There is a computer program 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. A clinical interview is commonly used to determine a PTSD diagnosis. The other method utilized is self-report assessment. However, these two methods can be prone to bias and can be unreliable at times. In other words, this innovation could be groundbreaking in the field of PTSD research and have a significant impact on veterans and their families.
Researchers are currently using random forests, a learning technique, which learns how to classify individuals based on examples. Therefore, this will allow the computer program to build decision rules and mathematical models that enable decision-making with increasing accuracy. Evidently, a computer program that can build decision based rules and mathematical models is extremely valuable. Machine learning can come into play with the programs ability to use rules and models. In conclusion, this breakthrough may be one of the best use cases for artificial intelligence that has been found yet.
To learn more about how the AI works, check out the original article by Science Daily here.