All Models are Biased, Some are More Transparent about it: Fully Interpretable and Adjustable Model for Mental Disorder Diagnosis
Keywords: interpretable AI, mental health, k-NN, neural symbolic, explainable AI, tunnable AI
TL;DR: We use a neural network model to simulate a weighted k-NN. The resulted model is fully interpretable and trainable. We apply that on a mental disorder diagnosis task and interviewed psychologists for their subjective opinions.
Abstract: Recent advances in machine learning have enabled AI applications in mental disorder diagnosis, but many methods remain black-box or rely on post-hoc explanations which are not straightforward or actionable for mental health practitioners. Meanwhile, interpretable methods, such as k-nearest neighbors (k-NN) classification, struggle with complex or high-dimensional data. A network-based k-NN model (NN-kNN) combines the interpretability with the predictive power of neural networks. The model prediction can be fully explained in terms of activated features and neighboring cases. We experimented with the model to predict the risks of depression and interviewed practitioners. The feedback of the practitioners emphasized the model's adaptability, integration of clinical expertise, and transparency in the diagnostic process, highlighting its potential to ethically improve the diagnostic precision and confidence of the practitioner.
Primary Area: interpretability and explainable AI
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12930
Loading