Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach
This addresses the costly annotation challenge for medical professionals analyzing conversations, though it is incremental as it builds on existing pseudo-labeling and human-in-the-loop methods.
The paper tackled the problem of automatically classifying medical dialogue into functional sections without requiring large expert annotations, using an iterative pseudo-labeling and human-in-the-loop approach, achieving an improvement from 69.5% to 82.5% accuracy on an expert-annotated dataset.
Medical conversations between patients and medical professionals have implicit functional sections, such as "history taking", "summarization", "education", and "care plan." In this work, we are interested in learning to automatically extract these sections. A direct approach would require collecting large amounts of expert annotations for this task, which is inherently costly due to the contextual inter-and-intra variability between these sections. This paper presents an approach that tackles the problem of learning to classify medical dialogue into functional sections without requiring a large number of annotations. Our approach combines pseudo-labeling and human-in-the-loop. First, we bootstrap using weak supervision with pseudo-labeling to generate dialogue turn-level pseudo-labels and train a transformer-based model, which is then applied to individual sentences to create noisy sentence-level labels. Second, we iteratively refine sentence-level labels using a cluster-based human-in-the-loop approach. Each iteration requires only a few dozen annotator decisions. We evaluate the results on an expert-annotated dataset of 100 dialogues and find that while our models start with 69.5% accuracy, we can iteratively improve it to 82.5%. The code used to perform all experiments described in this paper can be found here: https://github.com/curai/curai-research/tree/main/functional-sections.