Search AMIA.org

Electronic consultation (eConsult) content reflects important information about referring clinician needs across an organization, but is challenging to extract. The objective of this work was to develop machine learning models for classifying eConsult questions for question type and question content. Another objective of this work was to investigate the ability to solve this task with constrained expert time resources.

Cardiac surgery patients are at high risk for readmissions after hospital discharge- few of these readmissions are preventable by mitigating barriers underlying discharge care transitions. An in-depth evaluation of the nuances underpinning the discharge process and the use of tools to support the process, along with insights on patient and clinician experiences, can inform the design of evidence-based strategies to reduce preventable readmissions.

The Rapid Acceleration of Diagnostics-Underserved Populations (RADx-UP) program is a consortium of community-engaged research projects with the goal of increasing access to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) tests in underserved populations. To accelerate clinical research, common data elements (CDEs) were selected and refined to standardize data collection and enhance cross-consortium analysis.

This case study assesses the uptake, user characteristics, and outcomes of automated self-scheduling in a community-based physician group affiliated with an academic health system. We analyzed 1 995 909 appointments booked between January 1, 2019, and June 30, 2021 at more than 30 practice sites. Over the study period, uptake of self-scheduling increased from 4% to 15% of kept appointments. Younger, commercially insured patients were more likely to be users. Missed appointments [...]

Deep learning models for clinical event forecasting (CEF) based on a patient's medical history have improved significantly over the past decade. However, their transition into practice has been limited, particularly for diseases with very low prevalence. In this paper, we introduce CEF-CL, a novel method based on contrastive learning to forecast in the face of a limited number of positive training instances.

The HL7® fast healthcare interoperability resources (FHIR®) specification has emerged as the leading interoperability standard for the exchange of healthcare data. We conducted a scoping review to identify trends and gaps in the use of FHIR for clinical research.

The purpose of the study was to develop and validate a model to predict the risk of experiencing a fall for nursing home residents utilizing data that are electronically available at the more than 15 000 facilities in the United States.

To assess the functionality and feasibility of the GROWIN app for promoting early detection of growth disorders in childhood, supporting early interventions, and improving children's lifestyle by analyzing data collected over 3 years (2018-2020).

We investigated how the electronic health records (EHRs) strategies concerning EHR sourcing and vendor switching impact user satisfaction over time.