Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review.

Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.

Hospital Readmission Outcomes by Frailty Risk in Adults in Behavioral Health Acute Care.

The purpose of the current retrospective study was to determine whether frailty is predictive of 30-day readmission in adults aged ≥50 years who were admitted with a psychiatric diagnosis to a behavioral health hospital from 2013 to 2017. A total of 1,063 patients were included. A 26-item frailty risk score (FRS-26-ICD) was constructed from electronic health record (EHR) data. There were 114 readmissions. Cox regression modeling for demographic characteristics, emergent admission, comorbidity, and FRS-26-ICD determined prediction of time to readmission was modest (incremental area under the receiver operating characteristic curve = 0.671). The FRS-26-ICD was a significant predictor of readmission alone and in models with demographics and emergent admission; however, only the Elixhauser Comorbidity Index was significantly related to hazard of readmission adjusting for other factors (adjusted hazard ratio = 1.26, 95% confidence interval [1.17, 1.37]; p < 0.001), whereas FRS-26-ICD became non-significant. Frailty is a relevant syndrome in behavioral health that should be further studied in risk prediction and incorporated into care planning to prevent hospital readmissions. [Journal of Psychosocial Nursing and Mental Health Services, 59(10), 27-39.].

Association Between Dysphagia and Inpatient Outcomes Across Frailty Level Among Patients ≥ 50 Years of Age.

Frail patients may have heightened risk of dysphagia, a potentially modifiable health factor. Our aim is to examine whether the relationship between dysphagia and adverse health outcomes differs by frailty conditions among inpatients ≥ 50 years of age. Medical or surgical hospitalizations among patients ≥ 50 years of age in the Healthcare Cost and Utilization Project's National Inpatient Sample from 2014 through the first three quarters of 2015 were included. Adverse outcomes included length of stay (LOS), hospital costs, in-hospital mortality, discharge status, and medical complications. Dysphagia was determined by ICD-9-CM codes. Frailty was defined as (a) ≥ 1 condition in the10-item Johns Hopkins Adjusted Clinical Groups (ACG) frailty measure and a frailty index for the (b) ACG and (c) a 19-item Frailty Risk Score (FRS) categorized as non-frail, pre-frail, and frail. Weighted generalized linear models for complex survey designs using generalized estimating equations were performed. Of 6,230,114 unweighted hospitalizations, 4.0% had a dysphagia diagnosis. Dysphagia presented in 3.1% and 11.0% of non-frail and frail hospitalizations using the binary ACG (p < 0.001) and in 2.9%, 7.9%, and 16.0% of non-frail, pre-frail, and frail hospitalizations using the indexed FRS (p < 0.001). Dysphagia was associated with greater LOS, higher total costs, increased non-routine discharges, and more medical complications among both frail and non-frail patients using the three frailty definitions. Dysphagia was associated with adverse outcomes in both frail and non-frail medical or surgical hospitalizations. Dysphagia management is an important consideration for providers seeking to reduce risk in vulnerable populations.

Frailty risk in hospitalised older adults with and without diabetes mellitus.

BACKGROUND: Research indicates that diabetes mellitus (DM) may be a risk factor for frailty and individuals with DM are more likely to be frail than individuals without DM; however, there is limited research in hospitalised older adults. OBJECTIVES: To determine the extent of frailty in hospitalised older adults with and without DM using a 16-item Frailty Risk Score (FRS) and assess the role of frailty in predicting 30-day rehospitalisation, discharge to an institution and in-hospital mortality. METHODS: The study was a retrospective, cohort, correlational design and secondary analysis of a data set consisting of electronic health record data. The sample was older adults hospitalised on medicine units. Logistic regression was performed for 30-day rehospitalisation and discharge location. Cox proportional hazards regression was used to analyse time to in-hospital death and weighted using propensity scores. RESULTS: Of 278 hospitalised older adults, 49% had DM, and the mean FRS was not significantly different by DM status (9.6 vs. 9.1, p = 0.07). For 30-day rehospitalisation, increased FRS was associated with significantly increased odds of rehospitalisation (AOR = 1.24, 95% CI [1.01, 1.51], p = 0.04). Although 81% were admitted from home, 57% were discharged home and 43% to an institution. An increased FRS was associated with increased odds of discharge to an institution (AOR = 1.48, 95% CI [1.26, 1.74], p < 0.001). The FRS was not significantly associated with increased risk of in-hospital death (p = 0.17), but DM was associated with a 484% increase in the instantaneous risk of death (AHR = 5.84, 95% CI [1.71, 19.9], p = 0.005). CONCLUSION: Diabetes mellitus and frailty were highly prevalent; the mean FRS was not significantly different by DM status. Although increased frailty was significantly associated with rehospitalisation and discharge to an institution, only DM was significantly associated with in-hospital mortality. RELEVANCE TO CLINICAL PRACTICE: Frailty assessment may augment clinical assessment and facilitate tailoring care and determining optimal outcomes in patients with and without DM.

