CHENNAI: A recent study on AI through motion sensors and deep learning techniques revealed that AI could detect behavioural signs of anxiety with over 90% accuracy.
The research, published in pervasive and mobile computing, was conducted with data from adult participants, where their movements were recorded with the use of a sensor when they each performed a series of activities in a particular order.
Several symptoms of mental health issues such as anxiety can be assessed and recorded through AI.
Research studies have shown that AI is providing a breakthrough in detecting mental health problems and preventing its severity.
“Measurement of any behavioural aspects, if done correctly and in collaboration with a mental health practitioner for any post-diagnostic support, is crucial to improve the quality of life of individuals,” says Dr Srividhya Sekar, head of psychology at Safeguard Family.
However, since AI research in mental health is still in its infancy, more research is needed. “We must study the overall risks with the benefits of designed application and its replication in the real world. If designed well, AI tools can aid in early detection, evaluation, and treatment of psychological illnesses and may possibly help with prevention efforts as well,” adds Dr Srividhya.
However, experts opine that AI will not be able to replace the much-needed ‘human touch’ in healthcare, yet it can make life easier and reduce burnout for those dedicated to shaping a better future for medicine.
“Certain bodily functions such as biting of nails, tapping of legs and hands, knuckle cracking, scratching and others – can be due to mental health issues. These can be identified and recorded by AI. However, it’s applicable to certain specific concerns. This must be followed by a direct consultation with a licensed practitioner to fully understand the root cause of the symptoms,” clarified consultant psychologist Dr S Raman.
Visit news.dtnext.in to explore our interactive epaper!
Download the DT Next app for more exciting features!
Click here for iOS
Click here for Android