Neural Medication Extraction: A Comparison of Recent Models in Supervised and Semi-supervised Learning Settings
This addresses the challenge of encoding drug prescriptions in electronic medical records for healthcare professionals, but it is incremental as it focuses on comparing existing models rather than introducing new ones.
The paper tackled the problem of extracting medication information from free-text medical reports by evaluating neural architectures on the I2B2 dataset in supervised and semi-supervised settings, showing that simple DNN models and pre-trained models achieve competitive performance and push results above the state-of-the-art.
Drug prescriptions are essential information that must be encoded in electronic medical records. However, much of this information is hidden within free-text reports. This is why the medication extraction task has emerged. To date, most of the research effort has focused on small amount of data and has only recently considered deep learning methods. In this paper, we present an independent and comprehensive evaluation of state-of-the-art neural architectures on the I2B2 medical prescription extraction task both in the supervised and semi-supervised settings. The study shows the very competitive performance of simple DNN models on the task as well as the high interest of pre-trained models. Adapting the latter models on the I2B2 dataset enables to push medication extraction performances above the state-of-the-art. Finally, the study also confirms that semi-supervised techniques are promising to leverage large amounts of unlabeled data in particular in low resource setting when labeled data is too costly to acquire.