Using AI Within Digital Wound Monitoring of Surgical Wounds to Prioritise Non-healing Wounds for Urgent Review
- Conditions
- Wound Healing DelayedSurgical WoundHeart; Surgery, Heart, Functional Disturbance as Result
- Interventions
- Other: Standard follow-upDevice: Isla wound prioritisation module
- Registration Number
- NCT06475703
- Lead Sponsor
- Guy's and St Thomas' NHS Foundation Trust
- Brief Summary
The goal of this clinical trial is to learn if artificial intelligence within digital wound monitoring of surgical wounds can prioritise non-healing wounds for urgent review in patients having first/redo CABG surgeries with or without additional cardiac procedures; could include any of the following: any gender, age ≥18. The main question it aims to answer is:
Can investigators successfully develop artificial intelligence to prioritise images of patients' surgical wounds that are failing to heal or are infected, in order to facilitate early treatment?
Researchers will compare the wound prioritisation module with standard care to determine safety and acceptability outcomes.
Participants from the control group will:
* Have standard post-operative wound care follow-up at day 30 (survey, interview and phone call)
* Have standard post-operative wound care follow-up at day 60 (phone call)
Participants from the intervention group will:
* Use platform with new AI prioritisation module for 30 days after surgery
* Be contacted via SMS text message seven days, fourteen days and twenty-one days after surgery with the link request remaining open for 6 days until the next request is sent out
* Submit a photo of their wound and complete the UKHSA wound surveillance questionnaire
* Have standard post-operative wound care follow-up at day 30 (survey, interview and phone call)
* Have standard post-operative wound care follow-up at day 60 (phone call)
- Detailed Description
Background and study aims Over 10 million surgical operations are performed in England annually with approximately 2.1 million having problems with wound healing, of which 500,000 lead to infection. Most of these wound problems happen after patients have been discharged from the hospital. They need to be identified and treated early to prevent the problem from worsening.
Digital remote surgical wound monitoring is beginning to be used to monitor patients' surgical wounds at home after discharge from the hospital. This offers regular assessment when wound problems are most likely to develop. Early evaluations of digital wound monitoring suggest it improves clinical outcomes and has high patient satisfaction; however, it creates a new additional workload for clinicians.
Who can participate? Patients ≥18 years old having first/redo coronary artery bypass graft (CABG) surgeries with or without adjunct cardiac procedures such as valve replacement, or chest reopening during same admission as index surgery, and either no infection, or an existing non-infected wound complication, or any other infection except surgical site, at any of two recruitment sites (St Bartholomew's Hospital, London and Freeman Hospital, Newcastle). Patients without a smartphone/with physical disability/with visual impairment will be eligible if they are willing to use a smartphone or internet provided by the study, or their next of kin or carer is able-bodied or has a smartphone.
What does the study involve? The study will assess a new component for a digital wound monitoring platform, which has been developed and has recently received HRA approval to be validated for predictivity, sensitivity and specificity, and inter-rater reliability. The new component uses artificial intelligence (AI) to identify 'red flags' on the images patients submit to the wound monitoring platform. Images that have a possible red flag are then identified for urgent priority review. This helps clinicians manage this new workload by allowing the most urgent cases to be reviewed first.
A total of 120 patients in two hospitals will be invited to take part in the study. All participants (patients who take part) will receive normal wound care follow-up after surgery, and half of the participants will also receive the digital wound monitoring system with the AI to identify wounds which need urgent assessment.
What are the possible benefits and risks of participating? Participants allocated to the digital wound monitoring with AI may benefit from regular and ongoing wound assessment. Participants allocated to standard wound care may not receive additional direct benefits. This study will help improve the approach to Wound care.
There are no foreseeable disadvantages involved with taking part since all participants will receive their usual standard wound care follow-up. Being involved will require participants to give some of their own time.
Where is the study run from? This study is a collaboration of researchers and surgeons across the country. It is co-ordinated by Derby Clinical Trials Support Unit, on behalf of the Sponsor, Guys and St Thomas' NHS Foundation Trust (UK)
When is the study starting and how long is it expected to run for? December 2023 to December 2025
Who is funding the study? National Institute for Health and Care Research (NIHR) (UK)
Recruitment & Eligibility
- Status
- ACTIVE_NOT_RECRUITING
- Sex
- All
- Target Recruitment
- 120
- Patients having first/redo CABG surgeries with or without adjunct cardiac procedures such as valve replacement, or chest reopening during same admission as index surgery, and either no infection, or an existing non-infected wound complication, or any other infection except surgical site.
- Patients without a smartphone/with physical disability/with visual impairment will be eligible if they are willing to use a smartphone or internet provided by the study, or their next of kin or carer is able-bodied or has a smartphone.
- Patients having CABG requiring ventricular assist device (VAD) or
- extracorporeal membrane oxygenation (ECMO), or
- ventilated or unconscious patients, or
- pre-existing surgical site infection.
Study & Design
- Study Type
- INTERVENTIONAL
- Study Design
- PARALLEL
- Arm && Interventions
Group Intervention Description Standard follow-up Standard follow-up Patients in the control group will have standard post-operative wound care follow-up for 60 days. Isla digital wound monitoring + Standard follow-up Standard follow-up Patients in the intervention group will be contacted via SMS text message seven days, fourteen days and twenty-one days after surgery with the link request remaining open for 6 days until the next request is sent out. The exception being the last request link which will remain open until 30 days after surgery. In the requests patients are asked to submit a photo of their wound and complete the UKHSA wound surveillance questionnaire. Participants can also submit an image during the 30 days whenever they have a concern. Isla digital wound monitoring + Standard follow-up Isla wound prioritisation module Patients in the intervention group will be contacted via SMS text message seven days, fourteen days and twenty-one days after surgery with the link request remaining open for 6 days until the next request is sent out. The exception being the last request link which will remain open until 30 days after surgery. In the requests patients are asked to submit a photo of their wound and complete the UKHSA wound surveillance questionnaire. Participants can also submit an image during the 30 days whenever they have a concern.
