Can Social Media and Machine Learning Transform Mental Health Diagnoses?
Artificial Intelligence (AI) and machine learning are on the rise, and tech companies throughout the world are shifting their focus accordingly. New systems are being integrated into everyday workflows to streamline and simplify processes, and increasingly, make the impossible possible. In a new venture, scientists have turned their attention to how AI might be used in mental health screenings and diagnoses.
Recent studies published in EPJ Data Science journal revealed that applying machine learning tools to Instagram posts might just be the answer. Researchers at Harvard University and University of Vermont led a sample study of 166 individuals, monitoring the posts of people with a clinical diagnosis of depression as well as healthy individuals, or those who did not have a history or official diagnosis of depression.
Utilising machine learning, they were able to identify distinctions in colour choices, image qualities, and filters and enhancements among participants in both categories. These profile patterns were analysed to create a model confirming or predicting depression.
Depressed and undiagnosed depressive individuals tended to post darker images with blue or gray tints, blurred images, and single-face photos more often than their healthy counterparts, who posted brighter or lighter images with more aesthetic enhancements, and multiple faces in a photo. Additional findings revealed that depressed participants generally received more likes on their photos and posted more often.
While the results might not be so clear-cut when applied on a broader scale, the study still paves the way for a more in-depth exploration of how AI might someday be used in mental health screenings—and beyond.
Read the original article here.