by Cutting-edge research conducted by scientists at King’s College London demonstrates that artificial intelligence (AI) can accurately predict the likelihood of survival for brain cancer patients undergoing radiotherapy. This groundbreaking development has the potential to revolutionize the treatment process, allowing doctors to make more informed decisions about the next stage of treatment and potentially save lives.
The groundbreaking study, published recently in the journal Neuro-Oncology, is the first to utilize AI to predict both short-term and long-term survival rates for glioblastoma patients within eight months of receiving radiotherapy. Glioblastoma, a highly aggressive form of brain cancer, currently poses significant challenges in terms of treatment, with only 25% of patients surviving beyond the first year following diagnosis.
The researchers employed a deep learning model to analyze data and accurately predict patient outcomes. This advanced technology has the ability to provide more reliable and precise assessments for adults diagnosed with primary brain cancer.
Currently, patients are subjected to regular scans to determine if chemotherapy is effective. However, this approach often leads to some patients enduring the harmful side effects of ineffective treatment. By utilizing AI, doctors can instantly receive accurate predictions based on one routine MRI scan. This enables them to identify patients who would not benefit from chemotherapy and explore different treatment options or enroll them in clinical trials.
Dr. Thomas Booth, Reader in Neuroimaging at King’s College London and a Neurology Consultant at King’s College Hospital NHS Foundation Trust, explained the motivation behind the study, stating, “This study was motivated by a clinically-attuned and critical research question regarding aggressive brain tumors, and delivered by leveraging cutting-edge artificial intelligence.”
Alysha Chelliah, Ph.D. researcher from King’s College London, elaborated on the study’s methodology, stating, “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 enrollment, compared to those showing initial treatment response.”
The AI model was trained on a comprehensive dataset consisting of thousands of scans from various brain cancer patients.
Dr. Booth emphasized that the research aimed to address the unmet needs of patients undergoing modified treatment, including those receiving shorter courses and lower doses of radiotherapy when chemotherapy proves ineffective. By focusing on a routine scan after radiotherapy, the researchers were able to bypass the challenges associated with interpreting non-specific follow-up brain scans. Instead, they were able to provide an immediate and accurate prediction using AI, enabling clinicians to empower patients to make informed decisions about their treatment.
The implementation of AI technology in predicting patient survival rates in brain cancer treatment has immense potential for improving outcomes and reducing unnecessary treatments. This groundbreaking research could profoundly impact the future of cancer treatment, allowing healthcare professionals to optimize care for individuals diagnosed with glioblastoma. With its ability to provide instantaneous and accurate predictions, AI is poised to revolutionize the field of oncology and significantly improve patient outcomes.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
