Artificial Intelligence (AI) can be used to predict if adult patients with brain cancer are likely to survive more than eight months after receiving treatment, according to a study published in the journal Neuro-Oncology. The authors believe this could help clinicians care better for their patients and plan the next stage of potentially life-saving treatment quickly. This is the first time AI is used to predict the chances of survival after cancer treatment.
Glioblastoma is challenging to treat and has a low survival rate. Only one in four patients can survive more than one year after diagnosis.
Using AI, a team from King’s College London created a deep learning model to help them predict the outcomes for cancer patients with glioblastoma more reliably. The aim was to determine which patients were more likely to survive eight months after treatment. This is usually the time taken to complete a course of chemotherapy and radiotherapy.
At the moment, patients are scanned regularly to see if the treatment is working. However, this means some patients are getting chemotherapy that is not really helping fight the cancer and still suffer harmful side effects. If doctors could predict which patients can benefit from chemotherapy based on a routine MRI scan, they could consider alternative treatments for the patients who would not benefit.
“This study was motivated by a clinically-attuned and critical research question regarding aggressive brain tumours and delivered by leveraging cutting edge artificial intelligence. Whilst less common than other cancers, the devastation is disproportionate with a two-year survival rate of 18%,” said Dr Thomas Booth, from King’s College London and a Neurology Consultant at King’s College Hospital NHS Foundation Trust.
“We applied deep learning to predict whether glioblastoma patients will survive the first eight months after completing radiotherapy. The AI model showed improved performances when first trained to detect abnormalities on 10,000 brain MRIs. This approach is intended to improve the ability to identify patients who require early second-line treatment or clinical trial enrolment, compared to those showing initial treatment response,” added Alysha Chelliah, PhD researcher from King’s College London.
For this study, the team trained AI using 10,000 scans from all types of patients with brain cancer. “Instead of trying to grapple with interpreting each and every non-specific follow-up brain scan, we simply looked at one routine scan after radiotherapy and gave an accurate prediction using artificial intelligence to answer a simple question: which patients will not survive the next eight months? The AI was able to give us an immediate and accurate prediction, which means clinicians can empower patients to make choices about their treatment,” said Dr Booth. “We would be delighted if the cancer research community now uses our artificial intelligence tool to see improved outcomes for patients who won’t benefit from the usual course of chemotherapy.”
“This is exciting and fundamental research for people living with a glioblastoma, for two reasons. At its simplest level it demonstrates how AI can be used for patient benefit. More importantly, however, it empowers patients and their caregivers to make choices about the clinical pathway and gives control back at a time when so much control has been lost. Patients will be able to make informed decisions about treatment choices and will be able to plan how they want to spend the time they have left so that they can live their best possible day, every day,” commented Dr Helen Bulbeck, Director of Services and Policy at brainstrust. Dr Bulbeck was not involved in this work.
Chelliah A, Wood D, Canas L, Shuaib H, et al (2024) Glioblastoma and Radiotherapy: a multi-center AI study for Survival Predictions from MRI (GRASP study), Neuro-Oncology, noae017, https://doi.org/10.1093/neuonc/noae017