IBM’s Has Created a New AI Which Can Recognize Psychosis in Speech

Humans have used various languages to communicate with each other for millenniums. A language is a spellbinding tool, which helps us express our thoughts, opinions, feelings and bring so much delight. Mankind has witnessed rise and fall of great languages all the while trying to understand what one really means at times when he says what he says.

It’s been said that eyes are the windows to the soul; likewise, language is the window to the inner mind of a human.  If you pay close attention to the speech of man, or language, you can understand the way he thinks or what goes in his mind, his psychosis. Language is also the tool by which psychiatrists evaluate a patient for particular psychoses or mental disorders, including schizophrenia. But unless you are highly trained professional, who has a great listening ability and attention span, and then you can’t possibly understand it, much less analyze the psychosis of man.

Now a brilliant team of IBM engineers, comprising of IBM Research’s Computational Psychiatry Neuroimaging groups and universities all around the world have created an AI, which is capable of predicting with comparable precision the starting of psychosis in a patient.

The World Psychiatry has published an article on IBM’s psychosis- predicting AI.

The group built on the findings of a 2015 IBM study demonstrating the possibility of using AI to model the differences in speech patterns of high-risk patients who later developed psychosis and those who did not. Specifically, they quantified the concepts of “poverty of speech” and “flight of ideas” as syntactic complexity and semantic coherence, respectively, using an AI method called Natural Language Processing (NLP).