Weakly Supervised Medication Regimen Extraction from Medical Conversations

TL;DR

This paper introduces a weakly supervised approach for extracting medication-related information from medical conversations, utilizing a novel transformer-based attention scoring method to improve extraction accuracy and reduce annotation effort.

Contribution

The paper presents a new dataset and a transformer-based attention scoring function (TAScore) for span extraction in medical conversations, achieving significant accuracy improvements.

Findings

10-point increase in Longest Common Substring F1 score

Effective weakly supervised span extraction model

Novel TAScore attention mechanism

Abstract

Automated Medication Regimen (MR) extraction from medical conversations can not only improve recall and help patients follow through with their care plan, but also reduce the documentation burden for doctors. In this paper, we focus on extracting spans for frequency, route and change, corresponding to medications discussed in the conversation. We first describe a unique dataset of annotated doctor-patient conversations and then present a weakly supervised model architecture that can perform span extraction using noisy classification data. The model utilizes an attention bottleneck inside a classification model to perform the extraction. We experiment with several variants of attention scoring and projection functions and propose a novel transformer-based attention scoring function (TAScore). The proposed combination of TAScore and Fusedmax projection achieves a 10 point increase in Longest Common Substring F1 compared to the baseline of additive scoring plus softmax projection.