Perspectives of Frailty Among African American Men and Women.

Frailty is a syndrome of impaired homeostasis and poor response to stressors leading to adverse health outcomes. The aim of the current study was to explore lay perspectives about frailty among African American adults. Thirteen men and women participated in two focus groups. Content analysis yielded six themes: (a) Physical Impairment With Loss of Independence; (b) Can Happen to Anyone, At Any Age, At Any Time; (c) Mind-Body Connection; (d) Affects All Aspects of Life; (e) Positive Attitude and Prayer Guard Against Frailty; and (f) Be In Tune and Stay Connected. Findings suggest psychological and social factors, including a positive attitude and spirituality, are linked to physical function and well-being in aging and are influential in frailty. Culturally tailored interventions that focus not only on promoting physical function but also address psychological, social, and spiritual domains may foster the resilience needed to prevent or alleviate frailty in African American individuals. [Journal of Psychosocial Nursing and Mental Health Services, 56(7), 20-29.].

Resilience in Baccalaureate Nursing Students: An Exploration.

The purpose of the current study was to explore resilience in senior-level baccalaureate nursing students. Twenty-seven participants completed an online questionnaire assessing three stressors that pertained to marriage or divorce, death or loss of family members or close friends, and extreme financial hardship in the past 1 year. Resilience was measured using the 25-item Connor-Davidson Resilience Scale (CD-RISC-25) and one open-ended question about the experience of resilience. Mean CD-RISC-25 score was 73.26 (SD = 10.7; range = 45 to 96); only 33.3% of the sample was considered resilient (score >80). Qualitative data described academic stressors and support resources for resilience. Study findings underscore the relevance of resilience in nursing students. Nurse educators must help nursing students develop resilience to better prepare them for academic success and ensure a smooth transition into their professional nursing role. [Journal of Psychosocial Nursing and Mental Health Services, 56(7), 46-55.].

Using EHR Data to Identify Patient Frailty and Risk for ICU Transfer.

The predictive properties of four definitions of a frailty risk score (FRS) constructed using combinations of nursing flowsheet data, laboratory tests, and ICD-10 codes were examined for time to first intensive care unit (ICU) transfer in medical-surgical inpatients ≥50 years of age. Cox regression modeled time to first ICU transfer and Schemper-Henderson explained variance summarized predictive accuracy of FRS combinations. Modeling by age group and controlling for sex, all FRS measures significantly predicted time to first ICU transfer. Further multivariable modeling controlling for clinical characteristics substantially improved predictive accuracy. The effect of frailty on time to first ICU transfer depended on age, with highest risk in 50 to <60 years and ≥80 years age groups. Frailty prevalence ranged from 25.1% to 56.4%. Findings indicate that FRS-based frailty is a risk factor for time to first ICU transfer and should be considered in assessment and care-planning to address frailty in high-risk patients.Frailty prevalence was highest med-surg pts 60 to <70 years (56%); highest risk for time to first ICU transfer was in younger (50 to <60 years) and older (≥80 years) groups.

Using the ModSPICES Geriatric Assessment Tool in Undergraduate Nursing Education.

BACKGROUND: Trends in aging demographics for a growing older adult population highlights the need for Gerontologic nursing competencies to prepare future nurses to provide safe and effective person-centered care. METHOD: A geriatric assessment learning module incorporated the ModSPICES assessment tool based on geriatric syndromes in a didactic and clinical course in a prelicensure baccalaureate nursing program to facilitate nursing students' critical thinking and clinical judgment in the care of hospitalized older adults. RESULTS: The ModSPICES tool fostered nursing students' critical thinking for data collection with attention to geriatric syndromes, which are highly prevalent and associated with numerous adverse outcomes but are also preventable and treatable. The tool helped to aggregate diverse clinical information and establish priorities in care. CONCLUSION: The learning module strengthened the linkage between the classroom and clinical setting, enhanced the student's capacity and confidence in the promotion of function-focused care, and facilitated refinement of their evolving assessment skills. [J Nurs Educ. 2022;61(6):338-344.].

