Cin-Computers Informatics Nursing最新文献

This study proposes an evaluation of the efficacy of machine learning algorithms in classifying chronic pain based on Italian nursing notes, contributing to the integration of artificial intelligence tools in healthcare within an Italian linguistic context. The research aimed to validate the nursing diagnosis of chronic pain and explore the potential of artificial intelligence (AI) in enhancing clinical decision-making in Italian healthcare settings. Three machine learning algorithms-XGBoost, gradient boosting, and BERT-were optimized through a grid search approach to identify the most suitable hyperparameters for each model. Therefore, the performance of the algorithms was evaluated and compared using Cohen's κ coefficient. This statistical measure assesses the level of agreement between the predicted classifications and the actual data labels. Results demonstrated XGBoost's superior performance, whereas BERT showed potential in handling complex Italian language structures despite data volume and domain specificity limitations. The study highlights the importance of algorithm selection in clinical applications and the potential of machine learning in healthcare, specifically addressing the challenges of Italian medical language processing. This work contributes to the growing field of artificial intelligence in nursing, offering insights into the challenges and opportunities of implementing machine learning in Italian clinical practice. Future research could explore integrating multimodal data, combining text analysis with physiological signals and imaging data, to create more comprehensive and accurate chronic pain classification models tailored to the Italian healthcare system.

Obesity is health epidemic associated with health conditions specific to women's health. Healthcare providers must identify and develop a follow-up plan for patients with a body mass index of greater than 30 kg/m2 to meet the Merit-Based Incentive Payment System Quality Program rate for body mass index screening and follow-up. Barriers to addressing obesity in this population by healthcare providers include time available for counseling and knowledge about appropriate diagnosis and treatment options. This is a quality improvement project that implements a clinical template within an existing electronic health record platform that includes a treatment order set and prepopulated counseling prompts to improve the rate of which healthcare providers address obesity within the women's health clinic. After 12 weeks, 27 patients started a weight management plan, and the Merit-Based Incentive Payment System rate increased from 59% to 67%. Implementation of order set templates into electronic health record platforms with counseling guidance provides a framework for providers to develop a plan to address obesity to meet their patient's health goals and reduce health disparities related to obesity in women.

Nurse staffing decisions are often made without input from high-quality, reliable patient acuity measures, especially in medical-surgical settings. Staffing decisions not aligned with patient care needs can contribute to inadequate patient-to-nurse ratios and nurse burnout, potentially resulting in preventable patient harm and death. We conducted a proof-of-concept study to explore the feasibility of adapting an evidence-based patient acuity tool for use in the EHR. A retrospective cohort of pediatric medical-surgical inpatients was used to map electronic patient data variables. We developed an algorithm to calculate the score for one domain of the tool and validated it by comparing it with a score based on a manual chart review. Through multiple rounds of testing and refinement of the variables and algorithm, we achieved 100% concordance between scores generated by the algorithm and the manual chart review. Our proof-of-concept study demonstrates the feasibility and challenges of adapting an evidence-based patient acuity score for automation in the EHR. Further collaboration with data scientists is warranted to operationalize the tool in the EHR and achieve an automated acuity score that can improve staffing decisions, support nursing practice, and enhance team collaboration.

The human-centered design approach has gained prominence in the development of mobile health solutions. However, its application to support foot self-care for persons with diabetes has not been extensively explored. This study aims to develop a mobile application prototype using a human-centered design approach to support foot self-care for persons with type 2 diabetes. The project used mixed methods, including a scoping review, patient interviews, a Delphi panel, and an acceptability and usability study of an educational booklet. This three-phase approach encompassed defining the context of use, specifying user requirements, and developing design solutions. This article specifically details the third phase of the project: the development of the low-fidelity prototype. Functionalities such as daily reminders for foot care, notifications for medical appointments, communication features with healthcare professionals and peers, and repositories of videos and educational content were integrated into the design. These features were tailored to address user needs, emphasizing knowledge enhancement in self-care practices. The human-centered design approach enabled the creation of a comprehensive prototype with essential functionalities and robust educational content, filling gaps in the digital health market and empowering persons to better manage their foot health.

This study aimed to develop a mobile application self-management program for patients with implantable cardioverter-defibrillators and evaluate its effectiveness. A nonequivalent experimental group pre-post quasi-experimental study was conducted. The experimental group (n = 32) received the mobile application and education for 8 weeks. The control group (n = 32) received a booklet and education. Uncertainty, self-care competence, physical quality of life, mental quality of life, and physiological indicators (ejection fraction, systolic blood pressure, diastolic blood pressure, pulse rate) were assessed. Outcomes were analyzed using the independent t test, Mann-Whitney U test, analysis of covariance, and ranked analysis of covariance. Physical and mental quality of life significantly increased in the experimental group compared with the control group. Physiological indicators were unchanged. The mobile application self-management program may be utilized as a nursing intervention to improve quality of life for patients with implantable cardioverter-defibrillators.

