AI study at The Royal Marsden NHS shows benefits for tailoring treatment and diagnosing rare disease

A study undertaken by The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research, London, has shared the effectiveness of a new AI algorithm for tailoring treatment for some sarcoma patients and to help diagnose subtypes of rare disease.

The study focused on retroperitoneal sarcoma – a soft tissue sarcoma which develops in the back of the abdomen – being hard to diagnose and treat due to its location and rarity, the researchers stated.

An algorithm was developed using CT scans of 170 Royal Marsden patients, and then tested on 90 patients from centres across Europe and the US. The researchers noted the use of “a technique called radiomics to analyse the CT scan data, which can extract information about the patient’s disease from medical images, including data which can’t be distinguished by the human eye”.

Findings showed that 82 percent of tumours analysed by AI were accurately graded, against 44 percent correctly graded using a biopsy.

The research team believe that the technique could also be used in the diagnosis of other cancer types.

Dr Amani Arthur, registrar at The Royal Marsden NHS Foundation Trust and clinical research fellow at The ICR, London, said: “Through this early research, we’ve developed an innovative AI tool using imaging data that could help us more accurately and quickly identify the type and grade of retroperitoneal sarcomas than current methods. This could improve patient outcomes by helping to speed up diagnosis of the disease, and better tailor treatment by reliably identifying the risk of each patient’s disease.”

In the next phase of the study, Amani said, the model will be tested in clinic on patients with potential retroperitoneal sarcomas “to see if it can accurately characterise their disease and measure the performance of the technology over time.”

Professor Christina Messiou, digital theme lead at the NIHR BRC at The Royal Marsden, shared hopes that the tool “will eventually be used globally, ensuring that not just specialist centres – who see sarcoma patients every day – can reliably identify and grade the disease. In the future, this approach may help characterise other types of cancer, not just retroperitoneal sarcoma. Our novel approach used features specific to this disease, but by refining the algorithm, this technology could one day improve the outcomes of thousands of patients each year.”

The World Health Organisation recently published new guidance on the regulation of artificial intelligence for health, highlighting the need for “establishing AI systems’ safety and effectiveness, rapidly making appropriate systems available to those who need them, and fostering dialogue among stakeholders”.

The Departments for Health and Social Care and Science, Innovation and Technology have shared a proposal for the AI Life Sciences Accelerator Mission, subject to a full business case, which would involve funding of £100 million to be invested across areas where rapid deployment of artificial intelligence is viewed to have the “greatest potential” to tackle previously incurable diseases.