The algorithm could improve the ability of doctors to prescribe the most appropriate treatment for patients with bile duct 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.” Dr Shirin E Khorsandi, clinical researcher at King’s College Hospital
An artificial intelligence (AI) algorithm has been successful at prescribing the most effective treatment plan for patients diagnosed with a form of primary liver cancer, according to research published in the journal Cancer Research.
The algorithm, the Drug Ranking Using Machine Learning (DRUML), ranks drugs used to treat bile duct cancer according to their efficacy in reducing cancer cell growth. Using bile duct cancer cells and tumours from patients around the world, researchers from King’s College Hospital and Queen Mary University of London trained the algorithm to identify and rank how cell lines responded to over 400 different drugs. The software was able to determine a patient’s protein patterns in the cells and make treatment recommendations accordingly.
In future, it means that doctors might be able to use DRUML to predict how an individual patient will respond to different treatments, and therefore to select the most appropriate option for that patient.
Choosing the right treatment for patients with bile duct cancer is particularly challenging.
Professor Pedro Cutillas, researcher at Queen Mary University of London, said: “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.”
Dr Shirin E Khorsandi, clinical researcher at King’s College Hospital, said that the study represented a “significant advancement in artificial intelligence” and that “further patient involvement and participation will ensure that we have an algorithm that captures the best drugs for multiple variations of liver cancer.
She added: “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.”
Liver cancer affects 6,200 people each year in the United Kingdom. The disease has a high fatality rate because in the early stages it is symptomless, and patients often don’t consult a doctor until the disease is well advanced. Even when detected early, the five-year survival rate after diagnosis is less than 13%.