Frailty and In-Hospital Mortality Risk Using EHR Nursing Data.

PurposeThe purpose of this study was to evaluate four definitions of a Frailty Risk Score (FRS) derived from EHR data that includes combinations of biopsychosocial risk factors using nursing flowsheet data or International Classification of Disease, 10th revision (ICD-10) codes and blood biomarkers and its predictive properties for in-hospital mortality in adults ≥50 years admitted to medical-surgical units. Methods In this retrospective observational study and secondary analysis of an EHR dataset, survival analysis and Cox regression models were performed with sociodemographic and clinical covariates. Integrated area under the ROC curve (iAUC) across follow-up time based on Cox modeling was estimated. Results The 46,645 patients averaged 1.5 hospitalizations (SD = 1.1) over the study period and 63.3% were emergent admissions. The average age was 70.4 years (SD = 11.4), 55.3% were female, 73.0% were non-Hispanic White (73.0%), mean comorbidity score was 3.9 (SD = 2.9), 80.5% were taking 1.5 high risk medications, and 42% recorded polypharmacy. The best performing FRS-NF-26-LABS included nursing flowsheet data and blood biomarkers (Adj. HR = 1.30, 95% CI [1.28, 1.33]), with good accuracy (iAUC = .794); the reduced model with age, sex, and FRS only demonstrated similar accuracy. The poorest performance was the ICD-10 code-based FRS. Conclusion The FRS captures information about the patient that increases risk for in-hospital mortality not accounted for by other factors. Identification of frailty enables providers to enhance various aspects of care, including increased monitoring, applying more intensive, individualized resources, and initiating more informed discussions about treatments and discharge planning.

Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare.

Healthcare costs due to unplanned readmissions are high and negatively affect health and wellness of patients. Hospital readmission is an undesirable outcome for elderly patients. Here, we present readmission risk prediction using five machine learning approaches for predicting 30-day unplanned readmission for elderly patients (age ≥ 50 years). We use a comprehensive and curated set of variables that include frailty, comorbidities, high-risk medications, demographics, hospital, and insurance utilization to build these models. We conduct a large-scale study with electronic health record (her) data with over 145,000 observations from 76,000 patients. Findings indicate that the category boost (CatBoost) model outperforms other models with a mean area under the curve (AUC) of 0.79. We find that prior readmissions, discharge to a rehabilitation facility, length of stay, comorbidities, and frailty indicators were all strong predictors of 30-day readmission. We present in-depth insights using Shapley additive explanations (SHAP), the state of the art in machine learning explainability.

Advancing Nurse Scope of Practice in the Republic of Moldova Using Simulation.

BACKGROUND: Nurse identity in the Republic of Moldova is undergoing change to achieve recognition as a profession. This article describes a faculty development program designed to help articulate the professional nurse role and scope of practice through enhanced teaching pedagogies used in basic nursing education. METHOD: Experiential learning strategies such as high-fidelity simulation, unfolding geriatric case study, role-play, task trainers, moulage, and teach-back were used to demonstrate the nursing process and scope of practice. RESULTS: Fifteen faculty from five technical colleges of nursing participated in the Geriatric Nursing Institute (GNI). Debriefings yielded positive responses on using experiential learning strategies to augment didactic methods to facilitate student competencies, nurse identity, and scope of practice. CONCLUSION: The GNI contributed to the professional development of faculty with potential impact on nursing students to achieve enhanced preparedness in global nurse competencies. Although the pedagogical innovations were welcomed, future initiatives building on the GNI are needed. [J Nurs Educ. 2021;60(7):377-385.].

Definitions of Frailty in Qualitative Research: A Qualitative Systematic Review.

