Data-Centric Machine Learning in Nursing: A Concept Clarification.

The ubiquity of electronic health records and health information exchanges has generated abundant administrative and clinical healthcare data. The vastness of this rich dataset presents an opportunity for emerging technologies (eg, artificial intelligence and machine learning) to assist clinicians and healthcare administrators with decision-making, predictive analytics, and more. Multiple studies have cited various applications for artificial intelligence and machine learning in nursing. However, what is unknown in the nursing discipline is that while greater than 90% of machine-learning implementations use a model-centric strategy, a fundamental change is occurring. Because of the limitations of this approach, the industry is beginning to pivot toward data-centric artificial intelligence. Nurses should be aware of the differences, including how each approach affects their engagement in designing human-intelligent-like technologies and their data usage, especially regarding electronic health records. Using the Norris Concept Clarification method, this article elucidates the data-centric machine learning concept for nursing. This is accomplished by (1) exploring the concept's origins in the data and computer science disciplines; (2) differentiating data- versus model-centric machine learning approaches, including introducing the machine-learning operation life cycle and process; and (3) explaining the advantages of the data-centric phenomenon, especially concerning nurses' engagement in technological design and proper data usage.

Older Adults' Perception on and Use of Patient Portals: A Comparative Analysis of Two Samples.

Older adults can benefit from using patient portals. Little is known whether perception of and use of patient portals differ among older adults in diverse healthcare contexts. This study analyzed the difference in perceived usability, self-efficacy, and use of patient portals between older adults recruited from a healthcare system (n = 174) and older adults recruited from nationwide communities (n = 126). A secondary data analysis was conducted using the data sets of two independent studies. A series of linear and ordinal logistic regression analyses were performed. The healthcare system sample had more health issues, higher levels of perceived usability and self-efficacy, and frequent use of patient portals compared with the community sample. This study indicates that efforts to improve usability of patient portals and self-efficacy are essential for all older adult users. The association between perceived usability and patient portal use was stronger in the community sample than in the healthcare system sample, suggesting that approaches to support older adults' efficient use of patient portals should be tailored to their health status and care needs. Future studies may include inpatient and outpatient portals and investigate the impact on health outcomes of older adults across care settings.

Development of an academic-practice partnership model to anchor care coordination and population health.

The National Academy of Medicine's The Future of Nursing 2020-2030 recommends the expansion of the role of nurses throughout the continuum of health care in an effort to improve the health of the nation while decreasing costs. To accomplish this goal, nursing students and nurses must be well prepared to perform at their highest capacity to meet health care demands. Currently the U.S. health care delivery system is undergoing rapid changes that affect approaches to delivering care services. These changes call for education and practice reforms in nursing. This article introduces an innovative academic-practice partnership model (the University of Maryland Nursing [UMNursing] Care Coordination Implementation Collaborative), including its background, development, and blueprint for a large implementation project. The implementation model integrates nursing education and practice in areas of care co-ordination and population health, which have a significant impact on the Triple Aim of health. The project also uniquely integrates education, practice, and research, with the ultimate outcome of higher quality patient care.

Longitudinal Moderated Mediation Analysis in Parallel Process Latent Growth Curve Modeling in Intervention Studies.

BACKGROUND: Intervention studies are used widely in nursing research to explore the efficacy of intervention programs for changing targeted health outcomes. However, the analyses of such studies have focused predominantly on their main intervention effects; most studies ignore the mechanisms underlying how the intervention programs work partly because of lack of application details of the longitudinal mediation analysis techniques. OBJECTIVES: The aim of this study was to illustrate an application of parallel process latent growth curve modeling (PP-LGCM) to examine longitudinal moderated mediation effects. METHODS: Longitudinal data from an online bone health intervention study were used to demonstrate the step-by-step application of PP-LGCM with Mplus statistical software. RESULTS: With modification indices, we were able to achieve adequate model fit for PP-LGCM in our data. The mediation effects of self-efficacy on the intervention effects on exercise were nonsignificant for the entire sample. However, the conditional indirect effect showed the mediation effects were moderated by age group. DISCUSSION: PP-LGCM provides an efficient way to analyze and explain the underlying mechanisms for the intervention effects in a trial, especially when the intervention program is guided by a theory.

