Big Data From Social Media Helps Combat Prescription Drug Crisis
News Nov 17, 2017 | Original story from Geisel School of Medicine Dartmouth
Researchers at Dartmouth, Stanford University, and IBM Research, conducted a critical review of existing literature to determine whether social media big data can be used to understand communication and behavioral patterns related to prescription drug abuse. Their study found that with proper research methods and attention to privacy and ethical issues, social media big data can reveal important information concerning drug abuse, such as user-reported side effects, drug cravings, emotional states, and risky behaviors.
Their work, “Scaling Up Prescription Drug Abuse and Addiction Research Through Social Media Big Data,” is reported in the Journal of Medical Internet Research.
Prescription drug addiction is a well-known nationwide problem. Many people who are unable to get help for their addiction seek out peer support groups on Facebook or other social media platforms to share stories about their experiences and also provide social peer-based support.
Lead author, Sunny Jung Kim, PhD, an e-health communication scholar in the departments of biomedical data science and psychiatry at Dartmouth’s Geisel School of Medicine, says that because we are prolific consumers of social media, which is not limited to geography—globally, people spend more than two hours every day on social media platforms generating vast amounts of big data about our personal communications and activities—we can use these platforms to enhance public health communication strategies to help people on a large scale.
“Harnessing social media platforms and data can provide insight into important novel discoveries of collective public health risk behavior, a better understanding of peoples’ struggles with addiction, and their process of recovery,” Kim says. “I started this project because there were few studies about why people use social networking sites to share unsolicited, highly personal information about their drug use, nor about the psychological effects or consequences of this type of user-generated communication.”
Co-author Jeffrey Hancock, PhD, a professor in the department of communication and the director of computational social science at Stanford University, says, “Given the importance of this problem for the U.S. population, it’s imperative that we understand how social media is playing a role and how it can be part of the solution.”
Based on their findings, the researchers designed an evidence-based, multi-level framework to inform future social media-based substance use prevention and recovery intervention programs.
“Our review and typology suggests that social media big data and platforms can be a tremendous resource for monitoring and intervening on behalf of people with drug addiction and abuse problems,” Kim says.
This article has been republished from materials provided by Geisel School of Medicine Dartmouth. Note: material may have been edited for length and content. For further information, please contact the cited source.
Algorithm Speeds Up Medical Image Analysis 1000 TimesNews
Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. Researchers have described a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.
Antarctic Worm and Machine Learning Help Identify Cerebral Palsy EarlierNews
A research team has released a study in the peer-reviewed journal BMC Bioinformatics showing that DNA methylation patterns in circulating blood cells can be used to help identify spastic cerebral palsy (CP) patients. The technique which makes use of machine learning, data science and even analysis of Antarctic worms, raises hopes for earlier targeted CP therapies.
Towards Personalized Medicine: One Type of Data is Not EnoughNews
To understand the biology of diseased organs researchers use different types of molecular data. One of the biggest computational challenges at the moment is integrating these multiple data types. A new computational method jointly analyses different types of molecular data and disentangles the sources of disease variability to guide personalized treatment.READ MORE