A computer program was made that can help diagnose post-traumatic stress disorder in veterans by analyzing their voices. A study in the journal of Depression and Anxiety found that the AI tool can distinguish between the voices of those with or without PTSD with 89 percent accuracy. PTSD diagnosis is commonly determined by clinical interview or self-report assessment. These can be prone to bias and can be unreliable at times.
Researchers are currently using random forests, a statistical/machine learning technique, which has the ability to learn how to classify individuals based on examples. The AI program can build decision rules and mathematical models that enable decision-making with increasing accuracy as the amount of training data grows.
To learn more about how the AI works, check out the original article by Science Daily here.