Using data-driven analytics and ecological systems theory to identify risk and protective factors for school absenteeism among secondary students.

Chronic absenteeism is an administrative term defining extreme failure for students to be present at school, which can have devastating long-term impacts on students. Although numerous prior studies have investigated associated variables and interventions, there are few studies that utilize both theory-driven and data-informed approaches to investigate absenteeism. The current study applied data-driven machine learning techniques, grounded in "The Kids and Teens at School" (KiTeS) theoretical framework, to student-level data (N = 121,005) to identify risk and protective variables that are highly associated with school absences. A total of 18 risk and protective variables were identified; all 18 variables were characteristics of the microsystem or mesosystem, emphasizing school absences' proximity to variables within inner ecological systems rather than the exosystem or macrosystem. Implications for future studies and health infrastructure are discussed.

Documentation of Complementary and Integrative Health Therapies in the Electronic Health Record: A Scoping Review.

Introduction: Complementary and integrative health (CIH) therapies refers to massage therapy, acupuncture, aromatherapy, and guided imagery. These therapies have gained increased attention in recent years, particularly for their potential to help manage chronic pain and other conditions. National organizations not only recommend the use of CIH therapies but also the documentation of these therapies within electronic health records (EHRs). Yet, how CIH therapies are documented in the EHR is not well understood. The purpose of this scoping review of the literature was to examine and describe research that focused on CIH therapy clinical documentation in the EHR. Methods: The authors conducted a literature search using six electronic databases: Cumulative Index to Nursing and Allied Health Literature (CINAHL), Ovid MEDLINE, Scopus, Google Scholar, Embase, and PubMed. Predefined search terms included "informatics," "documentation," "complementary and integrative health therapies," "non-pharmacological approaches," and "electronic health records" using AND/OR statements. No restrictions were placed on publication date. The inclusion criteria were as follows: (1) Original peer-reviewed full article in English, (2) focus on CIH therapies, and (3) CIH therapy documentation practice used in the research. Results: The authors identified 1684 articles, of which 33 met the criteria for a full review. A majority of the studies were conducted in the United States (20) and hospitals (19). The most common study design was retrospective (9), and 26 studies used EHR data as a data source for analysis. Documentation practices varied widely across all studies, ranging from the feasibility of documenting integrative therapies (i.e., homeopathy) to create changes in the EHR to support documentation (i.e., flowsheet). Discussion: This scoping review identified varying EHR clinical documentation trends for CIH therapies. Pain was the most frequent reason for use of CIH therapies across all included studies and a broad range of CIH therapies were used. Data standards and templates were suggested as informatics methods to support CIH documentation. A systems approach is needed to enhance and support the current technology infrastructure that will enable consistent CIH therapy documentation in EHRs.

Evaluating Systemized Nomenclature of Medicine Clinical Terms Coverage of Complementary and Integrative Health Therapy Approaches Used Within Integrative Nursing, Health, and Medicine.

The use of complementary and integrative health therapy strategies for a wide variety of health conditions is increasing and is rapidly becoming mainstream. However, little is known about how or if complementary and integrative health therapies are represented in the EHR. Standardized terminologies provide an organizing structure for health information that enable EHR representation and support shareable and comparable data; which may contribute to increased understanding of which therapies are being used for whom and for what purposes. Use of standardized terminologies is recommended for interoperable clinical data to support sharable, comparable data to enable the use of complementary and integrative health therapies and to enable research on outcomes. In this study, complementary and integrative health therapy terms were extracted from multiple sources and organized using the National Center for Complementary and Integrative Health and former National Center for Complementary and Alternative Medicine classification structures. A total of 1209 complementary and integrative health therapy terms were extracted. After removing duplicates, the final term list was generated via expert consensus. The final list included 578 terms, and these terms were mapped to Systemized Nomenclature of Medicine Clinical Terms. Of the 578, approximately half (48.1%) were found within Systemized Nomenclature of Medicine Clinical Terms. Levels of specificity of terms differed between National Center for Complementary and Integrative Health and National Center for Complementary and Alternative Medicine classification structures and Systemized Nomenclature of Medicine Clinical Terms. Future studies should focus on the terms not mapped to Systemized Nomenclature of Medicine Clinical Terms (51.9%), to formally submit terms for inclusion in Systemized Nomenclature of Medicine Clinical Terms, toward leveraging the data generated by use of these terms to determine associations among treatments and outcomes.

