Search AMIA.org

Classifying whether concepts in an unstructured clinical text are negated is an important unsolved task. New domain adaptation and transfer learning methods can potentially address this issue.

The study sought to describe key features of clinical concepts and data required to implement clinical practice recommendations as clinical decision support (CDS) tools in electronic health record systems and to identify recommendation features that predict feasibility of implementation.

The study sought to determine the dependence of the Electronic Medical Records and Genomics (eMERGE) rheumatoid arthritis (RA) algorithm on both RA and electronic health record (EHR) duration.

Implementation of machine learning (ML) may be limited by patients' right to "meaningful information about the logic involved" when ML influences healthcare decisions. Given the complexity of healthcare decisions, it is likely that ML outputs will need to be understood and trusted by physicians, and then explained to patients. We therefore investigated the association between physician understanding of ML outputs, their ability to explain these to patients, and their willingness [...]

The biomedical research and healthcare delivery communities have increasingly come to focus their attention on the role of data and computation in order to improve the quality, safety, costs, and outcomes of both wellness promotion and care delivery. Depending on the scale of such efforts, and the environments in which they are situated, they are referred to variably as personalized or precision medicine, population health, clinical transformation, value-driven care, or [...]

Ensuring that federally funded health research keeps pace with the explosion of health data depends on better information technology (IT), access to high-quality electronic health data, and supportive policies. Because it prominently funds and conducts health research, the U.S. federal government needs health IT to rapidly evolve and has the ability to drive that evolution. The Office of the National Coordinator for Health Information Technology developed the National Health IT [...]

Reliable longitudinal risk prediction for hospitalized patients is needed to provide quality care. Our goal is to develop a generalizable model capable of leveraging clinical notes to predict healthcare-associated diseases 24-96 hours in advance.

Hospital engagement in electronic health information exchange (HIE) has increased over recent years. We aimed to 1) determine the change in adoption of 3 types of information exchange: secure messaging, provider portals, and use of an HIE; and 2) to assess if growth in each approach corresponded to increased ability to access and integrate patient information from outside providers.

This study introduces a temporal condition pattern mining methodology to address the sparse nature of coded condition concept utilization in electronic health record data. As a validation study, we applied this method to reveal condition patterns surrounding an initial diagnosis of pediatric asthma.

Electronic health record (EHR) log data have shown promise in measuring physician time spent on clinical activities, contributing to deeper understanding and further optimization of the clinical environment. In this article, we propose 7 core measures of EHR use that reflect multiple dimensions of practice efficiency: total EHR time, work outside of work, time on documentation, time on prescriptions, inbox time, teamwork for orders, and an aspirational measure for the [...]