Testing a Model of Patient Portal Use in Adult Patients.

PURPOSE: The aim of this study was to test a modified version of the Technology Acceptance Model, which describes users' technology adoption, to examine the relations between patient portal use and potential influencing factors in adult patients who have used patient portals. The modified model posits that patient portal use can be explained by attitude and self-efficacy for using patient portals, perceived usefulness and ease of use, data privacy and security concerns, eHealth literacy, education level, and age. DESIGN: A cross-sectional anonymous online survey was conducted for adult patients who had used their patient portals in the past 12 months. METHODS: Participants were recruited from 20 settings selected in a large integrated health care system. Data from 743 patients were subject to structural equation modeling for model testing. FINDINGS: Sixty-eight percent were White and female, with a mean age of 53.1 years (SD = 15.34). Forty-seven percent used patient portals about monthly or more frequently. Scores for perceived usefulness and ease of use of patient portals were relatively high (as measured using the modified Perceived Health Web Site Usability Questionnaire; each item mean, 6.0-6.2; range, 1-7). The final model adequately fit the data (comparative fit index = .983, standardized root mean square residual = .064, root mean square error of approximation = .059). Patient portal self-efficacy and data privacy and security concerns had a direct impact on patient portal use. Perceived usefulness and ease of use, eHealth literacy, education level, and age indirectly influenced patient portal use. CONCLUSIONS: This study contributes to expanding a theoretical understanding of adult patients' patient portal use in a real health care environment. Future studies need to include more diverse populations in various settings. CLINICAL RELEVANCE: Knowledge gained from this study can be used by technology experts to make patient portals more user friendly and by administrators to implement patient portals more effectively.

Health Information Exchange: Practical Overview and Implications for Nursing Practice.

The US healthcare system is moving into a new era of value-based care, which focuses on delivering safer and higher quality care while reducing costs. Health information exchange (HIE) has been a vital component in this process; however, there has been a lack of awareness and use of HIE among nurse leaders, clinicians, and researchers. The purpose of this article is to provide nurses and administrators with a brief overview of HIE and its impact on care delivery, as well as practical applications using specific case examples.

Older adults' use of patient portals: Experiences, challenges, and suggestions shared through discussion board forums.

Patient portals (PPs) are robust health IT programs that engage and empower patients in their care. Although PPs can benefit older adults who manage chronic conditions, their use of PPs have been largely overlooked and little training has been provided to them. Previously, our research team developed an older-adult-friendly Theory-based PP eLearning Program (T-PeP) and tested its impact on older adults with chronic conditions. As part of T-PeP, participants used discussion forums. The aim of this study was to explore older adults' experiences with using PPs, perceived impact of PP on their health, and suggestions for improvement through analysis of discussion posts. A total of 205 posts were subjected to content analysis. Findings from 10 major themes explained older adults' experiences with PPs and offered suggestions for vendors and healthcare organizations. As U.S. population is aging, older adults must be considered during the development and implementation of health IT programs.

The Effects of a Theory-Based Patient Portal e-Learning Program for Older Adults with Chronic Illnesses.

Introduction: The high prevalence of chronic illnesses is a serious public health problem in the United States, and more than 70 million older adults have at least one chronic illness. Patient portals (PPs) have an excellent potential to assist older adults in managing chronic illnesses; however, older adults' PP adoption rates have been low. Lack of support for older adults using PPs remains a critical gap in most implementation processes. The main aim of this study was to assess the impact of an older adult friendly Theory-based Patient portal e-Learning Program (T-PeP) on PP knowledge, selected health outcomes (health decision-making self-efficacy [SE] and health communication), PP SE and use, and e-health literacy in older adults. Materials and Methods: A two-arm randomized controlled trial was conducted with older adults (N = 272) who had chronic conditions. Participants were recruited online, and data were collected at baseline, 3 weeks, and 4 months. The main intervention effects were tested using linear mixed models. Results: The average age of participants was 70.0 ± 8.5 years, and 78.3% (n = 213) were white. At 3 weeks, the intervention group showed significantly greater improvement than the control group in all outcomes except PP use. At 4 months, the intervention effects decreased, but PP SE remained significant (p = 0.015), and the intervention group showed higher frequency of PP use than the control group (p = 0.029). Conclusion: The study findings showed that the T-PeP was effective in improving selected health and PP usage outcomes. Further studies are needed to test the long-term effects of T-PeP using more diverse samples.

