Dr. Ashleigh Myall
May 11th, 2025
Infection Prevention and Control (IPC) is the quiet engine behind providing safe, high-quality healthcare (World Health Organisation, n.d.). From containing local flu outbreaks to stopping the spread of highly drug-resistant bacteria, IPC protects vulnerable patients, healthcare staff, and the entire system from preventable harm. Yet, in many hospitals today, IPC remains reactive, responding to problems after they emerge rather than anticipating and preventing them.
Healthcare-Associated Infections: The Persistent Threat
Healthcare-associated infections (HCAIs) are infections patients acquire while receiving care (Centers for Disease Control and Prevention, n.d.). Preventing these infections is the core mission of IPC teams. But the challenge is vast: In Europe alone, 5 million HCAIs are estimated to occur in acute care hospitals annually, representing around 25 million extra days of hospital stay and a corresponding economic burden of €13–24 billion (World Health Organization, 2009). Despite over half of these infections being preventable, they remain commonplace in hospitals (European Centre for Disease Prevention and Control, 2018).
The Limits of a Reactive Infection Control
The foundation of effective IPC is situational awareness—knowing where problems are emerging so you can act quickly to prevent them from worsening. Yet today’s surveillance methods rely on a fragmented and reactive toolkit:
Point prevalence surveys offer only periodic snapshots, estimating infection burden at the population level rather than identifying specific individuals at risk.
Universal screening is comprehensive but often prohibitively expensive. It’s typically implemented in limited areas, fails to adapt to population movement, and lacks real-time responsiveness.
Ad-hoc screening, triggered by clinical suspicion or contact tracing, is inconsistent and prone to human bias.
Risk factor–based screening is more cost-effective but often too rigid to reflect changing local risks or emerging threats.
These approaches can help detect infections—but often only after acquisition has occurred. As a result, hospitals miss critical windows to intervene early, contain outbreaks, and reduce patient harm.
Predictive Surveillance: A Shift in Mindset
What if hospitals could know where the infections were before they appeared? Imagine knowing which patients are most likely to develop a highly resistant, multidrug-resistant infection in the coming days. Imagine identifying which wards are likely to experience a cluster before it happens. This is the promise of predictive surveillance.
We already see this approach in public health. Organisations like Bluedot (BlueDot, n.d.) use predictive models to detect and track emerging outbreaks—from flu to COVID-19—often days or weeks before traditional reporting catches up (Niiler, 2020). Now, hospitals can bring this intelligence inside their walls.
What Is Predictive Surveillance?
Predictive surveillance uses advanced algorithms to forecast infection risk at the individual, ward, or hospital level. It doesn't just describe what's already happened (retrospective reporting) or what is happening now (real-time dashboards, like Baxter's ICNET (Baxter International Inc., n.d.) and Epic System's Bugsy (Epic Systems Corporation, n.d.))—it tells you what’s likely to happen next.
Think of it as a clinical radar system: scanning current conditions and projecting forward, so IPC teams can act early and prevent infections before they escalate.
Graphic of 'clinical radar system', scanning for current infections and projecting forward, so IPC teams can act early and prevent infections before they escalate.
What It Enables
Predictive surveillance empowers IPC teams to make smarter, faster decisions by identifying risk in real time. It enables:
With predictive insights, IPC moves from broad protocols to precision interventions—taking action before infections emerge, not after.
Evidence of Capability
Early trials have shown strong performance. For instance, models have achieved high accuracy in forecasting hospital-onset infections (Myall et al., 2022), and recent real-world deployments are demonstrating that such models can identify high-risk patients and locations up to 5–7 days in advance (Vasikasin et al., 2025). These tools are already helping reduce delays in response, improve screening efficiency, and limit the spread of resistant pathogens.
A Dynamic, Precision Surveillance Strategy
Unlike static screening protocols, predictive surveillance continuously adapts to evolving risk within the hospital. It enables IPC teams to deploy limited resources where they’ll have the greatest impact—screening the right patients in the right locations and times. This results in:
Predictive surveillance also improves frontline compliance by making interventions more targeted and manageable, supporting effective prevention in both high- and low-prevalence settings.
Predictive IPC is only the beginning. As hospitals become more digitised, the real opportunity lies in connecting systems and layering intelligence, leveraging different data sources together to generate deeper insights and enable faster, more effective responses.
Genomic sequencing – to identify, track, and trace resistant organisms in real time (Genpax Ltd., n.d.).
Clinical notes – using natural language processing to extract early signals from unstructured data (Wu et al., 2025).
Next-generation diagnostics – combined with live surveillance for immediate decision support.
