Nurses' perceptions of the design, implementation, and adoption of machine learning clinical decision support: A descriptive qualitative study.

INTRODUCTION: The purpose of this study was to explore nurses' perspectives on Machine Learning Clinical Decision Support (ML CDS) design, development, implementation, and adoption. DESIGN: Qualitative descriptive study. METHODS: Nurses (n = 17) participated in semi-structured interviews. Data were transcribed, coded, and analyzed using Thematic analysis methods as described by Braun and Clarke. RESULTS: Four major themes and 14 sub-themes highlight nurses' perspectives on autonomy in decision-making, the influence of prior experience in shaping their preferences for use of novel CDS tools, the need for clarity in why ML CDS is useful in improving practice/outcomes, and their desire to have nursing integrated in design and implementation of these tools. CONCLUSION: This study provided insights into nurse perceptions regarding the utility and usability of ML CDS as well as the influence of previous experiences with technology and CDS, change management strategies needed at the time of implementation of ML CDS, the importance of nurse-perceived engagement in the development process, nurse information needs at the time of ML CDS deployment, and the perceived impact of ML CDS on nurse decision making autonomy. CLINICAL RELEVANCE: This study contributes to the body of knowledge about the use of AI and machine learning (ML) in nursing practice. Through generation of insights drawn from nurses' perspectives, these findings can inform successful design and adoption of ML Clinical Decision Support.

Experiences of in-hospital care among dementia caregivers in the context of high neighborhood-level disadvantage.

BACKGROUND: Persons living with dementia (PLWD) experience high rates of hospitalization and rehospitalization, exposing them to added risk for adverse outcomes including delirium, hastened cognitive decline, and death. Hospitalizations can also increase family caregiver strain. Despite disparities in care quality surrounding hospitalizations for PLWD, and evidence suggesting that exposure to neighborhood-level disadvantage increases these inequities, experiences with hospitalization among PLWD and family caregivers exposed to greater levels of neighborhood disadvantage are poorly understood. This study examined family caregiver perspectives and experiences of hospitalizations among PLWD in the context of high neighborhood-level disadvantage. METHODS: We analyzed data from the Stakeholders Understanding of Prevention Protection and Opportunities to Reduce HospiTalizations (SUPPORT) study, an in-depth, multisite qualitative study examining hospitalization and rehospitalization of PLWD in the context of high neighborhood disadvantage, to identify caregiver perspectives and experiences of in-hospital care. Data were analyzed using rapid identification of themes; duplicate transcript review was used to enhance rigor. RESULTS: Data from N = 54 individuals (47 individual interviews, 2 focus groups with 7 individuals) were analyzed. Sixty-three percent of participants identified as Black/African American, 35% as non-Hispanic White, and 2% declined to report. Caregivers' experiences were largely characterized by PLWD receiving suboptimal care that caregivers viewed as influenced by system pressures and inadequate workforce competencies, leading to communication breakdowns and strain. Caregivers described poor collaboration between clinicians and caregivers with regard to in-hospital care delivery, including transitional care. Caregivers also highlighted the lack of person-focused care and the exclusion of the PLWD from care. CONCLUSIONS: Caregiver perspectives highlight opportunities for improving hospital care for PLWD in the context of neighborhood disadvantage and recognition of broader issues in care structure that limit their capacity to be actively involved in care. Further work should examine and develop strategies to improve caregiver integration during hospitalizations across diverse contexts.

Data Science Implementation Trends in Nursing Practice: A Review of the 2021 Literature.

OBJECTIVES: The goal of this work was to provide a review of the implementation of data science-driven applications focused on structural or outcome-related nurse-sensitive indicators in the literature in 2021. By conducting this review, we aim to inform readers of trends in the nursing indicators being addressed, the patient populations and settings of focus, and lessons and challenges identified during the implementation of these tools. METHODS: We conducted a rigorous descriptive review of the literature to identify relevant research published in 2021. We extracted data on model development, implementation-related strategies and measures, lessons learned, and challenges and stakeholder involvement. We also assessed whether reports of data science application implementations currently follow the guidelines of the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by AI (DECIDE-AI) framework. RESULTS: Of 4,943 articles found in PubMed (NLM) and CINAHL (EBSCOhost), 11 were included in the final review and data extraction. Systems leveraging data science were developed for adult patient populations and were primarily deployed in hospital settings. The clinical domains targeted included mortality/deterioration, utilization/resource allocation, and hospital-acquired infections/COVID-19. The composition of development teams and types of stakeholders involved varied. Research teams more frequently reported on implementation methods than implementation results. Most studies provided lessons learned that could help inform future implementations of data science systems in health care. CONCLUSION: In 2021, very few studies report on the implementation of data science-driven applications focused on structural- or outcome-related nurse-sensitive indicators. This gap in the sharing of implementation strategies needs to be addressed in order for these systems to be successfully adopted in health care settings.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature.

