Monday, 16 September 2019, +05:30
Space for Advertisement
Sci-Tech Health Facebook posts better at predicting , mental health than...

Facebook posts better at predicting diabetes, mental health than demographic data

The researchers from the University of Pennsylvania and Stony Brook University in the US analyzed the entire Facebook post history of nearly 1,000 patients who agreed to have their electronic medical record data linked to their profiles.

-

Language in Facebook posts may help identify conditions such as , , and psychosis in patients, according to a study. It’s believed that language in posts could be indicators of disease and, with patient consent, could be monitored just like physical symptoms.

Using an automated data collection technique, the researchers from the University of Pennsylvania and Stony Brook University in the US analyzed the entire Facebook post history of nearly 1,000 patients who agreed to have their electronic medical record data linked to their profiles.

The researchers then built three models to analyze their predictive power for the patients: one model only analyzing the Facebook post language, another that used demographics such as age and sex, and the last that combined the two datasets.

Looking into 21 different conditions, researchers found that all 21 were predictable from Facebook alone. In fact, 10 of the conditions were better predicted through the use of Facebook data instead of demographic information.

“This work is early, but our hope is that the insights gleaned from these posts could be used to better inform patients and providers about their health,” said Raina Merchant, an associate professor at the University of Pennsylvania.

“As posts are often about someone’s lifestyle choices and experiences or how they’re feeling this information could provide additional information about disease management and exacerbation,” Merchant said.

Some of the Facebook data that was found to be more predictive than demographic data seemed intuitive.

For example, “drink” and “bottle” were shown to be more predictive of alcohol abuse. However, others were not as easy.

For example, the people that most often mentioned religious language like “God” or “pray” in their posts were 15 times more likely to have diabetes than those who used these terms the least.

Additionally, words expressing hostility — like “dumb” and some expletives — served as indicators of drug abuse and psychoses.

“Our digital language captures powerful aspects of our lives that are likely quite different from what is captured through traditional medical data,” said Andrew Schwartz, an assistant professor at Stony Brook University.

“Many studies have now shown a link between language patterns and a specific disease, such as language predictive of depression or language that gives insights into whether someone is living with cancer,” said Schwartz.

“However, by looking across many medical conditions, we get a view of how conditions relate to each other, which can enable new applications of AI for medicine,” he said.

Last year, many members of this research team were able to show that the analysis of Facebook posts could predict a diagnosis of depression as much as three months earlier than a diagnosis in the clinic.

This work builds on the study and shows that there may be potential for developing an opt-in system for patients that could analyze their social media posts and provide extra information for clinicians to refine care delivery.

Leave a Reply

Latest news

Khattar makes NRC election pitch before Haryana poll

While members of even the ruling coalition in Assam are unhappy with the way has panned out in their state, some BJP leaders are going around the country promising a similar exercise nationwide

Gangwar retracts: North Indians unemployable, he’d said

When recruiters arrive, they say the quality of candidates they are looking for is not in adequate supply in these areas, Union Minister of State (independent charge) for Labour and Santosh Gangwar had said in Bareilly on Saturday

Crude oil supply crisis in market for the first time due to attack on Saudi plant

Due to the drone attack by rebels, supply has decreased by 5.7 million barrels per day, which is 6% of the global supply

Bheto Bangali: Why And How You Identify One

A one-word translation for 'bheto' may be an exercise in futility; phrases like 'rice-influenced' or ‘rice-oriented’ do serve as literal translations while not quite bringing out the rich and diverse connotations of this one-word nomenclature used to describe the typical Bengali mentality, one that transcends diet and encompasses multiple aspects of life
- Advertisement -

Freight Equalisation Policy Crippled Bihar, Bengal, Odisha

The equalisation policy ensured that Maharashtra and Gujarat enjoyed hegemony in metal as well as cotton while Bihar, Bengal and got an upper hand in none

Salman Khan gifted her no house, says Ranu Mondal

If Salman Khan had given me a house, he would have presented it to me in front of everyone: social media sensation-turned-singer Ranu Mondal

Must read

- Advertisement -

You might also likeRELATED
Recommended to you

%d bloggers like this: