Tell me how you really feel: AI analyzes unbound verbal expression to personalize mental healthcare
Psychology researchers have demonstrated a way to finetune diagnoses of major depression and generalized anxiety disorder by analyzing freely elaborated thoughts and feelings using machine learning and natural language processing.
The team suggests the technique, called QCLA for question-based computational language assessment, can help round out conventional mental-health rating scales in clinical settings.
QCLA differs from conventional closed-end rating scales in that the latter require patients to rate their agreement with predefined items presented to them by a static template, the psychologists explain in a study published this month in Frontiers in Psychology.
To test the experimental free-expression technique, Katarina Kjell, Per Johnsson and Sverker Sikström, all of Lund University in Sweden, had 411 participants freely describe their mental health with both words and rating scales.
Using NLP and machine learning to analyze the responses, Kjell and colleagues found QCLA measures closely correlated with scales and descriptions for both major depression and generalized anxiety as published in the Diagnostic and Statistical Manual of Mental Disorders (DSM–5).
They additionally noted that individual measures of primary criteria—cognitive and emotional aspects—were better predictors of illness state than behavioral aspects, which are considered secondary measures.
Together these results “suggest that QCLA may be able to complement rating scales in measuring mental health in clinical settings,” the authors write.
More:
We believe that the QCLAs could be of great importance for clinical research and practice, where word-responses are coupled with objectively measured outcomes. Further, because the QCLA method is based on the respondent’s own descriptions of their experiences and symptoms related to a construct, the method carries the potential to personalize assessments, which might contribute to the ongoing discussion regarding the diagnostic heterogeneity of depression.”
The study is available in full for free.
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.