Smartphones and Mental Illness: How an LSU Professor Uses AI to Empower Patients and Doctors |  News

Smartphones and Mental Illness: How an LSU Professor Uses AI to Empower Patients and Doctors | News

Can smartphones detect mental health patterns and help clinicians evaluate patients?

Psychology professor Alex Cohen has been researching this question since he was in graduate school 20 years ago. Today, he’s collaborating with psychology students and faculty from LSU and beyond to look at how smartphone technology can help clinicians with mental health assessments.

LSU researchers have received a $1.4 million grant to study the impact of severe weather turbulence on the western part of the Gulf of Mexico.

“The reason I did this is because I never trusted my symptom ratings, my diagnoses, you know, I just saw people too complex to be reduced to a single digit. And so, using objective techniques, whether it’s from a smartphone or from a recording audio, video, or anything else, gives you richer data and more flexibility for people to understand,” Cohen said.

Cohen has developed an app that uses self-report assessments, geo-location tracking, and video diaries to look at various mental health issues. People send in data from all over the world, and Cohen and his team analyze various factors such as language patterns, singing, and facial expressions.

“We can … use computer modeling to try to predict how [people are] How they would do, how would they act, how might they respond to medication or treatment, how might they respond to stress and things like that,” Cohen said.

According to Cohen, symptoms can be traced through analyses. For example, Cohen said that if someone is concerned about depression, they can look at the person’s behavior throughout the day, how often they leave their home, the expressions and words they use in the video diaries and how they refer to themselves and others.

On the other hand, if someone wanted to consider mania, Cohen said they would do a similar analysis with “opposite expectations.” Looking at someone’s geographic location, Cohen said he expects more late-night activity, as well as animated expressions and a faster speech rate during video diaries.

Cohen said his research so far has shown that people express themselves in different ways, so even doctors’ best diagnoses aren’t always accurate.

“There’s one big finding, and nobody likes it — but that’s that doctors aren’t nearly as reliable as they think,” Cohen said. “Doctors … tasked with dealing with seriously mentally ill persons, [have] The very difficult task of evaluating them and trying to observe their behavior and compare it to some kind of imaginary standard.”

Cohen recently partnered with the Capital Region Human Services District, a company that provides public services for mental health and developmental disabilities in Baton Rouge and surrounding areas, to test the research and technology.

He said there is still “a tremendous amount of work to be done”, and the research faces many challenges, including figuring out how to translate analyzes across different types of people.

“We don’t all talk the same way, we don’t all express things the same way, we don’t all have the same patterns and timelines and things like that, you know,” Cohen said. “The Big Other [challenge] is to figure out how to make this sustainable.”

A biologist at LSU, in collaboration with NASA, has investigated how plants adapt to toxic soils that have high amounts of salt in them, similar to…

He said clinicians could benefit from this research by receiving more accurate data to work with, rather than relying solely on patient responses. Technology also has the potential to reduce waiting times in emergency rooms and improve patients’ response to treatment.

“I think we can develop tools that clinicians can use…[and] Empowering patients, their families and peer support groups, so they can better understand their illness and better predict what happens [and] Better manage treatments so that they reduce side effects…if they have on hand, you know, objective data that’s easily accessible, if patients are able to provide that…we’ll see better collaboration between patients and their doctors,” Cohen said.

Clinical Psychology graduate student Camille Warren has been working with Cohen since she was an undergraduate.

Warren’s research focuses on linguistic analysis of speech patterns through mobile phone assessments and looking at how often patients say certain words. Warren emphasized the importance of collecting a variety of data and not using basic research models as a method for stereotyping.

“We shouldn’t try to like, and separate these individuals in their analysis against each other, like African Americans versus Caucasian Americans…You have to make sure you have accurate samples, and like a variety of samples to train the model so you don’t find correlations that aren’t really helpful. Warren said.

Warren said she wants to do research with greater diversity to determine if current assessments are accurate. She mentioned how African Americans are more likely to develop schizophrenia than their white counterparts, and wanted to know if there’s something researchers aren’t looking at that is causing it.

“I don’t just want to explain these things, but I want to improve treatment. But before you can do that, you have to understand where the contrast comes from first.”

In the future, Warren said, the lab will collect a greater variety of samples to train their research model.

Clinical psychology graduate student Edward Granrod is also conducting research in Cohen’s lab and looking specifically at how what patients say affects their voice. To do this, Granrud looks at the keywords patients use and their phonetics to detect any patterns.

Like Warren, Granrod notes that diversity is an important factor when collecting data, and one of the challenges they face in the lab is how to use their findings for a broader population.

“How do we develop something that will be useful to so many people? This is difficult, especially when you then look at different cultural backgrounds such as races and countries.

Granrud’s research also takes into account how people’s speech patterns may change depending on their current environment, noting that there will be a difference in how someone talks to their family members versus a doctor.

While the research is still a work in progress, Granrud believes it has the potential to create greater access to mental health care.

“If this works, I think you will have this huge positive impact, not just like mental health care in America, but also in other countries that have fewer resources,” Granrod said. “What this does is that it potentially gets off the playing field so that more people can access help and that whatever resources are available to the system can be allocated in a fair way to those who need help to get it.”

#Smartphones #Mental #Illness #LSU #Professor #Empower #Patients #Doctors #News

Leave a Comment

Your email address will not be published. Required fields are marked *