Bias Discovery in Machine Learning Models for Mental Health
This addresses fairness issues in AI for clinical psychiatry, but it is incremental as it applies existing bias mitigation methods to a new domain.
The study tackled bias in machine learning models for mental health by analyzing a model trained on clinical psychiatry data to predict benzodiazepine administration, finding gender-based bias and implementing mitigation strategies that affected model performance.
Fairness and bias are crucial concepts in artificial intelligence, yet they are relatively ignored in machine learning applications in clinical psychiatry. We computed fairness metrics and present bias mitigation strategies using a model trained on clinical mental health data. We collected structured data related to the admission, diagnosis, and treatment of patients in the psychiatry department of the University Medical Center Utrecht. We trained a machine learning model to predict future administrations of benzodiazepines on the basis of past data. We found that gender plays an unexpected role in the predictions-this constitutes bias. Using the AI Fairness 360 package, we implemented reweighing and discrimination-aware regularization as bias mitigation strategies, and we explored their implications for model performance. This is the first application of bias exploration and mitigation in a machine learning model trained on real clinical psychiatry data.