Sudhakar Jha
... Read More
By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. Cookie Policy.
Written By: Sudhakar Jha | Published : September 3, 2018 7:44 PM IST
Massachusetts Institute of Technology has developed a neural network that has the ability to detect signs of depression based on how people talk © Shutterstock
People suffering from depression do not generally shown signs of their condition, due to various reasons, and social stigma attached to being depressed. And when they do talk about it, it s too late many a times. With the busy lives that we all live, we do not even bother looking for signs of depression in friends or family.
However, artificial intelligence in tracking the signs does come in handy! And that s why researchers at the Massachusetts Institute of Technology have actually developed a neural network that has the ability to detect signs of depression based on how people talk. It is believed that this new technology can be applied to all sorts of conversations, like normal day to day talks, where it can predict if the person is depressed. And that too without needing other information.
AI has been used in the past too, to detect depression. On many instances, researchers have used AI to detect depression from Instagram posts. However, there is a major different between the existing models and model that has been created by the MIT.
The earlier models usually require patients to answer specific questions, and it means that there are limitations on how the model can be used effectively to detect depression. On the other hand, MIT s model uses speech patterns to detect depression, without the need for asking specific questions or getting specific answers from the sufferer.
There are further tests needed but as a potential method, this model can definitely be applied to all sorts of conversations. And may be one day we might even witness an app on the same lines which monitor daily conversations and alert the user if it detects any signs of depression.
There are privacy concerns as well with this new model, but if it can be sorted out, then the possibilities of the system are good in detection and subsequent treatment of depression.
