Journal of the American Medical Informatics Association : JAMIA
-
J Am Med Inform Assoc · Nov 2017
What's buzzing on your feed? Health authorities' use of Facebook to combat Zika in Singapore.
In 2016, Singapore grappled with one of the largest Zika outbreaks in Southeast Asia. This study examines the use of Facebook for Zika-related outreach by the Ministry of Health (MOH) and the National Environmental Agency (NEA) from March 1, 2015, to September 1, 2016, and public response to this effort. Despite nearly equivalent outreach, MOH's Facebook posts received more likes (µ = 3.49) and shares (µ = 30.11), whereas NEA's posts received more comments (µ = 4.55), with NEA posting mostly on prevention (N = 30) and MOH on situational updates (N = 24). ⋯ Public engagement was significantly higher during Zika compared with prior haze and dengue outbreaks. The results indicate the value of Facebook as a tool for rapid outreach during infectious disease outbreaks, and as a "listening" platform for those managing the situation. We discuss implications for public health communication research and policy.
-
J Am Med Inform Assoc · Nov 2017
Identifying reports of randomized controlled trials (RCTs) via a hybrid machine learning and crowdsourcing approach.
Identifying all published reports of randomized controlled trials (RCTs) is an important aim, but it requires extensive manual effort to separate RCTs from non-RCTs, even using current machine learning (ML) approaches. We aimed to make this process more efficient via a hybrid approach using both crowdsourcing and ML. ⋯ Hybrid crowd-ML strategies warrant further exploration for biomedical curation/annotation tasks.
-
J Am Med Inform Assoc · Sep 2017
Pragmatic (trial) informatics: a perspective from the NIH Health Care Systems Research Collaboratory.
Pragmatic clinical trials (PCTs) are research investigations embedded in health care settings designed to increase the efficiency of research and its relevance to clinical practice. The Health Care Systems Research Collaboratory, initiated by the National Institutes of Health Common Fund in 2010, is a pioneering cooperative aimed at identifying and overcoming operational challenges to pragmatic research. ⋯ These challenges impact the validity, reliability, and integrity of PCTs. Achieving the full potential of PCTs and a learning health system will require meaningful partnerships between health system leadership and operations, and federally driven standards and policies to ensure that future electronic health record systems have the flexibility to support research.
-
J Am Med Inform Assoc · Jul 2017
Comparative StudyAre informed policies in place to promote safe and usable EHRs? A cross-industry comparison.
Despite federal policies put in place by the Office of the National Coordinator (ONC) to promote safe and usable electronic health record (EHR) products, the usability of EHRs continues to frustrate providers and have patient safety implications. This study sought to compare government policies on usability and safety, and methods of examining compliance to those policies, across 3 federal agencies: the ONC and EHRs, the Federal Aviation Administration (FAA) and avionics, and the Food and Drug Administration (FDA) and medical devices. Our goal was to identify whether differences in policies exist and, if they do exist, how policies and enforcement mechanisms from other industries might be applied to optimize EHR usability. ⋯ Our analysis highlights important areas of usability and safety policy from other industries that can better inform ONC policies on EHRs.
-
J Am Med Inform Assoc · May 2017
Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database.
The widespread adoption of electronic health records allows us to ask evidence-based questions about the need for and benefits of specific clinical interventions in critical-care settings across large populations. ⋯ Models that used SSAM features increased performance on both predictive tasks. These improvements may reflect an underlying, and ultimately predictive, latent state detectable from the physiological time series.