Older Adults' Experience Using Patient Portals in Communities: Challenges and Opportunities.

Patient portals can be beneficial for older adults who manage their own health. However, there is a lack of research on older adults' experience using patient portals in the community. The aim of this study was to assess older adults' perceived usability of patient portals they currently use. This was a secondary data analysis using selected baseline data from an online trial that tested the effects of a 3-week Theory-Based Patient Portal eLearning Program, and included 272 older adults recruited online. Data were analyzed using descriptive statistics and content analysis. Most participants owned patient portal accounts (n = 194 [71.3%]). Self-efficacy for using patient portals was relatively low (mean, 27.1; range, 0-40), and perceived usability of patient portals was also low (mean, 28.7; range, 6-42). The most-favored features of patient portals were review of medical information and eMessaging. The main difficulties in using patient portals were associated with login/access and specific portal functions. Managing multiple patient portals was a particular challenge for many participants. Findings from this study indicate the importance of providing proper levels of training and technical support to older adults to maximize use and improve outcomes of patient portal implementation.

The Korean eHealth Literacy Scale (K-eHEALS): Reliability and Validity Testing in Younger Adults Recruited Online.

BACKGROUND: In this digital era, eHealth literacy is an essential skill set to leverage health information available online to promote health outcomes. South Korea has an advanced health information technology infrastructure, including widespread use of the internet and mobile phones. A few studies have explored eHealth literacy in South Korea using translated versions of the eHEALS; however, they were not fully validated. A unified reliable and valid assessment tool is critical to assess and enhance the eHealth literacy level across the population. OBJECTIVE: The aim was to develop a Korean version of eHealth Literacy Scale (K-eHEALS) and evaluate its reliability and validity employing healthy young adults in Korea. METHODS: The K-eHEALS was developed based on eHEALS, a widely used tool that measures eHealth literacy, and was validated using a sample of 500 young adults recruited from a pool of a Korean internet survey panel. Content validity was assessed using the content validity index (CVI) for individual items and for scale. Construct validity was examined using exploratory factor analysis and hypothesis testing. The Cronbach alpha coefficient was used to determine the internal consistency and the Pearson correlation coefficient was used to evaluable the stability of the measure (n=55). RESULTS: Both individual and scale CVIs were acceptable (individual CVIs>0.67; scale CVI=0.83). Single factors accounting for 50.3% of the variance in the scales were extracted revealing the unidimensional latent structure of K-eHEALS. Hypothesis testing showed significant association between eHealth literacy and hours of internet use per day, supporting the construct validity. Items of the K-eHEALS were internally consistent (Cronbach alpha=.88) and stable over a 1-month period (r=.754, P<.001). CONCLUSIONS: The findings of this study suggest that K-eHEALS is a valid and reliable measure of eHealth literacy in Korean young adults. Additional studies are needed with more diverse groups of adults in Korea.

The Moderated Mediating Effect of Self-Efficacy on Exercise Among Older Adults in an Online Bone Health Intervention Study: A Parallel Process Latent Growth Curve Model.

This secondary data analyses of a longitudinal study assessed whether self-efficacy for exercise (SEE) mediated online intervention effects on exercise among older adults and whether age (50-64 vs. ≥65 years) moderated the mediation. Data were from an online bone health intervention study. Eight hundred sixty-six older adults (≥50 years) were randomized to three arms: Bone Power (n = 301), Bone Power Plus (n = 302), or Control (n = 263). Parallel process latent growth curve modeling (LGCM) was used to jointly model growths in SEE and in exercise and to assess the mediating effect of SEE on the effect of intervention on exercise. SEE was a significant mediator in 50- to 64-year-old adults (0.061, 95 BCI: 0.011, 0.163) but not in the ≥65 age group (-0.004, 95% BCI: -0.047, 0.025). Promotion of SEE is critical to improve exercise among 50- to 64-year-olds.

