Artificial Intelligence Predicts Symptoms in Cancer Patients
Cancer patients have to deal not only with symptoms of cancer and adverse effects due to treatments, but also with comorbidities such as depression, anxiety, and sleep disturbance. Because these symptoms greatly reduce patients' quality of life, it is imperative to combat them. Scientists have discovered how to better treat these symptoms by utilizing artificial intelligence (AI) in order to predict their presence and severity in cancer patients before they occur, allowing doctors to identify high-risk patients, provide appropriate patient education, and improve timing of preventive and individualized symptom management interventions.
Published in PLOS One, this study involved a collaboration of researchers from the Center for Vision, Speech and Signal Processing at the University of Surrey in England and researchers from the University of California in San Francisco, led by Professor Christine Miaskowski, PhD.
By reviewing existing data on patients' symptoms that had been collected during the course of computed tomography (CT) scans, investigators were able to use AI to predict future symptoms. Data was self-reported by patients regarding their symptom experience during the course of treatment. Based on these observations, the researchers developed an algorithm that could predict the patients at highest risk for developing comorbidities. Artificial intelligence was tested on this data and was able to accurately predict the actual reported symptoms of the patients.
Payam Barnaghi, PhD, Professor of Machine Intelligence at the University of Surrey and one of the leading authors of the study, stated, "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."
Another of the study's lead authors, Nikos Papchristou, a PhD student who contributed to building the machine learning algorithms for this project, remarked, "I am very excited to see how the 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."
For More Information
Papchristou N, Puschmann D, Barnaghi P, et al (2018). Learning from data to predict future symptoms of oncology patients. PLoS One, 13(12):e0208808. DOI:10.1371/journal.pone.0208808
Image courtesy of Mateus Figueiredo