AI Can Be A Viable Tool To Study Changes In Mental Health: SAIL and UCLA Study

488
  • Individuals and their treating clinicians used the MyCoachConnect interactive voice and mobile tool
  • The tool has been created and hosted on the Chorus platform at UCLA

According to a report by Hindubusinessline, the USC Signal Analysis and Interpretation Lab (SAIL), in new collaboration with UCLA has found out that artificial intelligence (AI) can accurately detect changes in patient’s clinical state from his or her speech and physician’s inputs. As per the report, SAIL partnered with researchers at UCLA to analyse voice data from patients. These patients were being treated for serious mental illnesses, including bipolar disorder, schizophrenia and major depressive disorders.

MyCoachConnect tool

The report said that the individuals and their treating clinicians used the MyCoachConnect interactive voice and mobile tool.This tool has been created and hosted on the Chorus platform at UCLA, to give voice diaries related to their mental health states. After this, SAIL collaborated with UCLA researchers to apply AI to listen to hundreds of voicemails.

It was done using custom software to detect changes in patients’ clinical states. SAIL AI was able to match clinicians’ ratings of their patients according to the report. Th next step in this research is to scale up the individualised approach to a larger population over longer time periods of observation

Tracking changes in clinical states

As per the report, senior author Dr Shri Narayanan, Niki and Max Nikias Chair in Engineering and Director of SAIL at the USC Viterbi School of Engineering said that machine learning allowed the team to illuminate the clinically-meaningful dimensions of language use and vocal patterns of the patients over time. It helped to personalise it at each individual level. The researchers also said that tracking changes in clinical states is important to detect if there is a change that shows that condition has improved or worsened.

Editor Team

LEAVE A REPLY

Please enter your comment!
Please enter your name here