Through a partnership with the Metropolitan Area Human Services, one of the largest providers of behavioral health services in Louisiana, LSU is leveraging AI technology to spot early warning signs of serious mental illness and improve treatment.
LSU psychology professor Alex Cohen is working to treat serious mental illnesses using artificial intelligence. He is developing a smartphone app that can track speech and facial expressions to alert them, their families and treatment teams of mental decline to help prevent costly – and frightening – and suicide emergencies. It recently partnered with the Capital District Human Services District, or CAHSD, one of the largest providers of behavioral health services in Louisiana. Headquartered in Baton Rouge, CAHSD serves about 10,000 people in seven surrounding parishes – Ascension, East and West Baton Rouge, East and West Feliciana, Iberville and Pointe Coupee. Through a pilot project led by Cohen, LSU is now providing patients in the CAHSD program with first episode psychosis, or FEP, with phones preloaded with Cohen’s app, called QITraq.
Patients in the FEP program are especially at high risk, and as such would benefit from the kind of ongoing support that Cohen’s technology enables, according to Outreach Services Mental Health Program Director Paul Tuminello at CAHSD.
“Our FEP patients have a hard time dealing with the first episode of psychosis,” Tuminello said. “Most of them have little treatment history, experience, knowledge or support, which takes time to develop, grow and maintain.”
We treat not only individuals, but their families as well. “Families are involved and some have limited knowledge and experience in dealing with delusions, hallucinations and other symptoms that their loved ones are experiencing. It can be a very frightening situation for everyone.”
Patients on FEP often experience paranoia. Getting them to trust technology that tracks what they say and think can be a huge hurdle, but Tuminello believes in transparency and putting patients and their families accountable for how and when technology is used. He also says that the feeling of not feeling completely alone can also be positive for patients and their families.
“Importantly, any data we collect is incredibly useful for modifying treatment planning and medication,” Tominello said. “We are a mobile service provider, so we work in the community and in customers’ homes, but we can’t be with them all the time. LSU’s cutting edge technology can help us determine if medications and treatment methods are working more accurately, so that patients don’t end up in hospital, to higher levels of care, or worse yet, in prison.We can precisely define the focus of treatment to meet the specific needs of a client – even if they have difficulty articulating what is happening during their sessions – with the additional information the app provides us after the session ends.
Although one in 30 Louisiana adults is diagnosed with a serious mental illness compared to one in 20 people in the country overall, the social, emotional, and economic burden is significant. Serious mental illness hampers productivity, burdens health care and law enforcement, and is a major driver of homelessness.
Globally, the direct and indirect cost of mental illness is estimated to be more than $6 trillion by 2030 – higher than the current GDP of any country, except for the United States and China.
The burden of mental illness is also imbalanced between black and white Americans, rich and poor. In Louisiana, a state with stark health disparities, differences in how these diseases are diagnosed and treated are particularly evident, says Professor Alex Cohen of LSU — largely because mental health care is so expensive.
“We have three parallel care systems,” Cohen said. “For the wealthy, there are private hospitals that provide extensive care and connectivity. For the connected and insured people, there is a network of private and public systems with community mental health centers, emergency rooms, and intensive outpatient clinics. For the disconnected poor, there are prisons, and you can imagine How does race and the economy of Louisiana play into this?
Cohen is the academic advisor for LSU doctoral student in psychology Kiara “Kamel” Warren, who grew up in North Baton Rouge where she witnessed many non-residential residents struggle with their mental health. As an African American, she wanted to join Cohen’s lab to conduct culturally sensitive research to address the many inequalities she saw in how mental illness is diagnosed and treated.
“One of the major inequities I see is the lack of African American mental health professionals and certainly the lack of African American women doing the research,” Warren said. African Americans should have a hand in interpreting data on African Americans’ mental illness to ensure that cultural nuances are not hidden. We live in an age when many people are becoming more aware of mental illness and how it can negatively affect their daily lives if left untreated. I hope more people will be encouraged to seek treatment if they see that the data has been analyzed with them in mind, and AI can help. AI has the potential to create unbiased analyzes that allow for better representation of different societal groups.”
The partnership with CAHSD, which serves a diverse population, has been key to Cohen. Its application should be used by people of different cultural and environmental conditions in order to become more equitable and responsive to their needs. Cohen also aims to use QITraq to identify unintended cultural and racial bias in physician-patient interactions. As an example, black Americans are two to three times more likely than white Americans to be diagnosed with schizophrenia, and it is not clear why.
“This is why community engagement and collaboration like this is so important,” Cohen said. “Real patients and their families should guide the development of the technology to make it useful and effective for more people on a large scale.”
The data from the pilot project will be used to improve the technology itself, turning massive amounts of ones and zeros into something that is clinically meaningful for CAHSD, but also generalizable to different and diverse populations.
“Even something like depression doesn’t appear or look the same if you’re in North Baton Rouge or South Baton Rouge,” Cohen said. “This is why most mental health apps on the market are bogus, frankly. They may track how often you use words like “depressed” or “sad,” or how often you ignore, but you may be very depressed and even suicidal without Never use these expressions. That’s why our technology captures pitch, volume, pause, and language as well as when and where someone uses a particular set of words.”
“Human speech is incredibly complex — you can extract thousands of features from phonemes alone,” Cohen continued. “To make our technology useful, we must capture key characteristics that can vary from region to region and person to person. People can have unique symptoms, and the complexity and richness of data makes this field ideal for artificial intelligence and natural language processing. Machines are great at sifting and recognizing on patterns in the data that we might otherwise miss.”
For Cohen, a licensed clinical psychologist, the impetus to develop QITraq using artificial intelligence came from what he calls “pure desperation at every stage” in the rapid and accurate assessment of high-risk clients, such as patients in the CAHSD FEP program.
“Although we were trained to do this, I found that I did not trust my clinical evaluations,” Cohen said. “I would sit with someone for an hour and hear them talk and then limit this complex interaction to a single number to guide treatment. As a clinician, I’ve always struggled with this and wanted more effective assessment tools.”
Cohen is careful to point out that Katrak is not intended to replace clinicians, but rather to provide them with additional, objective data that cannot easily be captured simultaneously, for example, when a mental health provider and their client are able to sit down. face to face.
“For people who have just experienced a psychotic break for the first time, things tend to be especially confusing and confusing,” Cohen said. “It’s a critical time in treatment that affects people’s trajectory — how well they function or become disabled over time.”
Paul Tuminello of CAHSD looks forward to heading into clients’ homes with a clearer idea of what to expect and what to do.
“With the LSU app, we will continue to get data even when we are not there; so when we show up, we will be more than willing to help,” Tominello said. And if this works for the critically ill population, it could be the start of a major transformation of mental health care in general. Imagine what this technology could do to help a depressed and anxious student, or an elderly patient experiencing loss. The applications are endless.”