BACKGROUND: The term "data science" encompasses several methods, many of which are considered cutting edge and are being used to influence care processes across the world. Nursing is an applied science and a key discipline in health care systems in both clinical and administrative areas, making the profession increasingly influenced by the latest advances in data science. The greater informatics community should be aware of current trends regarding the intersection of nursing and data science, as developments in nursing practice have cross-professional implications. OBJECTIVES: This study aimed to summarize the latest (calendar year 2020) research and applications of nursing-relevant patient outcomes and clinical processes in the data science literature. METHODS: We conducted a rapid review of the literature to identify relevant research published during the year 2020. We explored the following 16 topics: (1) artificial intelligence/machine learning credibility and acceptance, (2) burnout, (3) complex care (outpatient), (4) emergency department visits, (5) falls, (6) health care-acquired infections, (7) health care utilization and costs, (8) hospitalization, (9) in-hospital mortality, (10) length of stay, (11) pain, (12) patient safety, (13) pressure injuries, (14) readmissions, (15) staffing, and (16) unit culture. RESULTS: Of 16,589 articles, 244 were included in the review. All topics were represented by literature published in 2020, ranging from 1 article to 59 articles. Numerous contemporary data science methods were represented in the literature including the use of machine learning, neural networks, and natural language processing. CONCLUSION: This review provides an overview of the data science trends that were relevant to nursing practice in 2020. Examinations of such literature are important to monitor the status of data science's influence in nursing practice.

Characteristics of Cancer Symptom Clusters Reported through a Patient-Centered Symptom Cluster Assessment.

In the scope of symptom cluster research, few investigators have obtained patients' perceptions of their symptom clusters, even though this information is central to designing effective interventions. In this cross-sectional study, 38 adults with cancer completed measures of demographics, health outcomes (functional status, well-being, quality of life) and a symptom cluster assessment that captured symptom occurrence, severity, distress, clustering, a priority cluster, causal attributions, duration, directional relationships, and cluster interference with daily life. Participants described 72 distinct symptom clusters. Symptoms were most frequently attributed to the cancer diagnosis. Participants' priority symptom cluster typically included two symptoms of continuous duration and one intermittent symptom. Temporal order and direction of symptom relationships varied, with 75 different relationships described among symptom pairs. Greater symptom cluster burden and interference were related to poorer health outcomes. This patient-centered view of symptom clusters revealed substantial variability in symptom cluster characteristics with important implications for symptom management.

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.

Guideline-Recommended Symptom Management Strategies That Cross Over Two or More Cancer Symptoms.

PROBLEM IDENTIFICATION: Patients with cancer experience multiple symptoms, but current practice is driven by guidelines that address single symptoms. Identifying symptom management strategies recommended across two or more symptoms could relieve multiple symptoms and reduce patient burden. LITERATURE SEARCH: The Oncology Nursing Society, National Comprehensive Cancer Network, and American Society of Clinical Oncology websites were searched to identify management guidelines for 15 symptoms. DATA EVALUATION: The authors extracted symptom management strategies and recommendations. Recommendations were synthesized by symptom across the guidelines, and recommended strategies were compared across symptoms. SYNTHESIS: Among 32 guidelines reviewed, a total of 88 symptom management strategies (41 pharmacologic, 47 nonpharmacologic) were recommended across two or more symptoms. IMPLICATIONS FOR PRACTICE: Findings support the potential for coordinated selection of symptom management strategies that cross over multiple symptoms in a patient. Investigators should test these symptom management strategies in the context of co-occurring symptoms and develop guidelines that address multiple symptoms.

Systematic Review and Meta-analysis of Psychosocial Uncertainty Management Interventions.

BACKGROUND: Psychosocial uncertainty management interventions (UMIs) targeting patients and their family members might help to alleviate the negative influences of illness-related uncertainty, such as diminished quality of life and poor adjustment. OBJECTIVES: The aims of this study were to evaluate the key characteristics of psychosocial UMIs and assess intervention effects on patients' and their family members' short-term and long-term illness-related uncertainty. METHODS: We conducted a systematic review and meta-analysis of psychosocial UMIs published through 2017. We performed a comprehensive electronic search and manual review. The outcome indicator was illness-related uncertainty experienced by patients or their family members. RESULTS: We included 29 studies in the systematic review and 14 studies in the meta-analysis. The main intervention components were information and resource provision, coping skills training, social and emotional support, communication skills, symptom management and self-care, coordination of care, and exercise. Compared to usual care, patients who received UMIs reported less uncertainty immediately after intervention delivery (g = -0.44, 95% confidence interval [CI] [-0.71, -0.16]) and at later follow-up points (g = -0.47, 95% CI [-0.91, -0.03]). Family members who received UMIs also reported less uncertainty immediately after intervention delivery (g = -0.20, 95% CI [-0.33, -0.06]) and at later follow-up points (g = -0.20, 95% CI [-0.36, -0.04]). DISCUSSION: Psychosocial UMIs had small to medium beneficial effects for both patients and their family members. Questions remain regarding what intervention components, modes of delivery, or dosages influence effect size. More rigorously designed randomized controlled trials are needed to validate intervention effects on patients' and family members' uncertainty management.

Watershed and discharge influences on the phase distribution and tributary loading of total mercury and methylmercury into Lake Superior.

Knowledge of the partitioning and sources of mercury are important to understanding the human impact on mercury levels in Lake Superior wildlife. Fluvial fluxes of total mercury (Hg(T)) and methylmercury (MeHg) were compared to discharge and partitioning trends in 20 sub-basins having contrasting land uses and geological substrates. The annual tributary yield was correlated with watershed characteristics and scaled up to estimate the basin-wide loading. Tributaries with clay sediments and agricultural land use had the largest daily yields with maxima observed near the peak in water discharge. Roughly 42% of Hg(T) and 57% of MeHg was delivered in the colloidal phase. Tributary inputs, which are confined to near-shore zones of the lake, may be more important to the food-web than atmospheric sources. The annual basin-wide loading from tributaries was estimated to be 277 kg yr(-1) Hg(T) and 3.4 kg yr(-1) MeHg (5.5 and 0.07 mg km(-2) d(-1), respectively).