Anxiety is a very common problem as many people experience it. Anxiety almost affects 12% of the US population. It affects a person’s mental and physical health very badly. It can also increase the risk of many health complications so early detection is very important. Â
In a recent study conducted by researchers from northwestern University and the University of California have developed a new form of artificial intelligence (AI) that can predict whether a person has anxiety. This AI uses a short picture rating task and a small set of contextual variables to make accurate predictions. Researchers used minimal computational resources and a small set of variables, and they called them “Comp Cog AI”. They used it to predict anxiety levels. This method combined AI and computational thought. Â
This study was recently published in npj Mental Health Research. In this study, researchers used machine learning algorithms to predict current levels of anxiety in 3,476 people. These participants were asked to rate 48 pictures if they liked or disliked them with mildly emotional subject matter. This data is then used to quantify mathematical features of people’s judgments and predict current levels of anxiety. Â
When researchers observed the collected data, they found that the technology they used was able to predict levels of anxiety. This technology was 81% accurate in predicting higher or lower levels of anxiety. This picture rating task is very effective and can predict a person’s mental health status without asking direct questions that can make him feel bad or negative. This technology can be used to predict anxiety levels in many settings as it is independent of a person’s native language. Â
The researchers of this study think that they can use this method and develop an app for healthcare professionals, hospitals and the military. So, they can help them identify if a person is experiencing anxiety. This technology is very helpful as it can effectively predict the levels of anxiety. So, it will be very useful to reduce the risk in the future. Â
Reference Link:Â
Sumra Bari et al, A novel approach to anxiety level prediction using small sets of judgment and survey variables, npj Mental Health Research (2024). Â