The purpose of this qualitative systematic review was to examine how frailty was conceptually and operationally defined for participant inclusion in qualitative research focused on the lived experience of frailty in community-living frail older adults. Search of six electronic databases, 1994-2019, yielded 25 studies. Data collection involved extracting the definition of frailty from the study aim, background, literature review, methods, and sampling strategy in each research study. Quality appraisal indicated that 13 studies (52%) demonstrated potential researcher bias based on insufficient information about participant recruitment, sampling, and relationship between the researcher and participant. Content analysis and concept mapping were applied for data synthesis. Although frailty was generally defined as a multidimensional, biopsychosocial construct with loss of resilience and vulnerability to adverse outcomes, most studies defined the study population based on older age and physical impairments derived from subjective assessment by the researcher, a healthcare professional, or a family member. However, 13 studies (52%) used objective or performance-based quantitative measures to classify participant frailty. There was no consistency across studies in standardized measures or objective assessment of frailty. Synthesis of the findings yielded four themes: Time, Vulnerability, Loss, and Relationships. The predominance of older age and physical limitations as defining characteristics of frailty raises questions about whether participants were frail, since many older adults at advanced age and with physical limitations are not frail. Lack of clear criteria to classify frailty and reliance on subjective assessment introduces the risk for bias, threatens the validity and interpretation of findings, and hinders transferability of findings to other contexts. Clear frailty inclusion and exclusion criteria and a standardized approach in the reporting of how frailty is conceptually and operationally defined in study abstracts and the methodology used is necessary to facilitate dissemination and development of metasynthesis studies that aggregate qualitative research findings that can be used to inform future research and applications in clinical practice to improve healthcare.

Comparison of a Frailty Risk Score and Comorbidity Indices for Hospital Readmission Using Electronic Health Record Data.

The purpose of the current study was to investigate the predictive properties of five definitions of a frailty risk score (FRS) and three comorbidity indices using data from electronic health records (EHRs) of hospitalized adults aged ≥50 years for 3-day, 7-day, and 30-day readmission, and to identify an optimal model for a FRS and comorbidity combination. Retrospective analysis of the EHR dataset was performed, and multivariable logistic regression and area under the curve (AUC) were used to examine readmission for frailty and comorbidity. The sample (N = 55,778) was mostly female (53%), non-Hispanic White (73%), married (53%), and on Medicare (55%). Mean FRSs ranged from 1.3 (SD = 1.5) to 4.3 (SD = 2.1). FRS and comorbidity were independently associated with readmission. Predictive accuracy for FRS and comorbidity combinations ranged from AUC of 0.75 to 0.77 (30-day readmission) to 0.84 to 0.85 (3-day readmission). FRS and comorbidity combinations performed similarly well, whereas comorbidity was always independently associated with readmission. FRS measures were more associated with 30-day readmission than 7-day and 3-day readmission. [Research in Gerontological Nursing, 14(2), 91-103.].

Delegation in Long-term Care: Scope of practice or job description?

This study is a qualitative, descriptive study of how registered nurses (RNs) (N=33) in leadership roles in institutionalized long-term care settings delegate care, including their strategies and processes for delegating care, and their perceptions of barriers to effective delegation and potential benefits of delegation. Findings indicate two key approaches to delegation, including the "follow the job description" approach, emphasizing adherence to facility-level roles and job descriptions, and the "consider the scope of practice" approach, emphasizing consideration of multiple aspects of scope of practice and licensure, and the context of care. While the former resulted in more clarity and certainty for the RN, the latter facilitated a focus on quality of resident care outcomes as linked to the delegation process. Barriers to effective delegation were comparable among RNs using either approach to delegation, and almost all RNs could describe benefits of delegation for long-term care.

Teaching evidence-based nursing practice in geriatric care settings: the geriatric nursing innovations through education institute.

Evidence-based practice holds tremendous potential to optimize care outcomes for older adults, yet many nurses are ill prepared to identify, interpret, and apply the best evidence to their practice. The Geriatric Nursing Innovations through Education (GNIE) Institute is a 39-contact-hour, hybrid distance learning continuing education model designed to strengthen RNs'clinical knowledge, leadership skills, and capacity for implementing evidence-based geriatric care. The GNIE Institute combines reflective, learner-centered instructional approaches with a practicum during which evidence-based guidelines are implemented.The experiences of 128 RNs suggest that the GNIE Institute supports the implementation of a variety of best practices, including management of acute pain, dehydration, delirium, oral hygiene, urinary incontinence, and falls prevention. Participant feedback has shown low initial awareness of practice guidelines but high satisfaction with their use. The GNIE Institute thus represents a viable model for building the capacity of practicing RNs to implement evidence-based approaches to the care of geriatric syndromes across the care continuum.

