Feb 21 2019
In the near future, cancer patients who are given chemotherapy could gain from a new AI that can identify and predict the development of various combinations of symptoms—helping to ease a lot of the suffering caused by their occurrence and severity.
Image credit: Getty Images
This research by a team of scientists from the University of Surrey and the University of California is the first of its kind and has been published by Nature Scientific Reports. It details how they used Network Analysis (NA) to study the structure and relationships between 38 frequently occurring symptoms reported by more than 1300 cancer patients undergoing chemotherapy.
Some of the most typical symptoms stated by patients were fatigue, drowsiness, difficulty concentrating, dry mouth, nausea, numbness, hot flushes, and nervousness.
The team then categorized these symptoms into three major networks—occurrence, distress, and severity. The NA enabled the team to identify nausea as central—impacting symptoms spanning all three different main networks.
According to Cancer Research UK, 360,000 people are diagnosed with cancer yearly—with breast, lung, prostate, and bowel cancers counting for more than half of new cases in the UK. In England, about 28% of patients diagnosed with cancer have palliative or curative chemotherapy as part of their main cancer treatment.
This is the first use of Network Analysis as a method of examining the relationships between common symptoms suffered by a large group of cancer patients undergoing chemotherapy. The detailed and intricate analysis this method provides could become crucial in planning the treatment of future patients—helping to better manage their symptoms across their healthcare journey.
Payam Barnaghi, Professor of Machine Intelligence, Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey.
I am proud of our continued work to support cancer patients during their treatment and improving their quality of life with the help of machine learning.
Nikolaos Papachristou, Study Co-Author and Research Student, CVSSP, University of Surrey.
This is another heartening development from Professor Barnaghi and his group. This world-first study of how NA methods can help identify and analyse the symptoms of cancer patients supports the real benefits machine learning brings to society and the future of the healthcare industry.
Adrian Hilton, Professor and Director, CVSSP, University of Surrey.
Christine Miaskowski from the University of California said: “This fresh approach will allow us to develop and test novel and more targeted interventions to decrease symptom burden in cancer patients undergoing chemotherapy.”