Cognitive Computing

IBM 5 in 5: With AI, our words will be a window into our mental health

Share this post:


As a neuroscientist, I want to understand the brain. Beyond just the physical structures of neurons and the synapses, but how it works. How is it that we think? How is it that two pounds of protein and water can produce this amazing, complex organ that literally drives humanity? Ultimately, behavior is what the brain is for. We, in the scientific and medical community, are studying behavior with the same types of computational approaches that we use to study the physical attributes and workings of the brain.

Nearly 20 percent of individuals in the United States alone will experience a mental health condition sometime in their life. Ranging from the neurological (Huntington’s, Alzheimer’s, Parkinson’s etc) to mental (depression or psychosis) the global cost of treating mental disorders are greater than the cost of diabetes, respiratory disorders or cancer combined.

IBM 5 in 5

How can we help the doctors and patients who are impacted by these diseases? Could we, using computational biology, analytics and machine learning, build tools to quickly and simply analyze language and predict the onset of these diseases to allow for earlier intervention, better allocation of resources or better treatment planning?

We think so. In a study with Columbia University psychiatrists, we were able to predict, with 100 percent accuracy, who among a population of at-risk adolescents would develop their first episode of psychosis within two years. In other research with our Pfizer colleagues, we’re using only about 1 minute of speech from Parkinson’s patients to better track, predict and monitor the disease. We’re already seeing results of nearly 80 percent accuracy. In five years, we hope to advance the study of using words as windows into our mental health.

Some days I think I am more philosopher than scientist, but I am often reminded that those roles, like those of the neurons and behavior in the brain, are two halves of the same function. The field of neuroscience is moving quickly – we know so much, but still have much more to uncover.

What is the prediction?

In five years, what we say and write will be used as indicators of our mental health and physical wellbeing. Patterns in our speech and writing analyzed by cognitive systems will provide tell-tale signs of early-stage mental disease that prompt us to seek treatment.

 Why will this change the world?

Today, analysis of language is done in a labor-intensive process of manually interviewing and recording multiple lengthy sessions with a patient. There is no way to quantify or codify these sessions, resulting in a massive “big data” problem. A tool that could, in near real-time, analyze and codify a sample of the patient’s speech and provide an analysis would drastically shorten the time it took for doctors and caregivers to predict and diagnose patients. For all conditions, the earlier a diagnosis is made, the higher likelihood of a successful treatment and management of the disease.

 What is the underlying technology?

IBM is building an automated speech analysis application that runs off a mobile device. By taking approximately one minute of speech input, the system uses text-to-speech, advanced analytics, machine learning, natural language processing technologies and computational biology to provide a real-time, overview of the patient’s mental health.

Related Papers and Patents
Natalia B. Mota, Nivaldo A. P. Vasconcelos, Nathalia Lemos, Ana C. Pieretti, Osame Kinouchi, Guillermo A. Cecchi, Mauro Copelli, Sidarta Ribeiro, “Speech Graphs Provide a Quantitative Measure of Thought Disorder in PsychosisPLOS One.

Gillinder Bedi, Guillermo A Cecchi, Diego F Slezak, Facundo Carrillo, Mariano Sigman and Harriet de Wit, “A Window into the Intoxicated Mind? Speech as an Index of Psychoactive Drug EffectsNeuropsychopharmacology.

Gillinder Bedi, Facundo Carrillo, Guillermo A Cecchi, Diego Fernández Slezak, Mariano Sigman, Natália B Mota, Sidarta Ribeiro, Daniel C Javitt, Mauro Copelli & Cheryl M Corcoran, “Automated analysis of free speech predicts psychosis onset in high-risk youthsnpj Schizophrenia.

García AM, Carrillo F, Orozco-Arroyave JR, Trujillo N, Vargas Bonilla JF, Fittipaldi S, Adolfi F, Nöth E, Sigman M, Fernández Slezak D, Ibáñez A, Cecchi GA, “How language flows when movements don’t: An automated analysis of spontaneous discourse in Parkinson’s diseaseBrain and Language.

US Patent No. 9,531,875 – “Using graphical text analysis to facilitate communication between customers and customer service representatives”
US Patent No. 9,508,360 – “Semantic-free text analysis for identifying traits”

Read all of IBM’s 2016 technology predictions at IBM 5 in 5.




More stories

Meet Ari, the Smart Bike that Helps you Catch Green Lights

As more bikes take to the city streets than ever, researchers at RMIT have designed Ari, a smart e-bike that could help riders cruise the ‘green wave’.

Continue reading

Dark Matter Matters: AI Makes DNA Dark Matter Useful

What is the minimal description that captures a space? Asking a mathematician’s basic question of a  biological dataset reveals interesting answers about biology itself. This summarizes our underlying approach to subtyping hematological cancer. Disease subtyping is a central tenet of precision medicine, and is the challenging task of identifying and classifying patients with similar presentations […]

Continue reading

Helping to Untangle Cancer Drug Resistance with Data

Why do targeted cancer therapies often fail? We have acquired so much more understanding about cancer in the last fifty years than in the last five thousand years. Approaches to patient treatments have dramatically changed, and statistics show significant improvement in patient response and outcomes to therapy in the last half a century [1]. Yet […]

Continue reading