Researchers at the University of California, San Diego (UCSD), are using a novel device to study the behavior of patients with mental illnesses, such as bipolar disorder and schizophrenia. The device, called a behavioral-pattern monitor, combines a computerized vest, worn by the patient, and a video camera, embedded in the ceiling. Monitoring the patient with this technology could enable researchers to more accurately diagnose disorders and test the effectiveness of treatments.
“When patients with bipolar disorder and schizophrenia are very symptomatic and psychotic, they often look very similar, and this makes it hard to discern one population from the other,” says William Perry, a professor of psychiatry at UCSD and the lead investigator in the study, whose preliminary results reveal very distinct patterns of activity among patients within these two patient groups. The study uses the behavioral-pattern monitor and is being funded by the National Institute of Mental Health. “By analyzing these unique signature patterns, we hope to learn about the brain functioning in psychotic individuals in ways that current observation methods cannot.”
Diagnosing mental illness is complicated because there are no laboratory tests or physical changes in patients that make the problem obvious; there are only observatory methods of diagnosis, such as talking to patients and rating their symptoms, says Carol Tamminga, a psychiatry professor at the University of Texas’s Southwestern Medical Center, in Dallas. “It is one of the major difficulties in mental illness these days, and the reason the field is looking to move … to more brain-related information.”
For example, if a patient comes in and says she is hearing voices, psychiatrists don’t really know what this means to the patient or if it’s even true, explains Perry.
Researchers at UCSD will be tracking and evaluating the movement patterns of patients wearing a computerized vest, called the LifeShirt, developed by Vivometrics, a company based in Ventura, CA. Part of the behavioral-pattern monitor, the vest is embedded with sensors that measure the physiological responses of patients as they explore a novel environment, in this case a room containing different objects but no chairs. The vest is also equipped with an accelerometer that measures the G forces applied to it. The accelerometer is of particular importance to the UCSD researchers because it enables them to measure how these patients are interacting with their environment–are they walking, moving quickly, standing still, or fidgeting?–and it creates a signature of their activity.
The researchers also capture a patient’s movements using a video camera inserted in the ceiling of the room. The footage taken with the camera is turned into images that are converted into XY coordinates using an algorithm developed by coinvestigator Martin Paulus, also a professor of psychiatry at UCSD. With the XY data, Perry says that he and his colleagues can predict exploratory patterns and gauge the extent to which the patient’s behavior is chaotic and unpredictable. The data from the accelerometer was coordinated with the video data to create a pattern of behavior for each patient in the study.
The study is in its fourth year, and the researchers are evaluating both medicated and nonmedicated patients, then comparing them to healthy individuals. And while the results are preliminary, Tamminga thinks that Perry’s work could have an impact on psychiatry. “Currently, psychiatrists do not have any device that is specific enough to tell them about an illness. We have some human brain imaging through MRI and EEG studies, but none of these have been close to a diagnostic test.”
Perry says that if the appropriate behavioral signatures can be distinguished, the system could be used by drug companies to test the effectiveness of some medications. But the UCSD system is challenging because it makes the assumption that body movements are in perfect synchrony with the brain. This is sometimes true, but not always, says Tamminga.
To make this device applicable for psychiatry, the researchers need to conduct further studies that show how useful it is actually going to be in distinguishing between undiagnosed groups, says John Gilmore, professor of psychiatry and vice chair of research in the department of psychiatry at the University of North Carolina.
Perry’s ultimate goal: “We want someone to come into a room and spend 15 minutes, and based on the analysis, we can say the probability of this person having an attentional disorder or schizophrenia is quite high.”
Over the next couple of years, the researchers hope to improve the system and conduct a large study involving different medications and disorders.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
How Charm Industrial hopes to use crops to cut steel emissions
The startup believes its bio-oil, once converted into syngas, could help clean up the dirtiest industrial sector.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.