Patient-Centered Personal Health Record and Portal Implementation Toolkit for Ambulatory Clinics: A Feasibility Study.

Personal health records and patient portals have been shown to be effective in managing chronic illnesses. Despite recent nationwide implementation efforts, the personal health record and patient portal adoption rates among patients are low, and the lack of support for patients using the programs remains a critical gap in most implementation processes. In this study, we implemented the Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit in a large diabetes/endocrinology center and assessed its preliminary impact on personal health record and patient portal knowledge, self-efficacy, patient-provider communication, and adherence to treatment plans. Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit is composed of Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit-General, clinic-level resources for clinicians, staff, and patients, and Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit Plus, an optional 4-week online resource program for patients ("MyHealthPortal"). First, Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit-General was implemented, and all clinicians and staff were educated about the center's personal health record and patient portal. Then general patient education was initiated, while a randomized controlled trial was conducted to test the preliminary effects of "MyHealthPortal" using a small sample (n = 74) with three observations (baseline and 4 and 12 weeks). The intervention group showed significantly greater improvement than the control group in patient-provider communication at 4 weeks (t56 = 3.00, P = .004). For other variables, the intervention group tended to show greater improvement; however, the differences were not significant. In this preliminary study, Patient-Centered Personal Health Record and Patient Portal Implementation Toolkit showed potential for filling the gap in the current personal health record and patient portal implementation process. Further studies are needed using larger samples in other settings to ascertain if these results are generalizable to other populations.

Factors associated with eating performance for long-term care residents with moderate-to-severe cognitive impairment.

AIMS: The aim of this study was to examine the association of specific personal and environmental factors with eating performance among long-term care residents with moderate-to-severe cognitive impairment. BACKGROUND: Eating is the one of the most basic and easiest activities of daily living to perform. While multilevel factors can be associated with eating performance, the evidence among those with dementia was insufficient. DESIGN: A secondary analysis of baseline data collected between March and September in 2012 from 199 residents in eight long-term care facilities. METHODS: Eating performance was conceptualized using the single self-care 'feeding' item in the Barthel Index and was scored based on four levels of dependence and assistance required. Binary logistic regression was used to examine the adjusted association of specific factors with eating performance. RESULTS: Almost one-third of the residents needed help with eating. After adjusting the type of facility, number of comorbidities, chair-sitting balance, agitation and depression, compromised eating performance was associated with severe cognitive impairment and low physical capability. CONCLUSION: This study supported the association of eating performance with cognitive impairment and physical capability among long-term care residents with moderate-to-severe cognitive impairment. Targeted interventions should be implemented to reduce the impact of cognitive decline on eating performance and promote physical capability to optimize eating performance. Future work need to use validated multiple-item measures for eating performance and test the association of personal and environmental factors with eating performance among a larger heterogeneous group of long-term care residents to enhance understanding of the factors.

Testing reliability and validity of the eHealth Literacy Scale (eHEALS) for older adults recruited online.

Currently, vast amounts of health information and health management tools are available to the public online. To maximize the benefits of these e-health technologies, it is important to assess the e-health literacy of individuals. The eHealth Literacy Scale has been used widely in the past several years, but mainly in younger populations. The purpose of this study was to test the psychometric aspects of the eHealth Literacy Scale for older adults using a secondary data analysis (N=866; mean age, 62.8±8.5 years). Reliability of the eHealth Literacy Scale was examined by calculating α coefficients and conducting test-retest procedures. Its validity was assessed using exploratory factor analysis and the hypothesis testing procedure. Findings demonstrated that eHealth Literacy Scale was internally consistent (α=.94) and stable (t244=-1.48, P=.140). The exploratory factor analysis yielded a single factor structure explaining 67.3% of the variance. The hypothesis testing also supported the validity of eHealth Literacy Scale. In recent years, there have been great efforts to use e-health interventions to engage patients in healthcare and to help them manage their own health. Our study suggests that the eHealth Literacy Scale, a short screening tool for e-health literacy, can be successfully used for older adults.

Optimizing Eating Performance for Older Adults With Dementia Living in Long-term Care: A Systematic Review.

