Imperial College London

Academic Institute

Nagy Habib

Unknown

No

NIBDAPC_2024_0041

A surgical site infection (SSI) is a type of hospital-acquired infection that occurs in the incision created by an invasive surgical procedure. It can either affect the local area around the wound or inside the cavity where the operation is taking place (i.e. the abdomen in gallbladder surgery). SSIs are a frequent complication after surgery, affecting about 2-5% of patients. They can lead to serious health issues, such as pain, sepsis and even death. This is associated with delays in recovering from an operation, and an increase hospital costs. In the UK, SSIs make up almost 20% of all hospital-acquired infections and place a strain on the NHS. Preventing SSIs early could improve patient outcomes and reduce hospital costs, but predicting which patients are most at risk is challenging. This project will develop a data-driven tool to help healthcare teams identify patients most likely to develop SSIs. Using detailed patient data from the iCARE database we will analyse factors like patient age, health conditions, type of surgery, and recovery progress. By applying machine learning (a type of artificial intelligence) the project will create a predictive model that estimates SSI risk for each patient. This model will categorise patients by risk level, helping clinicians decide who might benefit from extra precautions like antibiotics, improved wound care, and close monitoring. The goal of this tool is to support better prevention of SSIs, helping patients recover more quickly and reducing the burden of infections on the NHS. This work could also provide insights for improving prediction of other types of hospital-acquired infections.

Surgical site infections (SSIs) represent a significant burden for patients, healthcare systems, and society at large. This research question addressing the development of a machine learning algorithm to predict SSIs is a priority for several compelling reasons. The identification and prioritisation of this as a research topic has been developed in-line with a prior James Lind Alliance Priority Setting Partnership on healthcare-associated infections (HAIs). The following was determined as Priority 1 in this process: ‘How can infections be identified early?’ As further explained within the rationale for the priority, early identification of infection can help with early treatment and avoid unnecessary treatment in people without infection. It can also help with isolation of people who carry communicable infections in hospital. Further studies are necessary to find out how these infections can be detected early. This proposal aims to address this question through developing a machine learning algorithm to predict SSI risk. The prevention and early detection of SSIs have been identified as key priorities by several stakeholders and guideline bodies: • The World Health Organisation (WHO) has highlighted SSI prevention as a global priority in its efforts to promote safer surgery. • In the UK, the National Institute for Health and Care Excellence (NICE) has issued guidelines emphasising the importance of SSI prevention and early detection, as well as antimicrobial stewardship. International data suggests that SSIs are one of the most common causes of HAIs. In the UK, they account for anywhere up to 20% of HAIs(3). SSIs are even more common in less-economically developed countries. SSI is implicated in one-third of postoperative deaths and accounts for 8% of all deaths caused by HAIs. Furthermore, SSIs cause pain and discomfort, increase hospital stay and put patients at greater risk of secondary infectious complications. This project aims to help identify those at risk of SSIs at an earlier stage in their care pathway and with improved accuracy compared to clinician assessment. If successful, this could be used to augment the care delivered to patients helping to speed up recovery from an operation and avoid the risk of complications and death associated with SSIs. This has an important economic impact with the additional cost of treating each infected patient estimated to be £10,523. The total costs to healthcare services across Europe are estimated to be between €1.47–19.1 billion. The NHS in England has set targets to reduce HAIs, including SSIs, and the threat of antimicrobial resistance as part of its Patient Safety Strategy. Many healthcare facilities aim to achieve SSI rates below international benchmarks, which vary by procedure type. Developing a machine learning algorithm to predict SSIs using de-identified patient data has the potential to: • Enable early intervention and prevention strategies • Reduce the incidence of SSIs and their associated complications • Decrease healthcare costs and improve resource allocation • Enhance patient outcomes and satisfaction through identifying patients who are at risk of SSI, allowing for changes in the delivery of care which reduce the complications associated with SSIs • Improve collective goals towards reducing the impact of antimicrobial resistance. By addressing this research question, we can contribute to the ongoing efforts to reduce SSIs, aligning with priorities set out in the UK by NHS England and internationally by WHO for improving patient safety and healthcare quality.

Public Health Research

16/01/2025

02/01/2025

De-Personalised

Not applicable

Not applicable

One-off

16/01/2025

TRE