Search AMIA.org

Holistic, ubiquitous support of patient-centered health care (eHealth) at all health care institutions and in patients' homes through information processing is increasingly supplementing institution-centered care. While eHealth indicators may measure the transition from institution-centered (e.g., hospital-centered) information processing to patient-centered information processing, collecting relevant and timely data for such indicators has been difficult.

Succinct and timely discharge summaries (DSs) facilitate ongoing care for patients discharged from acute care settings. Many institutions have introduced electronic DS (eDS) templates to improve quality and timeliness of clinical correspondence. However, significant intrahospital and intraunit variability and application exists. A review of the literature and guidelines revealed 13 key elements that should be included in a best practice DS. This was compared against our pediatric institution's eDS template-housed [...]

The overuse of cranial computed tomography (CT) to diagnose potential traumatic brain injuries (TBIs) exposes children with minor blunt head trauma to unnecessary ionizing radiation. The Pediatric Emergency Care Applied Research Network and the Clinical Research on Emergency Services and Treatments Network implemented TBI prediction rules via electronic health record (EHR) clinical decision support (CDS) to decrease use of CTs in children with minor blunt head trauma.

The assessment of user preferences for performance characteristics of patient-oriented clinical prediction models is lacking. It is unknown if complex statistical aspects of prediction models are readily understandable by a general audience.

Malfunctions in Clinical Decision Support (CDS) systems occur due to a multitude of reasons, and often go unnoticed, leading to potentially poor outcomes. Our goal was to identify malfunctions within CDS systems.

Computing patients' similarity is of great interest in precision oncology since it supports clustering and subgroup identification, eventually leading to tailored therapies. The availability of large amounts of biomedical data, characterized by large feature sets and sparse content, motivates the development of new methods to compute patient similarities able to fuse heterogeneous data sources with the available knowledge.

To automatically recognize self-acknowledged limitations in clinical research publications to support efforts in improving research transparency.

A key challenge in clinical data mining is that most clinical datasets contain missing data. Since many commonly used machine learning algorithms require complete datasets (no missing data), clinical analytic approaches often entail an imputation procedure to "fill in" missing data. However, although most clinical datasets contain a temporal component, most commonly used imputation methods do not adequately accommodate longitudinal time-based data. We sought to develop a new imputation algorithm [...]

The federal electronic health record (EHR) certification process was intended to ensure a baseline level of system quality and the ability to support meaningful use criteria. We sought to assess whether there was variation across EHR vendors in the degree to which hospitals using products from those vendors were able to achieve high levels of performance on meaningful use criteria.