New AI tool prescribes best treatment for liver cancer

Researchers at King’s College Hospital and Queen Mary University of London have developed an AI algorithm which can prescribe the most effective treatment plan for patients diagnosed with primary liver cancer.

The computer-based algorithm, named Drug Ranking Using Machine Learning (DRUML), classifies drugs used to treat bile duct cancer (a type of primary liver cancer), based on their efficacy in reducing cancer cell growth.

The research into DRUML was recently published in Cancer Research, an American Association of Cancer Research journal. Researchers say that the software could be used in the future to predict individual patient responses to therapies to enable them to select the most effective treatment plan.

Professor Pedro Cutillas, researcher at Queen Mary University of London, said: “Patients who are diagnosed with primary liver cancer often have a very poor prognosis. Cancers of the bile duct, in particular, exhibit great variation in their protein expression and characteristics from patient to patient. This variation results in patients displaying different responses to therapy. Hence why a one-size-fits-all approach to treatment is not the most effective way to reduce cancer cell growth and why we applied DRUML to this type of cancer.”

The team of researchers trained DRUML to identify and rank how cell lines from a range of cancers respond to over 400 different drugs. Working at Queen Mary’s Barts Cancer Institute, DRUML would examine data on the presence of dysregulated proteins, which are through to determine a cell’s ability to multiply.

Bile duct cancer cells and tumours were donated from patients globally, which were then used in the AI software process to determine a patient’s protein patterns in those cells and make recommendations on therapy accordingly.

Dr Shirin E Khorsandi, clinical researcher at King’s College Hospital and lead researcher of the work, added: “This study, we believe, represents a significant advancement in artificial intelligence and further patient involvement and participation will ensure that we have an algorithm that captures the best drugs for multiple variations of liver cancer.

“While this approach is still in its infancy, we are optimistic that the application of artificial intelligence to tackling one of the hardest to treat cancers, can transform how liver cancers are diagnosed and treated by clinicians in the future.”

AI is increasingly being tasked with detecting medical conditions. Last month a team from Moorfields Eye Hospital NHS Foundation Trust revealed they had developed an automated algorithm capable of detecting geographic atrophy.