Ida Androwich

Data mining in healthcare information systems: case study of a veterans' administration spinal cord injury population

In the following paper the process of knowledge generation from the Veterans Administration healthcare information system is explored. This inquiry is concerned with predicting length of stay of a subset of the total patient population, specifically those with spinal cord injuries (SCI). Although SCI patients do not present large numbers, they are outliers in the healthcare system due to extended hospital stays and high costs for treatment. Predicting length of stay can increase efficiencies and effectiveness in resource allocation thus lowering cost. The following research is the first of its kind to use nursing diagnosis and neural networks to predict length of stay. Background material on SCI and the knowledge discovery process is introduced. The entire data mining process is described beginning with data gathering followed by cleaning, aggregation, and integration. Issues faced while conducting the research are discussed. Results of artificial neural networks used to predict length of stay are presented.

Health-Related Quality of Life of Patients Following Selected Types of Lumbar Spinal Surgery: A Pilot Study

BackgroundOver 500,000 spinal surgeries are performed annually in the United States. Although pain relief and improved health-related quality of life (HRQOL) are expectations following lumbar spinal surgery, there is limited research regarding this experience from the individuals perspective. In addition, no studies have examined the HRQOL of persons who have had this surgery using a comprehensive approach. The intent of this study was to address this deficiency by an assessment of both the individual and environmental factors that impact perceived HRQOL using the Wilson and Cleary Model for Health-Related Quality of Life in persons who have undergone lumbar spinal surgery.MethodsThis was a pilot study of 57 adult patients undergoing elective lumbar spinal surgery for either herniated disk and/or degenerative changes. Individuals completed questionnaires measuring perceived pain, mood, functional status, general health perceptions, social support and HRQOL preoperatively and three months following surgery. Descriptive statistics, dependent t-tests, and MANOVAs were used to describe and compare the differences of the study variables over time.ResultsPreliminary results indicate overall perceived physical HRQOL was significantly improved postoperatively (t [56] = 6.45, p < .01), however, it was lower than the published norms for patients with low back pain. Both functional disability (t [56] = 10.47, p < .001) and pain (t [56] = 10.99, p < .001) were significantly improved after surgery. Although levels of fatigue and vigor were also significantly improved after surgery, both were less than the published norms. There was no change in the level of social support over time; however, level of support was consistent with that reported by patients with chronic illness.ConclusionAlthough perceived physical HRQOL was significantly improved three months postoperatively, fatigue and lack of vigor were issues for subjects postoperatively. Excessive fatigue and low vigor may have implications for successful rehabilitation and return to work for patients following lumbar spinal surgery. Further research is needed with a larger sample size and subgroup analyses to confirm these results.

Mapping parish nurse documentation into the nursing interventions classification: a research method

Mapping, or linking like terms that represent the same concept, is a research method increasingly used for testing the reliability and validity of standardized taxonomies. For mapping to be useful, it is critical that the procedure is reliable. One way to maximize reliability is to develop standardized mapping procedures, or rules to follow when linking the terms. This article will present a standardized mapping procedure method in a study that mapped narrative parish nurse documentation (170 health records, 1607 interactions) into the Nursing Interventions Classification (NIC), yielding an intercoder reliability kappa of 0.92. The mapping process identified conceptual issues in the NIC, which also are presented. Because the NIC is included in the Systematic Nomenclature of Medicine of Clinical Terms® (SNOMED CT®), these conceptual issues raised data aggregation issues in SNOMED CT. Those issues are also presented.

Modeling nursing interventions in the act class of HL7 RIM Version 3

The proposed Health Level 7 Reference Information Model (HL7 RIM) Version 3 is the foundation for expressing data to be communicated across health care information systems. The general objective of this analysis was to examine whether the RIM supports the expression of nursing interventions, considering both terminological and structural perspectives. The Nursing Terminology Summit Interventions Group focused on patient education about breast cancer, an intervention that differs sufficiently from other medical processes already considered by HL7 and represents issues surrounding both definition and execution of nursing process. Relevant actors, actions, and action relationships were culled from use cases and modeled into the proposed RIM structure and attributes by using modified instance diagrams. This method was effective and reproducible, and the RIM proved to be an adequate model for supporting breast cancer education. Additional interventions must be studied to fully assess the adequacy of the model to support all aspects of nursing process and terminology.