Electronic health record support nurses' work in many ways; however, nursing documentation within the system has also been associated with burden and noncompliance with organizational and regulatory requirements. An increasing number of studies have analyzed nursing documentation burden and noncompliance, but no scoping review has been conducted that focuses on electronic health record-based strategies for improving nursing documentation. This scoping review aimed to identify electronic health record-based strategies for improving nursing documentation in hospital settings. The Preferred Reporting Items for Systematic Review and Meta-Analyses Extension for Scoping Reviews guidelines were used, and databases MEDLINE, Web of Science, and CINAHL were searched on April 1, 2024. A total of 652 studies were retrieved, of which 25 were included at the full-text level. Six documentation issues emerged across the studies, with 44% identifying documentation compliance as the main issue. Three electronic health record-based strategies, such as organizational change, end-user reminder system, and financial incentives, regulation, and policy, were identified. Six documentation improvement outcomes with findings were identified, with 52% of the studies' outcome demonstrating improved documentation compliance. This review identified electronic health record-based and supplemental strategies that concentrate on improving nursing documentation. More research is needed to identify how these strategies may affect other measures, such as patient care outcomes, accuracy and quality of nursing documentation, and costs associated with nursing time spent on documentation activities.

Technological advancements have fueled the integration of virtual reality into nursing education, presenting innovative teaching modalities. Nonetheless, a conspicuous gap exists in understanding the influencing factors that impact the quality of virtual reality experiences, thereby challenging educators in creating optimal learning ecosystems tailored to nursing curricula. Adopting the Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines, a comprehensive search of electronic databases including PubMed, Embase, CINAHL, Web of Science, and the Cochrane Library was performed. Forty-five studies met the inclusion criteria, revealing a broad spectrum of factors affecting virtual reality experience quality. Human-centric factors encompassed cybersickness, accommodation for individuals who wear glasses, and left-handed, elderly, and women users. System-centric issues are mainly limited immersion and inadequate interaction. The synthesis of existing literature underscores the multifaceted nature of factors influencing virtual reality experience quality in nursing education. Recommendations include enhancing immersion and interaction, considering user diversity in design, and fostering international collaborations for content standardization.

This study analyzed the gaps in clinical guidelines for the Institute for Clinical Systems Improvement by using the Omaha System. Clinicians use various Non-Opioid approaches for pain management, leading to diverse coding requirements when inputting data into EHRs. Consequently, the lack of standardized coding for Non-Opioid pain management data leads to inconsistencies, hindering effective information transfer and reuse between care settings, impacting continuity of care. By encoding guidelines within the Omaha System, this study aims to create a standardized framework that enhances data integration and promotes seamless communication across healthcare environments. To address this, pain management guidelines for Non-Opioid approaches were mapped using the Omaha System, with a focus on content feasibility, linguistic validity, and term granularity. The analysis revealed three problems, three categories, and 11 targets in the coding of Non-Opioid approaches for pain management. By integrating guidelines encoded within EHRs, the development of improved guidelines is facilitated, enhancing their efficient utilization and thereby improving nursing records and information delivery systems. In conclusion, this approach addresses the need for standardized coding, advancing both guideline development and continuity of care through improved information systems.

Physiologic surveillance systems are intended to notify nurses of patient deterioration but can be rendered ineffective when alarm burden is high. Nurses reported increased alarm burden, loss of confidence that alarms signaled actionable events, and alarm fatigue. Additionally, standard quality assurance tracking indicated a need to evaluate comprehensively the hospital's crucial patient safety system. A systems approach was used to understand changes in the care environment and regain reliable system performance after practice drift. Interventions included decreasing the continuous surveillance pulse rate alarm threshold to 40 beats per minute, restandardizing the peripheral capillary oxygen saturation alarm threshold to 80%, and resetting expectations for alarm response and utilization of alarm escalation pagers. Bedside alarms per patient day decreased by 66.4% (P < .001) for peripheral capillary oxygen saturation low and by 71.2% (P < .001) for pulse rate low. Initial pager notifications per patient day decreased by 84.5% (P < .001) for peripheral capillary oxygen saturation low and by 93% (P < .001) for pulse rate low. Even systems that are stable for long periods are subject to practice drift. This study underscores the importance of clinical process standardization and continuous measurement of system performance with feedback to sustain performance of the patient safety systems nurses rely on.

Chronic diseases globally contribute to heightened rates of morbidity and mortality. Telehealth is a viable approach to managing chronic illness. In response to the coronavirus pandemic, a research facility implemented telehealth in April 2020 to continue research activities. A telehealth program evaluation was needed to explore the facility's strengths and improvement opportunities. The Centers for Disease Control and Prevention's Framework for Program Evaluation guided the evaluation to determine whether telehealth implementation improved care access, efficiency, and provider experiences. Missed and canceled visits, visit duration, and wait times between April 2020 and June 2023 were analyzed for those 19 years and older with chronic illnesses identified by International Classification of Diseases, 10th Revision codes. Provider experiences were measured with the Telehealth Usability Questionnaire. The facility transitioned from Microsoft Teams® to a telehealth platform in March 2023, offering more robust data. Analyses revealed improved completed visits, decreased patient abandoned visits, and varied canceled and duration percentages. Providers missed visits less frequently than patients. Run charts for telehealth total visits versus chronic visits did not reveal special cause variations. Provider experiences were favorable except for telehealth reliability and interface quality. Recommendations include continued user training, evaluating patients' experiences, exploring telehealth's impact on research participant recruitment, and standardizing evaluation processes through policy development.