In a bid to enhance medical research on chronic conditions, engineers at Ben-Gurion University of the Negev (BGU) have developed a method that analyzes medically themed social media posts to identify chronically ill patients and learn about their symptoms, treatments and daily life.
The project began with PhD student Maya Stemmer’s realization that big data analysis of millions of self-reported medical posts can yield actionable insights into chronic patients’ symptoms, treatments and daily life.
Although large amounts of health-related data are posted daily on Twitter and other networking platforms, which serve to share information and provide social support, research using social-media data to understand chronic conditions and patients’ lifestyles has so far been limited.
In the first stage of Stemmer’s study, supervised by Prof. Gilad Ravid and Prof. Yisrael Parmet of BGU’s Department of Industrial Engineering and Management, social network analysis and natural language processing were combined to automatically classify social-media comments posted by those suffering from a particular illness.
The engineers looked at tweets by people suffering from inflammatory bowel diseases such as Crohn’s and ulcerative colitis. They were able to discover chronically ill patients, who tended to post more often about their diseases.
By analyzing the data, the researchers identified distinctive characteristics of Crohn’s disease that helped differentiate it from ulcerative colitis. They were also able to confirm existing information about foods that increase or reduce inflammation.
The study further aimed to promote the wellbeing of people with IBD by addressing the potential of Twitter data in accessing the wisdom of the crowd regarding healthy lifestyles.
“We sought to leverage posts describing patients’ daily activities and their influence on their wellbeing to characterize lifestyle-related treatments,” said Stemmer.
While the method employed in the study can be modified for other platforms and other diseases, the advantage of Twitter is that its API enables advanced programmatic access for academic researchers.
“Using the framework to identify more patients and collect more data can shed light on patients’ coping strategies with their disease and its influence on their quality of life,” said Stemmer.