Spatial modelling – to understand transmission dynamics and risks based on ward layout and patient movement (Venkatachalam et al., 2023).
RFID and sensor networks – to map contact patterns among patients, staff, and equipment (Proxximos Limited, n.d., and Cadi Scientific Pte Ltd, n.d.).
Antimicrobial stewardship systems – to optimise prescribing and reduce resistance pressures (Rawson et al., 2024).
Together, these components will create an intelligent, adaptive infection control ecosystem—one that continuously learns, improves, and scales. The goal: fewer infections, faster responses, and a more resilient healthcare system.
Putting Prevention at the Heart of IPC
Too often, Infection Prevention and Control focuses on control alone—responding after infections occur. But with predictive tools now available, we can flip the script. The future of IPC is prevention-first, data-led, adaptive, and designed to stop infections before they escalate.
References
World Health Organization. (n.d.). Infection prevention and control. Retrieved May 11, 2025, from https://www.who.int/teams/integrated-health-services/infection-prevention-control
Centers for Disease Control and Prevention. (n.d.). Healthcare-associated infections. Retrieved May 11, 2025, from https://www.cdc.gov/healthcare-associated-infections/index.html
World Health Organization. (2009). WHO guidelines on hand hygiene in health care: first global patient safety challenge clean care is safer care. Geneva: World Health Organization. Retrieved May 11, 2025, from https://www.ncbi.nlm.nih.gov/books/NBK144030/PMC
European Centre for Disease Prevention and Control. (2018). Healthcare-associated infections – a threat to patient safety in Europe. Retrieved May 11, 2025, from https://www.ecdc.europa.eu/en/publications-data/infographic-healthcare-associated-infections-threat-patient-safety-europe
BlueDot. (n.d.). BlueDot: The world's most trusted infectious disease intelligence. Retrieved May 11, 2025, from https://bluedot.global/
Baxter International Inc. (n.d.). ICNET Clinical Surveillance Software. Retrieved May 11, 2025, from https://www.icnetsoftware.com/icnetsoftware.com+6
Epic Systems Corporation. (n.d.). Acute and Inpatient Care. Retrieved May 11, 2025, from https://www.epic.com/software/acute-and-inpatient-care/
Myall, A., Price, J.R., Peach, R.L., Abbas, M., Mookerjee, S., Zhu, N., Ahmad, I., Ming, D., Ramzan, F., Teixeira, D. and Graf, C., 2022. Prediction of hospital-onset COVID-19 infections using dynamic networks of patient contact: an international retrospective cohort study. The Lancet Digital Health, 4(8), pp.e573-e583. https://doi.org/10.1016/S2589-7500(22)00093-0
NEX Health Intelligence. (2025). Clinical report: Predictive infection surveillance in a 1,200-bed national military hospital. Retrieved May 11, 2025, from https://www.nex-intelligence.org/case-study-pmk-2025
Genpax Ltd. (n.d.). Genpax: Infectious disease surveillance. Retrieved May 12, 2025, from https://www.genpax.co/
Wu, J.T., Langford, B.J., Shenoy, E.S., Carey, E., & Branch-Elliman, W. (2025). Chatting new territory: large language models for infection surveillance from pilot to deployment. Infect Control Hosp Epidemiol, 1–3. Advance online publication. https://doi.org/10.1017/ice.2025.20
Venkatachalam, I., Conceicao, E.P., Sim, J.X.Y., Whiteley, S.D., Lee, E.X.W., Lim, H.S., Cheong, J.K.M., Arora, S., Fang, H.S.A., & Chow, W. (2023). Three-dimensional disease outbreak surveillance system in a tertiary hospital in Singapore: A proof of concept. Mayo Clinic Proceedings: Digital Health, 1(2), 172–184. https://doi.org/10.1016/j.mcpdig.2023.04.001
Proxximos Limited. (n.d.). Proxximos: A digital solution for infection prevention & control. Retrieved May 11, 2025, from https://proxximos.com/
Cadi Scientific Pte Ltd. (n.d.). Cadi Scientific: Solutions Designed for Healthcare. Retrieved May 11, 2025, from https://cadi.com.sg/
Rawson, T.M., Zhu, N., Galiwango, R., Cocker, D., Islam, M.S., Myall, A., Vasikasin, V., Wilson, R., Shafiq, N., Das, S. and Holmes, A.H., 2024. Using digital health technologies to optimise antimicrobial use globally. The Lancet Digital Health, 6(12), pp.e914-e925. https://doi.org/10.1016/S2589-7500(24)00198-5
