AI can Predict Brain Cancer Patients' Survival

Artificial Intelligence (AI) can predict whether adult patients with brain cancer will survive more than eight months after receiving radiotherapy treatment.

The use of the AI to successfully predict patient outcomes would allow clinicians to be better informed for planning the next stage of treatment and refer patients to potentially life-saving treatment quicker.

This is the first use of AI to predict short-term and long-term survivors within eight-months of radiotherapy.

The paper published recently in Neuro-Oncology shows how researchers from King’s College London created a deep learning model to allow them to more reliably and accurately predict outcomes for patients with adult primary brain cancer.

Glioblastoma is a difficult to treat cancer with just one in four patients surviving more than one year after diagnosis. The researchers applied deep learning - a type of AI - to predict whether glioblastoma patients would survive the eight months after receiving radiotherapy. Eight months is typically the time taken to complete a typical course of routine chemotherapy that usually follows radiotherapy.

Currently, patients are regularly and routinely scanned to see if the chemotherapy is working. But this means that some patients have ineffective chemotherapy which wouldn’t save their life and suffer through harmful side effects.

Instead, by giving an instantaneous and accurate prediction from one routine MRI scan, the AI allows doctors to identify patients who would not benefit from chemotherapy to try a different treatment or start an experimental treatment in a clinical trial.

Dr Thomas Booth, Reader in Neuroimaging at King's College London and a Neurology Consultant at King’s College Hospital NHS Foundation Trust, said: "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%."

Alysha Chelliah, PhD researcher from King's College London, said: "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 10,000s of 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."

Researchers trained the AI on a dataset of 10,000s of scans from all types of patients with brain cancer.

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."

Dr Booth added: "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."

Commenting on how the work of Dr Booth and his team at King’s College London supported people-first brain tumour research as advocated for by the charity brainstrust, Dr Helen Bulbeck, Director of Services and Policy at brainstrust said: "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."

Dr Michele Afif, CEO at The Brain Tumour Charity added: "The use of AI to evaluate and predict response to radiotherapy at a much earlier point in a patient's treatment for glioblastoma is a hugely important step in tackling this notoriously difficult to treat disease.

At The Brain Tumour Charity, we welcome this important advance which could lead to more informed discussions at an early enough point in a patient’s treatment to consider meaningful alternatives, such as clinical trials.

We look forward to seeing how this exciting research progresses as it is validated for wider use as a tool to improve care for those diagnosed with a brain tumour."

The study involved a collaboration of 11 neuro-oncology centres from across the UK.

Chelliah A, Wood DA, Canas LS, Shuaib H, Currie S, Fatania K, Frood R, Rowland-Hill C, Thust S, Wastling SJ, Tenant S, Foweraker K, Williams M, Wang Q, Roman A, Dragos C, MacDonald M, Lau YH, Linares CA, Bassiouny A, Luis A, Young T, Brock J, Chandy E, Beaumont E, Lam TC, Welsh L, Lewis J, Mathew R, Kerfoot E, Brown R, Beasley D, Glendenning J, Brazil L, Swampillai A, Ashkan K, Ourselin S, Modat M, Booth TC.
Glioblastoma and Radiotherapy: a multi-center AI study for Survival Predictions from MRI (GRASP study).
Neuro Oncol. 2024 Jan 29:noae017. doi: 10.1093/neuonc/noae017

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...