As the National Health Service (NHS) approaches its 75th birthday, it continues to seek innovative solutions to modernize healthcare delivery and meet the evolving needs of society. One such advancement comes from Cambridge Universities Hospitals NHS Foundation Trust (CUH), where an artificial intelligence (AI) system called OSAIRIS is revolutionizing radiotherapy treatment planning and reducing waiting times for patients at Addenbrooke's Hospital.
Developed by and for the NHS, OSAIRIS empowers medical specialists by streamlining the preparation of scans, thereby significantly cutting the time patients have to wait between referral and treatment initiation. Working alongside this AI technology, specialists can plan radiotherapy treatments approximately two and a half times faster than if they were working alone. This improvement ensures that more patients can receive treatment sooner, ultimately enhancing the likelihood of better outcomes.
One critical aspect of radiotherapy treatment planning is the labor-intensive process of manually outlining healthy organs on scans, known as "segmentation." This step is crucial for protecting healthy tissues surrounding the cancerous area from radiation. Typically, it can take a doctor anywhere from 20 minutes to three hours to perform this task for each patient. However, with OSAIRIS, the AI system automates the segmentation process, freeing oncologists to focus on treatment planning. While the AI handles segmentation, the oncologist meticulously reviews each scan, ensuring accuracy and retaining control throughout the process.
Dr. Raj Jena, an oncologist at CUH and the driving force behind the research, explains, "OSAIRIS does much of the work in the background so that when the oncologist sits down to start planning treatment, most of the heavy lifting is done. It is the first cloud-based AI technology to be developed and deployed within the NHS, which we will be able to share across the NHS for patient benefit."
The journey to develop OSAIRIS spans a decade of collaborative research, including work with Microsoft Research on Project InnerEye. This Microsoft research effort focuses on developing machine learning and open-source software to assist clinicians in planning radiotherapy treatments. The Project InnerEye team conducted peer-reviewed research with eight clinical centers worldwide, demonstrating that clinicians using machine learning assistance could segment images significantly faster than manual methods, while maintaining accuracy comparable to human experts.
Supported by a £500,000 grant from the NHS AI Lab, Dr. Jena's team leveraged the open-source software technology from Project InnerEye and Azure Machine Learning to create OSAIRIS. Rigorous tests and risk assessments have been conducted to ensure the safe use of OSAIRIS in the day-to-day care of radiotherapy patients across the NHS. In "Turing tests," where doctors were unable to differentiate between the work of OSAIRIS and that of a human doctor, the AI system proved its effectiveness. Importantly, the oncologist remains in control throughout the process, retaining the final decision-making authority.
At Addenbrooke's Hospital in Cambridge, all NHS patients requiring radiotherapy treatment for prostate or head and neck cancer are benefiting from the accelerated treatment planning made possible by OSAIRIS. Looking ahead, Dr. Jena and his team are actively exploring further applications for the AI technology. They are developing models for lung cancer, breast cancer, and brain tumors, expanding the scope of patients who can benefit from reduced waiting times and improved health outcomes.
Aditya Nori, General Manager of Healthcare for Microsoft Research, expresses enthusiasm about the potential impact of AI in healthcare: "The fact that we have AI finally in the NHS also will open the doors for other kinds of AI technologies to really reduce the burden that's placed on clinicians, and more importantly, improve patient safety, outcomes, and experiences." The NHS team is collaborating with other hospitals to implement similar AI solutions, with the ultimate goal of improving patient care and outcomes on a broader scale.
Thanks to Azzure OSAIRIS AI solutions, waiting times in hospitals, particularly in radiotherapy treatment planning, are being significantly reduced. The integration of AI technology in healthcare is transforming the way specialists operate, enabling them to work more efficiently and ensuring that patients receive the treatment they need more promptly. With ongoing research and collaborations, we can look forward to a future where AI continues to revolutionize healthcare and enhance patient care across the NHS and beyond.
Sources microsoft and nationalhealthexecutive.
Comments