Why this topic?
We need to find better ways to understand and use cultural information from diverse patients to improve mental health treatment. When healthcare providers consider a patient’s cultural background, treatments are more successful. Ignoring culture can lead to patients quitting therapy early or not getting better.
Our project aims to address this gap by using AI to find culturally important information in therapy notes. We’ll use data from several hundred patients who have agreed to participate in our research. We will be using Natural Language Processing to examine patterns in unstructured notes, then using those findings to make predictions.
Why is this important?
We need to find better ways to understand and use cultural information from diverse patients to improve mental health treatment. When healthcare providers consider a patient’s cultural background, treatments are more successful. Ignoring culture can lead to patients quitting therapy early or not getting better.
Experts agree that good mental health care should include understanding different cultures, being aware of cultural differences, and having skills to work with diverse patients. This approach is thought to help people from various racial and ethnic backgrounds have better outcomes in therapy. However, there’s still debate about the best ways to help therapists become more culturally aware and responsive.
Artificial intelligence (AI) and machine learning (ML) have been used in mental health to help bridge the gap between what therapists know and how they apply that knowledge. These tools have helped therapists better identify symptoms. But right now, there aren’t any AI tools to help identify important cultural information.
Project Status
We are early in this research and looking for help with coding and data entry
If you are a George Mason Student interested in getting involved in research in the lab, please contact Dr. Tonge about openings for research assistants.
If you are a person interested in our results: we’re still very early in the process of research in this area! It may be more than a year before we have results to share. Subscribe for updates below or leave a comment!
TIDL@GMU 