BACKGROUND: Review of research to date has been focusing on maintaining weight and nutrition with little attention on optimizing eating performance. OBJECTIVE: To evaluate the effectiveness of interventions on eating performance for older adults with dementia in long-term care (LTC). METHODS: A systematic review was performed. Five databases including Pubmed, Medline (OVID), EBM Reviews (OVID), PsychINFO (OVID), and CINAHL (EBSCOHost) were searched between January 1980 and June 2014. Keywords included dementia, Alzheimer, feed(ing), eat(ing), mealtime(s), oral intake, autonomy, and intervention. Intervention studies that optimize eating performance and evaluate change of self-feeding or eating performance among older adults (≥65 years) with dementia in LTC were eligible. Studies were screened by title and abstract, and full texts were reviewed for eligibility. Eligible studies were classified by intervention type. Study quality was accessed using the Quality Assessment Tool for Quantitative Studies, and level of evidence using the 2011 Oxford Centre for Evidence-Based Medicine (OCEBM) Levels of Evidence. RESULTS: Eleven intervention studies (five randomized controlled trials [RCTs]) were identified, and classified into four types: training program, mealtime assistance, environmental modification, and multicomponent intervention. The quality of the 11 studies was generally moderate (four studies were rated as strong, four moderate, and three weak in quality), with the main threats as weak designs, lack of blinding and control for confounders, and inadequate psychometric evidence for measures. Training programs targeting older adults (Montessori methods and spaced retrieval) demonstrated good evidence in decreasing feeding difficulty. Mealtime assistance offered by nursing staff (e.g., verbal prompts and cues, positive reinforcement, appropriate praise and encouragement) also showed effectiveness in improving eating performance. LINKING EVIDENCE TO ACTION: This review provided preliminary support for using training and mealtime assistance to optimize eating performance for older adults with dementia in LTC. Future effectiveness studies may focus on training nursing caregivers as interventionists, lengthening intervention duration, and including residents with varying levels of cognitive impairment in diverse cultures. The effectiveness of training combined with mealtime assistance may also be tested to achieve better resident outcomes in eating performance.

Implementation of a Participant-Centered Weight Management Program for Older Nurses: A Feasibility Study.

American nurses (3.06 million) are at high risk for being overweight, as the majority are post-menopausal women (93.3% female; mean age 47). Studies have indicated that more than half of all nurses are either overweight or obese. This fact is of concern because nurses often lead major health promotion efforts. The aim of this study was to examine the feasibility of a novel participant-centered weight management program (PCWM) among nurses. The participant-centered (P-C) theoretical framework used originated from the field of usability engineering (i.e., user-centered design). Study methods included a single group pre-test/post-test design (baseline, eight weeks, three months) and an intervention consisting of face-to-face education sessions, technology-augmented exercise programs, and an eHealth portal. The results demonstrated a significant decrease in body weight, increased fruit and vegetable consumption, and increased exercise at eight weeks. In our discussion of this study, we note that although the intervention effects decreased at three months, these results are promising, considering that the intervention used was not regimented and relied only on nurses' activation of their planned health behaviors. The major limitation of the study was the small sample size recruited from one large community hospital. Further research is needed to improve the sustainability of the program.

Reliability and validity of the revised Osteoporosis Knowledge Test.

BACKGROUND AND PURPOSE: The purpose of this study was to test the psychometric properties of the Osteoporosis Knowledge Test (OKT) revised to incorporate recent evidence-based recommendations for bone health. METHODS: The revised OKT was tested with 866 participants (mean age = 62.8 years +/- 8.5 years) in an online bone health study. RESULTS: Based on Rasch analysis, there was evidence of internal consistency with an item separation index of 12.68 and a reliability score of .98. The person separation index was 2.06 with a reliability score of .81. The INFIT and OUTFIT mean-square statistics for items on both subscales all demonstrated good fit ranging from 0.71 to 1.40, except for 2 items that had low OUTFIT statistics. CONCLUSIONS: The revised OKT provides sufficient reliability and construct validity.

Nature-based virtual reality intervention to manage stress in family caregivers of allogeneic hematopoietic stem cell transplant recipients: a two-phase pilot study protocol.