Measuring spiritual care with informatics.

Nursing is at a critical juncture in creating data repositories that support nursing research and theory development, as health systems adopt and design electronic health records. This article discusses how informatics theory can be used to guide designing nursing documentation screens and analyzing the resulting data sets, while highlighting methods to maximize reliability and validity and to address measurement issues. Examples will be applied to spiritual care, a required dimension of care. These examples present methods to capture and study “soft” areas of nursing that have not traditionally been documented or measured.

Nursing as a Learning Discipline A Call to Action

The advent of the electronic health record and numerous mobile, wireless tools with the capacity to capture, store, and transmit prodigious amounts of data, both using and creating evidence-based content and analytics for clinical decision support, requires that all care providers rethink approaches to care delivery. The nursing profession is called to acutely appreciate and support the vision of documentation systems that provide optimal decision support at the point of care, represent nursing knowledge, and are also capable of capturing care delivery outcomes that can be used to inform future care and improve the health of the public.

Surveillance as an intervention in the care of stroke patients.

Background: The term surveillance describes nurses’ cognitive work to identify and prevent patient complications. Surveillance involves frequent assessment of patients, attention to cues, and recognition of complications. Surveillance serves to prevent the phenomenon “failure to rescue,” which is defined as the inability to recognize a complication that results in the loss of a patient’s life. Previous research has focused on differences between novices and experts during simulated tasks such as developing a plan of care. More recently, attention has focused on the early recognition of patient complications. Little research has been conducted on surveillance, especially with respect to the intervention during the delivery of care. Purpose: The purpose of this study was to explore the nursing intervention of surveillance in the care of stroke patients. Methods and Design: A descriptive exploratory design using think-aloud was employed. The study focused on 10 nurses working on a medical neurology unit and their patients in a large Midwestern academic health center. While providing care to a stroke patient, the nurse was prompted to think aloud as they (1) received report, (2) performed an initial assessment of the patient, and (3) concluded the work shift. Data analysis was conducted using content analysis to define the cues and information processing strategies used by these nurses during the delivery of care to stroke patients. Findings and Conclusion: The findings suggest that nurses in this study used surveillance. Using cues from change-of-shift handoff information, a mental image of what the patient would look/be like was formed. This mental image served as a baseline for the evaluation of the patient’s current state.

Toward a Central Repository for Sharing Nursing Informatics' Best Practices.

Building on prior work done by the Transforming Nursing DocumentationWorking Group 10, in 2015, the authors volunteered to explore the feasibility of creating a central repository for best practices in nursing informatics. In this report, we share what we discovered. We started our explorations by talking to several nurse leaders known to have faced the challenges of nursing documentation in their own settings and who could offer solutions that we hoped they might share. Obviously, there is no need for a best practices repository unless there are best practices to be shared and people willing to do so. We interviewed Dr Patricia Sengstack, who is chief nursing informatics officer at the Bon Secours Health System. Dr Sengstack had led an evaluation of the patient admission assessment nursing documentation in her health system, during which she found that completing every field in the electronic nursing admission assessment alone required 532 key clicks, including 14 different screening assessments. Overall, the admission assessment had been configured so that there were 153 “required fields” that must be completed. Further study led Sengstack to estimate that only 25% of the nursing data in the electronic health record (EHR) were actually useful to nurses. Bon Secours is now engaged in a streamlining process, identifying what is of little or no use—or simply a historical relic. She is also working with Bon Secours quality experts to assist in identifying if items in the assessment are truly required by Centers for Medicare &Medicaid Services or the Joint Commission or if the organization’s interpretation mandates the documentation. Sengstack was willing to share the streamlining process that Bon Secours used with other organizations via a central repository.