Imagine having the ability to predict someone’s anxiety level just by having them rate a couple of pictures and answer some easy questions.
That’s exactly what researchers from the University of Cincinnati and Northwestern University have achieved with their “Comp Cog AI” system.
By combining AI with the science of how our minds process information, they’ve created a tool that may accurately discover individuals who may be combating anxiety.
The study, published in Mental Health Research, involved over 3,000 participants from across the US.
Each person rated a series of mildly emotional images from the International Affective Picture System (IAPS) and provided basic details about themselves, akin to age and perceived loneliness.
IAPS was developed by the Center for the Study of Emotion and Attention on the University of Florida. It provides a standardized set of photographs rated for his or her emotional content when it comes to valence (pleasantness), arousal (intensity), and dominance (control).
An example of a picture from the International Affective Picture System (IAPS). Source: Mental Health Research.
The AI system then analyzed this data, searching for patterns in the best way people responded to the images and the way these responses related to their anxiety levels.
After training, the Comp Cog AI system was capable of predict anxiety with as much as 81% accuracy, offering hope for a future where mental health challenges may be identified and addressed more effectively.
As lead writer Sumra Bari explains, “We used minimal computational resources and a small set of variables to predict anxiety levels. An necessary set of those variables quantify processes necessary to judgment.”
More concerning the study
Here’s more about how the study worked:
- Data collection: Participants accomplished an image rating task, assigning rankings from -3 (dislike very much) to +3 (like very much) to 48 mildly emotional images from IAPS. They also answered questions on their age, perceived loneliness, and demographic information.
- Feature extraction: The AI system extracted 15 key judgment variables from the image rating data, akin to loss aversion, risk aversion, and reward-aversion consistency. These variables quantify biases in reward/aversion judgments and have been linked to brain systems implicated in each judgment and anxiety.
- AI training and prediction: The researchers used Random Forest and balanced Random Forest machine learning algorithms to coach the AI system on a subset of the information. The AI used the judgment variables and contextual aspects to predict each participant’s anxiety level, as measured by the state anxiety portion of the State-Trait Anxiety Inventory (STAI).
- Model evaluation and interpretation: The trained AI system was tested on the remaining data to evaluate its accuracy, sensitivity, and specificity in predicting anxiety levels. The researchers also conducted mediation and moderation analyses to know how the judgment variables and contextual aspects interacted to model anxiety.
The 4 most significant predictors – age, loneliness, household income, and employment status – contributed 29-31% of the model’s predictive power, while the 15 judgment variables collectively contributed 55-61%.
Co-senior writer Aggelos Katsaggelos highlighted the importance of the study’s approach, stating, “Use of an image rating task with contextual variables that affect judgment could appear easy, but understanding patterns in preference allows us to uncover the critical components for a big set of behaviors.”
The researchers envision developing the Comp Cog AI technology right into a user-friendly app for healthcare providers, hospitals, and even the military to quickly discover individuals at high risk for anxiety.
As Bari notes, “The picture-rating task may be used to supply every day and unbiased snapshots of an individual’s mental health status without asking direct questions which can trigger negative or upsetting feelings.”
Previous research harnessed AI to assist diagnose schizophrenia, while tools have been developed to deliver AI therapy to those with mental health conditions through digital avatars.