Millions of family members and/or friends in the U.S. serve as unpaid caregivers for individuals with chronic conditions, such as cancer. Caregiving for someone undergoing an intense allogeneic hematopoietic stem cell transplant (HSCT) is particularly demanding, with accompanying physical and psychological stress. Increased stress and stress-related symptoms could make it difficult for caregivers to fulfill their roles and could negatively impact the health status and quality of life of themselves and the recipients. Virtual reality (VR) is a promising technology increasingly used for treatment and wellness in various medical settings. There is growing evidence that studies have reported the positive effects of the VR intervention in managing and reducing stress among diverse populations in various clinical scenarios; however, no published studies have focused on family caregivers of patients with cancer. The study aims to assess the feasibility and acceptability of a four-week nature-based VR intervention and to examine the effectiveness of the VR intervention on stress in HSCT caregivers. This study comprises two phases. Phase I of the study will be a single-arm pre-post design focused on assessing the feasibility and acceptability of the VR intervention. Phase II of the study will be a prospective randomized controlled group design to examine the effectiveness of the VR intervention on perceived stress. Adults (≥ 18 years) who serve as primary caregivers for a person who will undergo an allogeneic HSCT will be recruited. Fifteen participants will be enrolled for Phase I and 94 participants for Phase II (Active VR arm N=47; Sham VR arm N=47). The nature-based immersive VR program contains 360° high-definition videos of nature scenes along with nature sounds through a head-mounted display (HMD) for 20 minutes every day for four weeks. Primary outcome is perceived stress measured by the Perceived Stress Scale. Secondary/exploratory outcomes are stress-related symptoms (e.g., fatigue, sleep disturbance) and physiological biomarkers (e.g., cortisol, alpha-amylase). The importance and innovativeness of this study consist of using a first-of-its-kind, immersive VR technology to target stress and investigating the health outcomes assessed by validated objective biomarkers as well as self-report measures of the nature-based intervention in the caregiver population. Clinical trial registration: ClinicalTrials.gov, identifier NCT05909202.

Adult Patients' Experiences of Using a Patient Portal With a Focus on Perceived Benefits and Difficulties, and Perceptions on Privacy and Security: Qualitative Descriptive Study.

BACKGROUND: Patient portals can facilitate patient engagement in care management. Driven by national efforts over the past decade, patient portals are being implemented by hospitals and clinics nationwide. Continuous evaluation of patient portals and reflection of feedback from end users across care settings are needed to make patient portals more user-centered after the implementation. OBJECTIVE: The aim of this study was to investigate the lived experience of using a patient portal in adult patients recruited from a variety of care settings, focusing on their perceived benefits and difficulties of using the patient portal, and trust and concerns about privacy and security. METHODS: This qualitative descriptive study was part of a cross-sectional digital survey research to examine the comprehensive experience of using a patient portal in adult patients recruited from 20 care settings from hospitals and clinics of a large integrated health care system in the mid-Atlantic area of the United States. Those who had used a patient portal offered by the health care system in the past 12 months were eligible to participate in the survey. Data collected from 734 patients were subjected to descriptive statistics and content analysis. RESULTS: The majority of the participants were female and non-Hispanic White with a mean age of 53.1 (SD 15.34) years. Content analysis of 1589 qualitative comments identified 22 themes across 4 topics: beneficial aspects (6 themes) and difficulties (7 themes) in using the patient portal; trust (5 themes) and concerns (4 themes) about privacy and security of the patient portal. Most of the participants perceived the patient portal functions as beneficial for communicating with health care teams and monitoring health status and care activities. At the same time, about a quarter of them shared difficulties they experienced while using those functions, including not getting eMessage responses timely and difficulty finding information in the portal. Protected log-in process and trust in health care providers were the most mentioned reasons for trusting privacy and security of the patient portal. The most mentioned reason for concerns about privacy and security was the risk of data breaches such as hacking attacks and identity theft. CONCLUSIONS: This study provides an empirical understanding of the lived experience of using a patient portal in adult patient users across care settings with a focus on the beneficial aspects and difficulties in using the patient portal, and trust and concerns about privacy and security. Our study findings can serve as a valuable reference for health care institutions and software companies to implement more user-centered, secure, and private patient portals. Future studies may consider targeting other patient portal programs and patients with infrequent or nonuse of patient portals.