Results from a large-scale international clinical trial led by researchers at University College London (UCL) and the London School of Hygiene and Tropical Medicine (LSHTM) show that AI technology is effective in planning life-saving radiotherapy for cervical and prostate cancer.
94% of cervical cancer deaths occur in low- and middle-income countries (350,000 women will die in 2022). Radiotherapy is the main treatment modality, but currently only 10% of people in low-income countries who require radiotherapy receive it (in middle-income countries, this figure is 40%), and the lack of skilled professionals is one of the major barriers.
Researchers say AI technology can save time and money by quickly creating high-quality radiation treatment plans, and help bridge the workforce gap so more people can receive treatment and be cured.
The trial, called ARCHERY, was conducted in hospitals in India, South Africa, Jordan, and Malaysia and involved more than 1,000 cancer patients with three major cancers: cervical cancer, prostate cancer, and head and neck cancer. We assessed whether AI technology could enable international best practice radiotherapy planning, typically carried out by oncologists and physicists, and could be used in all resource settings, including countries such as the UK.
Planning for radiation therapy involves several complex steps that often require long work by oncologists (to delineate the tumor on CT scans as well as identify areas at risk of tumor spread and areas of healthy tissue at risk of radiation damage) and physicists (to determine the optimal location, size, and shape of the radiation beam). The AI-based software does this automatically by identifying the target structure and determining the optimal radiation beam configuration. This has traditionally been a task that would take days or weeks.
The new research, presented at the European Society of Radiation Therapy Oncology (ESTRO) conference in Stockholm, found that AI technology can plan high-quality radiation treatments in more than 95% of cervical cancer cases.
In the case of prostate cancer, this technique planned high-level radiotherapy in 85% of cases, which is still considered suitable for routine use in clinical practice. Results for head and neck cancer are expected later this year.
These results demonstrate that this AI technology achieves very high standards when it comes to cervical cancer, supporting routine use in hospitals around the world. By doing so, you can contribute to the World Health Organization’s Cervical Cancer Eradication Program. It can also be used to support the delivery of prostate cancer treatment in any national setting. ”
Ajay Agarwal, Principal Researcher and Professor, London School of Hygiene and Tropical Medicine
Agarwal further added, “In a typical workflow, radiation therapy planning can take many hours over several weeks, depending on the availability of specialized staff. This AI technology can reduce that time to just over an hour. This is important because it has the potential to reduce wait times and expand access to this life-saving treatment.”
Professor Mahesh Parmar, co-investigator and director of the UCL Institute of Clinical Trials, said: “Radiotherapy is at the heart of cancer treatment, curing 40 per cent of cancer cases. However, millions of people around the world do not have access to radiotherapy. If radiotherapy were available, more than a million lives could be saved each year.”
“Our trial also fills an important gap in rigorously testing AI technologies for cancer treatment. Unlike our trial, trials testing AI tools are often small, conducted in only one center, and can have a high risk of bias. They are rarely conducted outside of high-income countries, where the need is often greatest.”
“This trial highlights the importance of providing the best available evidence to support the implementation of the most promising AI technologies to improve health outcomes at scale.”
ESTRO Chairman Professor Matthias Guckenberger, from the University Hospital Zurich in Switzerland, said: “Radiotherapy is an essential tool in the treatment and cure of cancer. It is a highly precise treatment, meaning that tumors can be carefully targeted without damaging other parts of the body. The cost of radiotherapy equipment can be high, but when used effectively the benefits to cancer patients are immeasurable.”
“The results of the ARCHERY trial show that artificial intelligence can be used to plan treatment for cervical cancer patients. Treatments planned with the help of AI are reviewed by experts and in most cases they turn out to be correct and have the potential to successfully treat patients. The use of AI is also likely to speed up the process of treatment planning and implementation.”
“Using AI in this way could not only help treat and cure more cancer patients, but also save hospitals time and resources. In low-resource countries, where there may not be enough radiotherapy equipment to treat all the patients who need it, there are clear benefits to improving the efficiency of cancer services. But AI can also be leveraged to increase the efficiency of cancer services around the world.AI We know that AI has tremendous potential in medicine, but for AI to prove its effectiveness, we need large-scale trials like this one, with patients in several countries around the world, to truly benefit patients and their doctors.” ”
The ARCHERY trial is funded by the US National Institute for Health Research (NIH), the Rising Tide Foundation and the UK Medical Research Council. It was designed and run by the UCL Innovative Clinical Trials Unit.
The AI technology, known as Radiation Therapy Planning Assistant, was developed by Professor Lawrence Cote and his team at the University of Texas MD Anderson Cancer Center.
sauce:
university college london
