The Royal Free Hospital and North Middlesex University Hospital have shared how the use of an AI contouring tool has helped to reduce time spent on manual processes and repetitive tasks within their radiography department.
The AI software is being used to automate contouring within radiotherapy, replacing a manual process to outline specific areas within the body and the organs at risk.
Mark Prentice, clinical lead for radiotherapy, explained this is a “very time-consuming process, and it is getting more time-consuming as we find ourselves able to treat more complicated cancers with radiotherapy.” By automating this process, both organisations have been able to deliver “quicker treatment and focus more on patient care”.
The system has been in use in North Middlesex for the past three years, where it has reportedly seen a 60 percent reduction in time spent on contouring organs at risk and has saved 3.5 hours a week in breast treatment alone. It was introduced to RFH over the summer, with hopes that it will help to reduce manual workloads and increase turnaround times for treatment planning.
According to the Royal Free Hospital, the AI system was trained on large datasets and “uses advanced algorithms to automatically generate accurate contours based on medical imaging data”. Further audits have been planned for both organisations, so they continue to review how AI could be used to support other innovation and help “shape the future of cancer treatment”.
This follows the launch of a virtual fracture clinic at North Middlesex University Hospital that went live earlier in the year with the aim to “improve patient experience and boost efficiency”. The clinic was set up to support patients following a scan for a fracture or a minor injury, aiming to reduce physical follow-up appointments where possible.
Using AI to automate healthcare processes: the wider trend
Great Ormond Street Hospital for Children NHS Foundation Trust has gone live with the AI scribing tool TORTUS across outpatient services, with the aim to “enhance patient care through digital innovation” and support clinicians with documentation. Based on a recent trial, some of the main benefits that have been noted include more time spent on face-to-face interactions, less time spent on admin tasks and improved accuracy and efficiency in clinical notes.
A team of researchers at Imperial College Healthcare NHS Trust have created an AI tool designed to read ECGs and support doctors to identify those at risk of developing the potentially fatal heart condition, heart block. AIRE-CHB is an AI tool that has been trained on over 1.1 million ECG heart recordings from 190,000 patients in Boston and tested on a further 50,000 people from the UK. It’s said to detect the earliest signs of heart block and identify patients who will encounter problems later on in life if the condition is left untreated.
Teams from Moorfields Eye Hospital NHS Foundation Trust and the University College London Institute of Ophthalmology have developed an AI tool capable of predicting patients at risk of developing retinopathy. Trained using more than 8,000 eye scans from 409 patients in the US and UK, the HCQuery algorithm works by analysing retinal images captured using optical coherence tomography, a standard part of screening for hydroxychloroquine patients. It correctly identified 100 percent of patients with retinopathy up to 2.74 years earlier than doctors, according to Moorfields.