Creating a Gerontological Nursing Digital Repository Within a Learning Management System.

BACKGROUND: Faculty who teach gerontological nursing are challenged to deliver competency-based baccalaureate nursing education. Because our courses are divided into multiple sections and taught by a variety of faculty, the need for a peer-reviewed, curated repository of gerontological learning materials was conceived. METHOD: Syllabi for prelicensure and RN-to-baccalaureate nursing (BSN) degree gerontological courses were reviewed. Stufflebeam's Content, Input, Process and Product (CIPP) model of program evaluation provided a framework to guide the process of identifying existing resources and gaps in eLearning materials. Using the Learning Object Review Instrument, faculty determined the relevance and applicability of eLearning materials. RESULTS: A crosswalk between the syllabi and the American Association of Colleges of Nursing-recommended geriatric nursing competencies was completed to evaluate eLearning materials identified as valuable. Consensus was reached, and content was placed in the learning management system. CONCLUSION: This project can serve as a model for other course faculty and faculty in other specialty areas to enhance the curriculum by providing readily available, multifaceted instructional resources. [J Nurs Educ. 2019;58(10):607-610.].

Risk prediction and segmentation models used in the United States for assessing risk in whole populations: a critical literature review with implications for nurses' role in population health management.

OBJECTIVE: We sought to assess the current state of risk prediction and segmentation models (RPSM) that focus on whole populations. MATERIALS: Academic literature databases (ie MEDLINE, Embase, Cochrane Library, PROSPERO, and CINAHL), environmental scan, and Google search engine. METHODS: We conducted a critical review of the literature focused on RPSMs predicting hospitalizations, emergency department visits, or health care costs. RESULTS: We identified 35 distinct RPSMs among 37 different journal articles (n = 31), websites (n = 4), and abstracts (n = 2). Most RPSMs (57%) defined their population as health plan enrollees while fewer RPSMs (26%) included an age-defined population (26%) and/or geographic boundary (26%). Most RPSMs (51%) focused on predicting hospital admissions, followed by costs (43%) and emergency department visits (31%), with some models predicting more than one outcome. The most common predictors were age, gender, and diagnostic codes included in 82%, 77%, and 69% of models, respectively. DISCUSSION: Our critical review of existing RPSMs has identified a lack of comprehensive models that integrate data from multiple sources for application to whole populations. Highly depending on diagnostic codes to define high-risk populations overlooks the functional, social, and behavioral factors that are of great significance to health. CONCLUSION: More emphasis on including nonbilling data and providing holistic perspectives of individuals is needed in RPSMs. Nursing-generated data could be beneficial in addressing this gap, as they are structured, frequently generated, and tend to focus on key health status elements like functional status and social/behavioral determinants of health.

Barriers to and facilitators of clinical practice guideline use in nursing homes.

OBJECTIVES: To identify barriers to and facilitators of the diffusion of clinical practice guidelines (CPGs) and clinical protocols in nursing homes (NHs). DESIGN: Qualitative analysis. SETTING: Four randomly selected community nursing homes. PARTICIPANTS: NH staff, including physicians, nurse practitioners, administrative staff, nurses, and certified nursing assistants (CNAs). MEASUREMENTS: Interviews (n=35) probed the use of CPGs and clinical protocols. Qualitative analysis using Rogers' Diffusion of Innovation stages-of-change model was conducted to produce a conceptual and thematic description. RESULTS: None of the NHs systematically adopted CPGs, and only three of 35 providers were familiar with CPGs. Confusion with other documents and regulations was common. The most frequently cited barriers were provider concerns that CPGs were "checklists" to replace clinical judgment, perceived conflict with resident and family goals, limited facility resources, lack of communication between providers and across shifts, facility policies that overwhelm or conflict with CPGs, and Health Insurance Portability and Accountability Act regulations interpreted to limit CNA access to clinical information. Facilitators included incorporating CPG recommendations into training materials, standing orders, customizable data collection forms, and regulatory reporting activities. CONCLUSION: Clinicians and researchers wishing to increase CPG use in NHs should consider these barriers and facilitators in their quality improvement and intervention development processes.