6.5 C
New York
Wednesday, August 17, 2022

Facebook is better then Scientists when it comes to predicting diseases

Must Read

What Fills Earth’s Oceans With Life-supporting Oxygen? – New Scientific Theory

What drives Ocean Oxygenation? Is it driven by atmospheric oxygen levels or something else?

As Much As 56% Of People Will Never Know They Were Ever Infected With Omicron, Finds New Study

"More than one in every two people who were infected with Omicron didn't know they had it,"...

Researchers Reveal Surprising Secrets Of One Of Our Oldest Ancestors

For paleobiologists, it's one step forward and one step back. A large, international team...
Revyuh Logo 120 x 120
Jiya Saini
Jiya Saini is a Journalist and Writer at Revyuh.com. She has been working with us since January 2018. After studying at Jamia Millia University, she is fascinated by smart lifestyle and smart living. She covers technology, games, sports and smart living, as well as good experience in press relations. She is also a freelance trainer for macOS and iOS, and In the past, she has worked with various online news magazines in India and Singapore. Email: jiya (at) revyuh (dot) com

The language in Facebook’s publications can help identify conditions such as diabetes, anxiety, depression and psychosis in patients, according to a study published in PLOS ONE. The results indicate that the language in these publications could be an indicator of the aforementioned diseases and with the consent of the patient, could be analyzed as physical symptoms.

“This work is incipient but our hope is that the information obtained from these publications can be used to better inform patients and those responsible for the health field” – explains lead author Raina Merchant. “Because social media posts often deal with choices and lifestyle experiences, this information could provide additional data on disease control.”

Using an automated data collection technique, the Merchant team analyzed the complete history of Facebook posts of nearly 1,000 patients who agreed to give their data from electronic medical records and their Facebook profiles. Then, the authors built three models to analyze the predictive power for patients: a model that only analyzes Facebook’s publications, another that used demographic data such as age and sex, and the last one that combined the two.

When analyzing 21 different conditions, the researchers found that all of them were predictable using only Facebook. In fact, 10 of the conditions were predicted better by using Facebook data instead of demographic information.

“Our digital language – concludes Merchant – captures important aspects of our lives that are probably very different from what is obtained through traditional medical data. Many studies have shown a link between language patterns and specific diseases, such as predictive language for depression or language that provides information about whether a person is living with cancer. However, when analyzing many medical conditions, we can see how the conditions develop, relate to each other, which may allow new applications of artificial intelligence for medicine. For example, if someone is trying to lose weight and needs help to understand their food choices and exercise regimens, Having a doctor check your social media record could give you a better understanding of your usual patterns to help improve them. The challenge of this new technique is that there is a lot of information and we are not able to interpret it or to make clinical decisions based on them “.

- Advertisement -
- Advertisement -

Latest News

- Advertisement -

More Articles Like This

- Advertisement -