Clinical Tagging with Joint Probabilistic Models
This addresses the challenge of clinical tagging for healthcare applications, but it is incremental as it builds on existing probabilistic graphical models with a focus on noisy labels.
The authors tackled the problem of predicting clinical conditions from electronic medical records without gold-standard labels by using noisy anchors, and their method outperformed baselines that ignored label noise or did not model conditions jointly.
We describe a method for parameter estimation in bipartite probabilistic graphical models for joint prediction of clinical conditions from the electronic medical record. The method does not rely on the availability of gold-standard labels, but rather uses noisy labels, called anchors, for learning. We provide a likelihood-based objective and a moments-based initialization that are effective at learning the model parameters. The learned model is evaluated in a task of assigning a heldout clinical condition to patients based on retrospective analysis of the records, and outperforms baselines which do not account for the noisiness in the labels or do not model the conditions jointly.