AI can predict brain cancer survival rates in patients suffering from ‘most deadly form’ of the disease, scientists reveal
- Scientist-trained system based on a dataset of 10,000 brain cancer scans
- AI can predict whether a patient will survive eight months after treatment
- Read more: AI develops cancer treatment in just 30 days
Artificial intelligence can predict the survival rate of patients suffering from the deadliest form of cancer, scientists have revealed.
Researchers at King’s College London trained a system to determine whether those diagnosed with glioblastoma would live for at least eight months after radiotherapy, allowing doctors to explore other treatments if patients did not.
The average survival time for glioblastomas is 12 to 18 months – only 25 percent of patients survive more than a year and only five percent of patients survive more than five years.
Patients typically need regular scans before doctors can see the effectiveness of drugs, but the new system showed it could produce the same results by analyzing a single MRI scan.
Researchers at King’s College London trained a system to determine whether those diagnosed with glioblastoma would live for at least eight months after radiotherapy, allowing doctors to explore other treatments if patients did not.
The AI was trained with a dataset of 10,000 MRI scans of different types of cancer.
Alysha Chelliah, who was involved in the study, said: ‘We applied deep learning to predict whether glioblastoma patients will survive the first eight months after completing radiotherapy.
‘This approach aims to improve the ability to identify patients in need of early second-line treatment or enrollment in clinical trials, compared to patients who demonstrate an initial treatment response.’
The National Foundation for Cancer Research – which funds research into cancers – says glioblastomas are the ‘most deadly form of brain cancer’.
It occurs when cells that support the nerves in the brain begin to divide uncontrollably.
The fast-growing cells invade nearby brain tissue, making them difficult to remove, but generally do not spread to other parts of the body.
It is estimated that approximately one in 30,000 people have the condition.
The average survival time for glioblastomas is 12 to 18 months – only 25 percent of patients survive more than a year and only five percent of patients survive more than five years. The black mass in the upper right is glioblastoma
Dr. Thomas Booth, who was involved in the research, said: ‘This study was motivated by a clinically tailored and critical research question relating to aggressive brain tumors, and was delivered using advanced artificial intelligence.
‘Although it is less common than other cancers, the devastation is disproportionate with a two-year survival rate of 18 percent.’
The team set out to find a better method for predicting short- and long-term survival rates, which would eliminate the need for multiple scans that can delay treatments.
‘Rather than trying to interpret every non-specific follow-up brain scan, we simply looked at one routine scan after radiotherapy and, using artificial intelligence, provided an accurate prediction to answer a simple question: which patients will not survive the next one. eight months,” Booth said.
‘The AI was able to give us an immediate and accurate prediction, meaning doctors can empower patients to make choices about their treatment.’