Supervised topic models for clinical interpretability
arXiv:1612.01678
Abstract
Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels will be negligible. Second, due to conditional independence assumptions in the graphical model the impact of supervised labels on the learned topic-word probabilities is often minimal, leading to poor predictions on heldout data. We investigate penalized optimization methods for training sLDA that produce interpretable topic-word parameters and useful heldout predictions, using recognition networks to speed-up inference. We report preliminary results on synthetic data and on predicting successful anti-depressant medication given a patient's diagnostic history.
Accepted poster presentation at NIPS 2016 Workshop on Machine Learning for Health (http://www.nipsml4hc.ws/)
References in corpus (1)
Cited by in corpus (5)
- An Evaluation of the Human-Interpretability of Explanation
- How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
- xGEMs: Generating Examplars to Explain Black-Box Models
- Machine Learning and Visualization in Clinical Decision Support: Current State and Future Directions
- Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models