Cleveland Clinic researchers use AI to personalise radiation therapy
July 9, 2019
Cleveland Clinic and Siemens Healthcare researchers are using artificial intelligence (AI) to improve the success rate of radiation therapy for cancer patients and reduce the side effects.
The researchers are using AI to analyse medical scans and health records to personalise the dose of radiation therapy used to treat cancer patients.
In an article in The Lancet Digital Health, the research team explains how it has developed an AI framework based on patient computerised tomography (CT) scans and electronic health records. This AI framework is the first to use medical scans to inform radiation dosage, moving the field forward from using generic dose prescriptions to more individualised treatments.
Currently, radiation therapy is delivered uniformly. The dose delivered does not reflect differences in individual tumour characteristics or patient-specific factors that may affect treatment success. The AI framework begins to account for this variability and provides individualised radiation doses that can reduce the treatment failure probability to less than five per cent.
“While highly effective in many clinical settings, radiotherapy can greatly benefit from dose optimisation capabilities,” said lead author Mohamed Abazeed (pictured), a radiation oncologist at Cleveland Clinic’s Taussig Cancer Institute and a researcher at the Lerner Research Institute. “This framework will help physicians develop data-driven, personalised dosage schedules that can maximise the likelihood of treatment success and mitigate radiation side effects for patients.”
The framework was built using CT scans and the electronic health records of 944 lung cancer patients treated with high-dose radiation. Pre-treatment scans were input into a deep-learning model, which analysed the scans to create an image signature that predicts treatment outcomes. Using mathematical modelling, this image signature was combined with data from patient health records – which describe clinical risk factors – to generate a personalised radiation dose.
“The development and validation of this image-based, deep-learning framework is exciting because not only is it the first to use medical images to inform radiation dose prescriptions, but it also has the potential to directly impact patient care,” said Abazeed. “The framework can ultimately be used to deliver radiation therapy tailored to individual patients in everyday clinical practices.”
There are several factors that set this first-of-its-kind framework apart from other similar clinical machine learning algorithms and approaches. The technology developed by the team uses an artificial neural network that merges classical approaches of machine learning with the power of a modern neural network. The network determines how much prior knowledge to use to guide predictions about treatment failure. The extent that prior knowledge informs the model is tuneable by the network.
This hybrid approach is suitable for clinical applications since most clinical datasets in individual hospitals are more modest in sample size compared with non-clinical datasets used to make other well-known AI predictions, such as online shopping or ride-sharing.
Additionally, this framework was built using one of the largest datasets for patients receiving lung radiotherapy, rendering greater accuracy and limiting false findings. Lastly, each clinical centre can use its own CT datasets to customise the framework and tailor it to the specific patient population.
“Machine learning tools, including deep learning, are poised to play an important role in healthcare,” said Abazeed. “This image-based information platform can provide the ability to individualise multiple cancer therapies but more immediately is a leap forward in radiation precision medicine.”
This study, which was done in collaboration with Siemens Healthcare, was funded by a National Institutes of Health grant to Abazeed, the National Cancer Institute, American Lung Association, Siemens Healthcare and VeloSano (Cleveland Clinic’s flagship philanthropic initiative) to advance cancer research.