An Applied Healthcare Data Science Roadmap for Nursing Leaders: A Workshop Development, Conceptualization, and Application.

Nurse leaders working with large volumes of interdisciplinary healthcare data are in need of advanced guidance for conducting analytics to improve population outcomes. This article reports the development of a roadmap to help nursing leaders use data science principles and tools to inform decision-making, thus supporting research and approaches in clinical practice that improve healthcare for all. A consensus-building and iterative process was utilized based on the Cross-Industry Standard Process for Data Mining approach to big data science. Using the model, a set of components are described that combine and achieve a process for data science projects applicable to healthcare issues with the potential for improving population health outcomes. The roadmap was tested using a workshop format. The workshop was presented to two audiences: nurse leaders and informatics/healthcare leaders. Results were positive and included suggestions for how to further refine and communicate the roadmap.

Knowledge Discovery With Machine Learning for Hospital-Acquired Catheter-Associated Urinary Tract Infections.

Massive generation of health-related data has been key in enabling the big data science initiative to gain new insights in healthcare. Nursing can benefit from this era of big data science, as there is a growing need for new discoveries from large quantities of nursing data to provide evidence-based care. However, there are few nursing studies using big data analytics. The purpose of this article is to explain a knowledge discovery and data mining approach that was employed to discover knowledge about hospital-acquired catheter-associated urinary tract infections from multiple data sources, including electronic health records and nurse staffing data. Three different machine learning techniques are described: decision trees, logistic regression, and support vector machines. The decision tree model created rules to interpret relationships among associated factors of hospital-acquired catheter-associated urinary tract infections. The logistic regression model showed what factors were related to a higher risk of hospital-acquired catheter-associated urinary tract infections. The support vector machines model was included to compare performance with the other two interpretable models. This article introduces the examples of cutting-edge machine learning approaches that will advance secondary use of electronic health records and integration of multiple data sources as well as provide evidence necessary to guide nursing professionals in practice.

Factors Associated With Healthcare-Acquired Catheter-Associated Urinary Tract Infections: Analysis Using Multiple Data Sources and Data Mining Techniques.

PURPOSE: The purpose of this study was to identify factors associated with healthcare-acquired catheter-associated urinary tract infections (HA-CAUTIs) using multiple data sources and data mining techniques. SUBJECTS AND SETTING: Three data sets were integrated for analysis: electronic health record data from a university hospital in the Midwestern United States was combined with staffing and environmental data from the hospital's National Database of Nursing Quality Indicators and a list of patients with HA-CAUTIs. METHODS: Three data mining techniques were used for identification of factors associated with HA-CAUTI: decision trees, logistic regression, and support vector machines. RESULTS: Fewer total nursing hours per patient-day, lower percentage of direct care RNs with specialty nursing certification, higher percentage of direct care RNs with associate's degree in nursing, and higher percentage of direct care RNs with BSN, MSN, or doctoral degree are associated with HA-CAUTI occurrence. The results also support the association of the following factors with HA-CAUTI identified by previous studies: female gender; older age (>50 years); longer length of stay; severe underlying disease; glucose lab results (>200 mg/dL); longer use of the catheter; and RN staffing. CONCLUSIONS: Additional findings from this study demonstrated that the presence of more nurses with specialty nursing certifications can reduce HA-CAUTI occurrence. While there may be valid reasons for leaving in a urinary catheter, findings show that having a catheter in for more than 48 hours contributes to HA-CAUTI occurrence. Finally, the findings suggest that more nursing hours per patient-day are related to better patient outcomes.

