Journal of biomedical informatics
-
A recent article in this journal proposed a naturalistic approach to decision making that overcomes problems intrinsic to classical decision theory. The approach emphasizes cognitive and multi-level processes, the development of expert reasoning, and the role of decision support in individual and organizational decision making. ⋯ It is suggested that its rich, empirically tested, distinctions among kinds of cognitive and organizational processes and types of decisions and tasks make Image Theory especially valuable in describing impediments to implementing EBPs. The paper discusses how naturalistic theory can assist clinicians, administrators, researchers, and policy makers in achieving a balance between evidence-based medicine and patient-centered practice.
-
Conventional model-based or statistical analysis methods for functional MRI (fMRI) are easy to implement, and are effective in analyzing data with simple paradigms. However, they are not applicable in situations in which patterns of neural response are complicated and when fMRI response is unknown. In this paper the "neural gas" network is adapted and rigourosly studied for analyzing fMRI data. ⋯ A comparison of this new method with Kohonen's self-organizing map and with a fuzzy clustering scheme based on deterministic annealing is done in a systematic fMRI study showing comparative quantitative evaluations. The most important findings in this paper are: (1) both "neural gas" and the fuzzy clustering technique outperform Kohonen's map in terms of identifying signal components with high correlation to the fMRI stimulus, (2) the "neural gas" outperforms the two other methods with respect to the quantization error, and (3) Kohonen's map outperforms the two other methods in terms of computational expense. The applicability of the new algorithm is demonstrated on experimental data.
-
Information about the chief complaint (CC), also known as the patient's reason for seeking emergency care, is critical for patient prioritization for treatment and determination of patient flow through the emergency department (ED). Triage nurses document the CC at the start of the ED visit, and the data are increasingly available in electronic form. ⋯ We use text analysis to extract CC concepts from triage nurses' natural language entries. Our methodology for building the nursing terminology utilizes natural language processing techniques and the Unified Medical Language System.
-
The purpose of this analysis was to determine the adequacy of evolving national standardized terminologies with regard to coded data elements (concepts) in an automated clinical pathway designed to drive adherence with the American College of Cardiology (ACC)/American Heart Association (AHA) Guidelines for Evaluation and Management of Chronic Heart Failure. ⋯ Evolving national standardized terminologies provided matching terms for the majority of the data elements in the automated clinical pathway. Standard clinical terminologies with granular terms such as LOINC and SNOMED CT are required to represent the depth and detail of certain procedures and guideline-based care. Gaps exist in Health Insurance Portability and Accountability Act (HIPAA) mandated terminologies for representing interdisciplinary concepts in national adherence measures.
-
Comparative Study
Retrospective data collection and analytical techniques for patient safety studies.
To enhance patient safety, data about actual clinical events must be collected and scrutinized. This paper has two purposes. First, it provides an overview of some of the methods available to collect and analyze retrospective data about medical errors, near misses, and other relevant patient safety events. ⋯ In contrast, in the same hospitals over a two-year period, we collected event data on 135 cases identified with traditional quality improvement processes (event incidence of 0.7-2.7%). In these quality improvement cases, 120 (89%) had patient impact and 74 (55%) led to patient injury. Preliminary analyses not only illustrate some of the analytical methods applicable to safety data but also provide insight into the potential value of the non-routine event approach for the early detection of risks to patient safety before serious patient harm occurs.