Study finds profound differences in the impact of COVID-19 on mental health!

COVID-19 has revealed stark disparities in the mental health of college students, with some struggling more than others to stay emotionally healthy during the pandemic, according to a new study from Dartmouth College

The multi-year study compared the first year of the COVID-19 pandemic to the year before, showing how college students' mental health and behaviors have changed in response to the public health crisis

The study is the first to use mobile technology to compare the mental health of the same research group over a 12-month period before and during the pandemic, and it shows how smartphone technology and artificial intelligence can be used as an "early detection system" for mental health

Andrew Campbell, Dartmouth College's Albert Bradley 1915 Third-Century Professor of Computer Science, said: "The pandemic has put students on a mental health roller coaster, and most are walking.

The longitudinal study used a smartphone app and a digital questionnaire to assess depression, anxiety and stress in 180 volunteers from the year before the outbreak (March 19 to February 20) to the start of the outbreak University students for the next full year (March 20-February 21)

The study identified two groups of people who experienced the pandemic with very different experiences

Overall, heightened anxiety about COVID-19 was strongly associated with increased depression, anxiety, and stress

"The behavioral changes we're seeing in the student population are consistent with the experiences of the general population and are worrying," said Subigya Nepal, a Dartmouth doctoral candidate and the study's lead author.

On average, the study found that during the pandemic, students' behaviours changed and time spent engaging in multiple activities dropped significantly

Specific findings on the behavioral impact of COVID-19 in the first year include:

• Time at home, sleeping and sedentary all increased

  
  

• College students travel less distance and unique locations

  
  

• The study subjects spent more time using their cellphones, as well as using social media

  
  

• Students spend less time walking, biking and driving

  
  

The research is part of the Student Life computer science research project, which is evaluating the effectiveness of using smartphones to identify and predict anxiety, depression and stress in college students

This is the third research paper in ongoing research since the start of the COVID-19 pandemic

"Such a large amount of continuous data, spanning two years in total, allows us to draw important insights and robust conclusions about the behavioral changes in these students caused by COVID-19," said Campbell, lead researcher and co-author of the study
.

Given the link between anxiety about COVID-19 and general mental health identified in the study, researchers used machine learning techniques to see if artificial intelligence could predict anxiety about COVID-19 as an indicator of emotional health
.

The study, published in the Proceedings of the International Conference on Human Factors in Computational Systems, reports an accuracy of 75 percent and concludes that deep learning models can help classify COVID-19 problems
.
The team says it may be possible to build a machine learning model to predict pandemic concerns and people prone to mental health problems
.

"The technical results are promising," Nipal said
.
"It appears that we will have to live with the pandemic or some variant of it for some time to come, so the insights from our work will be relevant for identifying and managing future mental health aspects of COVID-19
.
"

The research team emphasizes that the study was limited to a small number of undergraduates attending elite universities
.
The research team urges caution in interpreting these results because they don't know how well the findings can be generalized to other populations
.

While recognizing the potential of mobile sensing, the team also identified challenges in using the technology, including concerns about transparency, effectiveness, and privacy
.

Future work will include determining whether the technology could be used as an early detection system, and could also provide personalised advice to help people through difficult times, or notify providers with their consent so they can inform individuals help
.

Courtesy of Dartmouth College