Toward Understanding Clinical Context of Medication Change Events in Clinical Narratives
This work is significant for clinical researchers and healthcare providers, as it provides a dataset and framework to better understand medication changes from clinical notes, which is an incremental step towards improving medication management.
This paper addresses the need for clinical context in understanding medication change events from clinical narratives, which is crucial for applications like medication timeline generation. The authors developed the Contextualized Medication Event Dataset (CMED), comprising 9,013 medication mentions across 500 clinical notes, using a novel conceptual framework for organizing clinical event context.
Understanding medication events in clinical narratives is essential to achieving a complete picture of a patient's medication history. While prior research has explored classification of medication changes from clinical notes, studies to date have not considered the necessary clinical context needed for their use in real-world applications, such as medication timeline generation and medication reconciliation. In this paper, we present the Contextualized Medication Event Dataset (CMED), a dataset for capturing relevant context of medication changes documented in clinical notes, which was developed using a novel conceptual framework that organizes context for clinical events into various orthogonal dimensions. In this process, we define specific contextual aspects pertinent to medication change events, characterize the dataset, and report the results of preliminary experiments. CMED consists of 9,013 medication mentions annotated over 500 clinical notes, and will be released to the community as a shared task in 2021.