AI predicts, identifies the development of cancer symptoms
A new AI method that allows physicians to identify and predict the development of symptoms in post-chemotherapy patients is being tested by researchers from the University of Surrey and the University of California. Findings of the study were published in Scientific Reports.
“One of the underlying assumptions of this research is that symptoms that cluster together may share underlying mechanisms that are potential targets for therapeutic interventions,” wrote lead author Nikolaos Papachristou, PhD, of the University of Surrey in Guilford, U.K., and colleagues. “While progress is being made in symptom clusters research, one of the major gaps in knowledge using standard statistical approaches is that the nature of the relationships among individual symptoms and symptom clusters have not been evaluated.”
While there are AI-based resources to provide personalized recommendations for side effects, this AI has the ability to identify and predict core symptoms before they occur.
In this first study of its kind, the researchers used Network Analysis (NA) to assess the structure and relation between 38 common symptoms—including nausea, difficulty concentrating, fatigue, drowsiness, dry mouth, numbness and nervousness—reported by more than 1,300 cancer patients who received chemotherapy.
Additionally, the researchers assessed six other symptoms, including hot flashes, chest tightness, difficulty breathing, abdominal cramps, increased appetite and weight gain.
Papachristou and colleagues grouped the symptoms into three key “networks”—occurrence, severity and distress. The NA enabled the team to classify nausea as central, or a symptom that impacts all three key networks.
"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,” said Payam Barnaghi, PhD, of the University of Surrey, in a statement. “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."
These findings, the researchers noted in the study, can be used to guide the development of symptom management interventions based on identifying core symptoms and symptom clusters within a network.
"This fresh approach will allow us to develop and test novel and more targeted interventions to decrease symptom burden in cancer patients undergoing chemotherapy,” said Christine Miaskowski, PhD, of the University of California, in the same statement.
As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.