reviews and primary studies published during 2024–2026 on AI in infection control, hand-hygiene monitoring, automated surveillance, CDI risk prediction and antimicrobial resistance (AMR) forecasting.5 Priority was given to sources relevant
to acute hospital practice and to those containing information on model development, implementation or measurable outcomes. International studies were retained where they provided methodological insights likely to transfer to NHS settings – for example, AI-based hand-hygiene measurement or CDI-targeted stewardship workflows. Given the translational immaturity of the field, non-peer-reviewed UK implementation reports were used cautiously.
Epidemiological context and need in the UK The contemporary English HCAI picture creates a clear use case for data-driven IPC. UKHSA’s annual commentary for FY2024/25 reported that E. coli bacteraemia increased by 17.0% between FY2020/21 and FY2024/25, while MRSA increased
September 2026 I
www.clinicalservicesjournal.com 19
AI with young man
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