Search AMIA.org

We aimed to investigate to what extent clustering of related drug interaction alerts (drug-drug and drug-disease interaction alerts) would decrease the alert rate in clinical decision support systems (CDSSs).

Event notifications are real-time, electronic, automatic alerts to providers of their patients' health care encounters at other facilities. Our objective was to examine the effects of organizational capability and related social/organizational issues upon users' perceptions of the impact of event notifications on quality, efficiency, and satisfaction.

We propose a computational framework for integrating diverse patient measurements into an aggregate health score and applying it to patient stability prediction.

The Johns Hopkins Center for Population Health IT hosted a 1-day symposium sponsored by the National Library of Medicine to help develop a national research and development (R&D) agenda for the emerging field of population health informatics (PopHI).

Clinical information models are formal specifications for representing the structure and semantics of the clinical content within electronic health record systems. This research aims to define, test, and validate evaluation metrics for software tools designed to support the processes associated with the definition, management, and implementation of these models.

First, to evaluate the effect of standard vs pictograph-enhanced discharge instructions on patients' immediate and delayed recall of and satisfaction with their discharge instructions. Second, to evaluate the effect of automated pictograph enhancement on patient satisfaction with their discharge instructions.

Communication inequalities deepen health disparities even when internet access is achieved. The goal of this study is to understand how a range of barriers may inhibit individuals from low socioeconomic position (SEP) from engaging with online health information even when it is freely available.

Traditionally, patient groups with a phenotype are selected through rule-based definitions whose creation and validation are time-consuming. Machine learning approaches to electronic phenotyping are limited by the paucity of labeled training datasets. We demonstrate the feasibility of utilizing semi-automatically labeled training sets to create phenotype models via machine learning, using a comprehensive representation of the patient medical record.