Predicting survival rates of brain cancer patients using AI

AI can now predict the survival rate of people with brain cancer.


The technology can successfully tell us if, after receiving radiotherapy, patients will survive for more than eight months. 


Utilising AI for accurate prognosis prediction could help clinicians with treatment choices and early intervention, ultimately helping patients live longer. 


It is the first of its kind in terms of being able to accurately forecast the survival of patients within an eight-month timeframe of receiving radiotherapy. 


Recently published in Neuro-Oncology, the study illustrates how a team of researchers from King’s College London developed a deep learning model, enabling more precise and dependable outcome forecasts for adult primary brain cancer patients.


The survival rate for glioblastoma is low, with just a quarter of patients making it past a year following diagnosis. 


Traditionally, patients undergo regular scans to assess chemotherapy efficacy. However, this approach risks subjecting some patients to ineffective treatments and accompanying adverse effects.


By leveraging instantaneous and precise predictions from routine MRI scans, the AI empowers physicians to pinpoint patients unlikely to benefit from chemotherapy. This enables exploration of alternative treatments or enrollment in clinical trials for experimental therapies.


Dr Thomas Booth said: “Feedback from all patients and clinicians at the start of the study meant that we wanted to address the unmet need of improving outcomes of the large proportion of patients undergoing modified treatment – usually a shorter course and lower dose of radiotherapy if chemotherapy is not effective – as well as the minority of patients who can tolerate “optimal” treatment. Almost all previous research considers only the latter group of patients.


“We also side-stepped a thorny issue: after radiotherapy, follow-up brain scan findings are often non-specific and oncologists cannot be certain whether a treatment is working or failing.


“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 8 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.”