Delay Within the 3-Hour Surviving Sepsis Campaign Guideline on Mortality for Patients With Severe Sepsis and Septic Shock.

OBJECTIVES: To specify when delays of specific 3-hour bundle Surviving Sepsis Campaign guideline recommendations applied to severe sepsis or septic shock become harmful and impact mortality. DESIGN: Retrospective cohort study. SETTING: One health system composed of six hospitals and 45 clinics in a Midwest state from January 01, 2011, to July 31, 2015. PATIENTS: All adult patients hospitalized with billing diagnosis of severe sepsis or septic shock. INTERVENTIONS: Four 3-hour Surviving Sepsis Campaign guideline recommendations: 1) obtain blood culture before antibiotics, 2) obtain lactate level, 3) administer broad-spectrum antibiotics, and 4) administer 30 mL/kg of crystalloid fluid for hypotension (defined as "mean arterial pressure" < 65) or lactate (> 4). MEASUREMENTS AND MAIN RESULTS: To determine the effect of t minutes of delay in carrying out each intervention, propensity score matching of "baseline" characteristics compensated for differences in health status. The average treatment effect in the treated computed as the average difference in outcomes between those treated after shorter versus longer delay. To estimate the uncertainty associated with the average treatment effect in the treated metric and to construct 95% CIs, bootstrap estimation with 1,000 replications was performed. From 5,072 patients with severe sepsis or septic shock, 1,412 (27.8%) had in-hospital mortality. The majority of patients had the four 3-hour bundle recommendations initiated within 3 hours. The statistically significant time in minutes after which a delay increased the risk of death for each recommendation was as follows: lactate, 20.0 minutes; blood culture, 50.0 minutes; crystalloids, 100.0 minutes; and antibiotic therapy, 125.0 minutes. CONCLUSIONS: The guideline recommendations showed that shorter delays indicates better outcomes. There was no evidence that 3 hours is safe; even very short delays adversely impact outcomes. Findings demonstrated a new approach to incorporate time t when analyzing the impact on outcomes and provide new evidence for clinical practice and research.

Modeling Flowsheet Data to Support Secondary Use.

The purpose of this study was to create information models from flowsheet data using a data-driven consensus-based method. Electronic health records contain a large volume of data about patient assessments and interventions captured in flowsheets that measure the same "thing," but the names of these observations often differ, according to who performs documentation or the location of the service (eg, pulse rate in an intensive care, the emergency department, or a surgical unit documented by a nurse or therapist or captured by automated monitoring). Flowsheet data are challenging for secondary use because of the existence of multiple semantically equivalent measures representing the same concepts. Ten information models were created in this study: five related to quality measures (falls, pressure ulcers, venous thromboembolism, genitourinary system including catheter-associated urinary tract infection, and pain management) and five high-volume physiological systems: cardiac, gastrointestinal, musculoskeletal, respiratory, and expanded vital signs/anthropometrics. The value of the information models is that flowsheet data can be extracted and mapped for semantically comparable flowsheet measures from a clinical data repository regardless of the time frame, discipline, or setting in which documentation occurred. The 10 information models simplify the representation of the content in flowsheet data, reducing 1552 source measures to 557 concepts. The amount of representational reduction ranges from 3% for falls to 78% for the respiratory system. The information models provide a foundation for including nursing and interprofessional assessments and interventions in common data models, to support research within and across health systems.

Big data science: A literature review of nursing research exemplars.

