AI Model Predicts Cancer Symptom Severity
News Jan 03, 2019 | Original Press Release from the University of Surrey
Researchers analyzed data from patients during computed tomography x-ray scanning. Credit: daveynin from United States [CC BY 2.0 (https://creativecommons.org/licenses/by/2.0)], via Wikimedia Commons
In what is believed to be the first study of its kind, published in the PLOS One journal, researchers from the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey detail how they created two machine learning models that are both able to accurately predict the severity of three common symptoms faced by cancer patients – depression, anxiety and sleep disturbance. All three symptoms are associated with severe reduction in cancer patients’ quality of life.
Researchers analysed existing data of the symptoms experienced by cancer patients during the course of computed tomography x-ray treatment. The team used different time periods during this data to test whether the machine learning algorithms are able to accurately predict when and if symptoms surfaced.
The results found that the actual reported symptoms were very close to those predicted by the machine learning methods.
This work has been a collaboration between the University of Surrey and the University of California in San Francisco (UCSF). The UCSF research in this joint collaboration is led by Professor Christine Miaskowski.
Payam Barnaghi, Professor of Machine Intelligence at the University of Surrey, said: “These exciting results show that there is an opportunity for machine learning techniques to make a real difference in the lives of people living with cancer. They can help clinicians identify high-risk patients, help and support their symptom experience and pre-emptively plan a way to manage those symptoms and improve quality of life.”
Nikos Papachristou, who worked on designing the machine learning algorithms for this project, said: “I am very excited to see how machine learning and AI can be used to create solutions that have a positive impact on the quality of life and well-being of patients”.
Professor Adrian Hilton, Director of Surrey’s Centre for Vision, Speech and Signal Processing (CVSSP), said: “These exciting developments by Professor Barnaghi and his team show the incredible potential of machine learning in transforming the way healthcare professionals treat people suffering from cancer. We continue to explore the boundless potential of AI at CVSSP and we believe our work has a real place in helping to shape the future of health services across the globe.”
This article has been republished from materials provided by the University of Surrey. Note: material may have been edited for length and content. For further information, please contact the cited source.
Reference: Papachristou, N., Puschmann, D., Barnaghi, P., Cooper, B., Hu, X., Maguire, R., … Miaskowski, C. (2018). Learning from data to predict future symptoms of oncology patients. PLOS ONE, 13(12), e0208808. https://doi.org/10.1371/journal.pone.0208808
Researchers who sequenced the fecal samples of over 3,000 healthy volunteers recently described the so-called B2 enterotype, which is deficient in some anti-inflammatory bacteria. Today, they published more data, showing the high prevalence of this particular enterotype across multiple disease diagnoses.READ MORE
New research may explain why an antioxidant that protects the brain is also associated with deterioration in areas susceptible to Alzheimer’s disease. The antioxidant, superoxide dismutase or SOD1, improves cognition, but an Iowa State University research team found SOD1’s protective benefits dramatically weaken when levels of tau proteins – a hallmark of Alzheimer’s disease – increase.