Advancements in psychology heavily rely on interaction between the doctor and the patient. Computers are rarely used as the main diagnostic tool due to the complex variables related to brain functionality.
Simply put, machines are not able to fully grasp the delicate intricacies of the human mind- not yet.
But closing the gap between computers and medical applications in the field of psychiatry is Columbia University, the New York State Psychiatric Institute, and the IBM T.J. Watson Research Center. The group released a groundbreaking study that could change the way doctors profile their patients.
Using a speech computer program, the team was able to successfully detect the development of psychosis with 100 percent accuracy; compared to traditional screening methods, such as biomarkers from neuroimaging and EEG recordings of brain activity, which are only able to detect the problem 79 percent of the time.
Searching for Speech Disruptions
During the analysis stage, doctors usually look for a spectrum of behaviors associated with the early onset of schizophrenia. One of these is disruptive speech. To capitalize on this warning sign, researchers designed algorithms that carefully sift through conversations, searching for sudden shifts in topics and information. Those who had at least one disruptive shift within the 45-minute session were highly prone to schizophrenic episodes.
“In our study, we found that minimal semantic coherence — the flow of meaning from one sentence to the next — was characteristic of those young people at risk who later developed psychosis,” said Guillermo Cecchi, one of the investigators from IBM Research. “As an interviewer, if my mind wandered briefly, I might miss it. But a computer would pick it up.”
Here is an example of an auditory exchange that was flagged during the study (the patient eventually developed psychosis within the two-and-a-half year window):
I was always into video games. I mean, I don’t feel the urge to do that with this, but it would be fun. You know, so the one block thing is okay. I kind of lied though and I’m nervous about going back.
Other symptoms that doctors look out for during diagnosis include peripheral thinking, suspiciousness and sudden changes in general emotion.
While the study showed very promising results, there’s still a lot left to uncover before the nascent technology hits mainstream practice. A wider demographic is needed to test the accuracy of the software, as the initial research was limited to at-risk youths.
Additionally, different versions of the program might be needed when testing for specific types of psychosis, namely bipolar, drug-induced, schizoaffective and etc.
“We know that thought disorder is an early core feature of schizophrenia evident before psychosis onset,” explained Cheryl Corcoran, an assistant professor of clinical psychiatry at Columbia University.
“The main question then is: What are the brain mechanisms underlying this abnormality in language? And how might we intervene to address it and possibly improve prognosis? Could we improve the concurrent language problems and function of children and teenagers at risk, and either prevent psychosis or at least modify its course?”