BACKGROUND: Big data and cutting-edge analytic methods in nursing research challenge nurse scientists to extend the data sources and analytic methods used for discovering and translating knowledge. PURPOSE: The purpose of this study was to identify, analyze, and synthesize exemplars of big data nursing research applied to practice and disseminated in key nursing informatics, general biomedical informatics, and nursing research journals. METHODS: A literature review of studies published between 2009 and 2015. There were 650 journal articles identified in 17 key nursing informatics, general biomedical informatics, and nursing research journals in the Web of Science database. After screening for inclusion and exclusion criteria, 17 studies published in 18 articles were identified as big data nursing research applied to practice. DISCUSSION: Nurses clearly are beginning to conduct big data research applied to practice. These studies represent multiple data sources and settings. Although numerous analytic methods were used, the fundamental issue remains to define the types of analyses consistent with big data analytic methods. CONCLUSION: There are needs to increase the visibility of big data and data science research conducted by nurse scientists, further examine the use of state of the science in data analytics, and continue to expand the availability and use of a variety of scientific, governmental, and industry data resources. A major implication of this literature review is whether nursing faculty and preparation of future scientists (PhD programs) are prepared for big data and data science.

A Data Mining Approach to Determine Sepsis Guideline Impact on Inpatient Mortality and Complications.

Sepsis incidents have doubled from 2000 through 2008, and hospitalizations for these diagnoses have increased by 70%. The use of the Surviving Sepsis Campaign (SSC) guidelines can lead to earlier diagnosis and treatment; however, the effectiveness of the SSC guidelines in preventing complications for this population is unclear. The overall purpose of this study was to apply SSC guideline recommendations to EHR data for patients with severe sepsis or septic shock and determine guideline compliance as well as its impact on inpatient mortality and sepsis complications. Propensity Score Matching in conjuction with Bootstrap Simulation were used to match patients with and without exposure to the SSC recommendations. Findings showed that EHR data could be used to estimate compliance with SSC recommendations as well as the effect of compliance on outcomes. Compliance with guideline recommendations ranged from 9% to 100%. For individual recommendations with sufficient data, association with outcomes varied. Checking lactate influenced four outcomes; however, two were negative and two positive. Use of a ventilator for patients with respiratory distress had a positive association with three outcomes.

Accelerating the Global Workforce Demand for Nurse Informaticians: Advanced Health Informatics Certification (AHIC).

Advances in professional recognition of nursing informatics vary by country but examples exist of training programs moving from curriculum-based education to competency based frameworks to produce highly skilled nursing informaticians. This panel will discuss a significant credentialing project in the United States that should further enhance professional recognition of highly skilled nurses matriculating from NI programs as well as nurses functioning in positions where informatics-induced transformation is occurring. The panel will discuss the professionalization of health informatics by describing core content, training requirements, education needs, and administrative framework applicable for the creation of an Advanced Health Informatics Certification (AHIC).

Urgent Call for Nursing Big Data.

The purpose of this panel is to expand internationally a National Action Plan for sharable and comparable nursing data for quality improvement and big data science. There is an urgent need to assure that nursing has sharable and comparable data for quality improvement and big data science. A national collaborative - Nursing Knowledge and Big Data Science includes multi-stakeholder groups focused on a National Action Plan toward implementing and using sharable and comparable nursing big data. Panelists will share accomplishments and future plans with an eye toward international collaboration. This presentation is suitable for any audience attending the NI2016 conference.

Nursing Management Minimum Data Set: Cost-Effective Tool To Demonstrate the Value of Nurse Staffing in the Big Data Science Era.

There is a growing body of evidence of the relationship of nurse staffing to patient, nurse, and financial outcomes. With the advent of big data science and developing big data analytics in nursing, data science with the reuse of big data is emerging as a timely and cost-effective approach to demonstrate nursing value. The Nursing Management Minimum Date Set (NMMDS) provides standard administrative data elements, definitions, and codes to measure the context where care is delivered and, consequently, the value of nursing. The integration of the NMMDS elements in the current health system provides evidence for nursing leaders to measure and manage decisions, leading to better patient, staffing, and financial outcomes. It also enables the reuse of data for clinical scholarship and research.