Advisory for teams that need to examine how an AI model reaches a prediction, from choosing explanation methods to planning evaluation and human-review steps.
Selected publications, talks, and projects related to this area. Each link opens the work and its original source.
A 2025 preprint applies interpretable machine learning to predict treatment response and remission in body dysmorphic disorder. It examines which baseline factors drive those predictions.
A 2023 preprint tests whether phone-sensor data can forecast changes in schizophrenia symptoms and explain them with counterfactual explanations. It is evaluated in a simulated monitoring setting.
Interpretable machine learning shows that higher baseline anxiety predicts lower odds of improvement in major depressive disorder. The trial compared three smartphone-delivered interventions.
Content on this site is for informational and professional purposes only and is not medical advice. AI systems discussed here require appropriate clinical, legal, regulatory, and safety review before healthcare deployment.