- Primary Outcome Measures
Name Time Method Prescribed wound treatments 30 days Analysis will be reported based on allocated treatment.
Quality of images assessed by clinicians, in percentages 30 days A quality image is one that can be used to make a clinical decision
Clinician satisfaction using interviews 30 days Acceptability of the intervention including attitude, burden, perceived effectiveness, ethicality, intervention coherence, opportunity costs and self-efficacy. Will also collect acceptability of being involved as a study participant. Survey variables that are continuous will be reported with means \& 95% confidence intervals (95% CI), if shown to be normally distributed, using a normality plot, otherwise will be reported with medians \& Interquartile Ranges (IQR). The categorical variables will be reported with frequencies \& percentages.
Patient satisfaction using interviews 30 days Acceptability of the intervention including attitude, burden, perceived effectiveness, ethicality, intervention coherence, opportunity costs and self-efficacy. Will also collect acceptability of being involved as a study participant. Survey variables that are continuous will be reported with means \& 95% confidence intervals (95% CI), if shown to be normally distributed, using a normality plot, otherwise will be reported with medians \& Interquartile Ranges (IQR). The categorical variables will be reported with frequencies \& percentages.
Quality of images assessed by clinicians, in frequencies 30 days A quality image is one that can be used to make a clinical decision
Clinician satisfaction using surveys 30 days Acceptability of the intervention including attitude, burden, perceived effectiveness, ethicality, intervention coherence, opportunity costs and self-efficacy. Will also collect acceptability of being involved as a study participant. Survey variables that are continuous will be reported with means \& 95% confidence intervals (95% CI), if shown to be normally distributed, using a normality plot, otherwise will be reported with medians \& Interquartile Ranges (IQR). The categorical variables will be reported with frequencies \& percentages.
Patient satisfaction using surveys 30 days Acceptability of the intervention including attitude, burden, perceived effectiveness, ethicality, intervention coherence, opportunity costs and self-efficacy. Will also collect acceptability of being involved as a study participant. Survey variables that are continuous will be reported with means \& 95% confidence intervals (95% CI), if shown to be normally distributed, using a normality plot, otherwise will be reported with medians \& Interquartile Ranges (IQR). The categorical variables will be reported with frequencies \& percentages.
Recruitment rate (number and percentage of eligible patients recruited to the study). Patients who were consented but not randomised will not be included in the recruitment rate. 30 days Recruitment rate (including access and barriers to recruitment and willingness to be randomised) will be assessed as a percentage of all eligible patients, regardless of treatment allocation.
Adherence with the module (intervention group only). Adherence will be reported as the number and percentage of adherent patients in the intervention group. 30 days To be adherent a patient needs to submit 1 photo within the 30 day period.
Loss to follow-up (number and percentage of intervention patients complete the study) 30 days Loss to follow-up will be assessed based on all randomised patients.
Number of wound problems/infections (in number and percentage) 30 days Analysis will be reported based on allocated treatment.
Quality of life survey using SF-6D v2 At baseline, 30 days, and 60 days Severity of wound problems/infections 30 days Analysis will be reported based on allocated treatment.
Wound-related hospital admissions (in number and percentage) 30 days Analysis will be reported based on allocated treatment.
Prescribed antibiotics (in number and percentage) 30 days Analysis will be reported based on allocated treatment.
Time to review images in minutes (intervention only) 30 days Analysis will be reported based on allocated treatment.
Further surgery to treat wounds in number and percentage 30 days Analysis will be reported based on allocated treatment.
Number of clinic visits in number and percentage 30 days Analysis will be reported based on allocated treatment.
Number of General Practice visits in frequency and percentage 30 days Analysis will be reported based on allocated treatment.
Patient travel time in minutes 30 days
- Secondary Outcome Measures
Name Time Method Number of follow-up requests (number and percentage) 60 days Feasibility outcome: access/barriers to participation using survey 60 days Reasons for compliance/non-compliance will be explored in the staff interviews 60 days Survey data will be analysed using descriptive statistics, and qualitative data from the interviews will be analysed using thematic analysis.
Feasibility outcome: access/barriers to participation using interviews 60 days Reasons for compliance/non-compliance will be explored in the staff surveys 60 days Survey data will be analysed using descriptive statistics, and qualitative data from the interviews will be analysed using thematic analysis.
Reasons for compliance/non-compliance will be explored in the patient intervention group surveys 60 days Survey data will be analysed using descriptive statistics, and qualitative data from the interviews will be analysed using thematic analysis.
Reasons for compliance/non-compliance will be explored in the patient intervention group interviews 60 days Survey data will be analysed using descriptive statistics, and qualitative data from the interviews will be analysed using thematic analysis.
Feasibility outcome: attrition rate in percentage 60 days Feasibility outcome: willingness of participants to be randomised in number and percentage 60 days Number of wound images/non wound images (number and percentage) 60 days Feasibility outcome: time (in minutes) to conduct telephone assessments to patients and phone calls to GPs to collect antibiotic data 60 days Feasibility outcome: resources to conduct telephone assessments to patients and phone calls to GPs to collect antibiotic data 60 days Number photos initiated by patients - intervention group only (number and percentage) 60 days Number of photos received per patient (number and percentage) 60 days Number of requests (for images) complied with - intervention group only (number and percentage) 60 days
Trial Locations
- Locations (2)
Freeman Hospital
🇬🇧Newcastle Upon Tyne, United Kingdom
St Bartholomew's Hospital
🇬🇧London, United Kingdom