The Impact of Leadership in the Autonomy and Engagement of Nurses: A Cross-sectional Multicenter Study Among Nurses Outside the United States.

OBJECTIVE: To add to the body of evidence regarding nurse engagement and related factors from a non-US sample of nurses. BACKGROUND: Leadership has a positive impact on nurses' autonomy and engagement experiences. It is necessary to explore the factors that explain the relationships between leadership, autonomy, and engagement level. METHODS: Nurses (n = 4393) from 9 hospitals participated in a survey in March 2020. Multivariable logistic regression analysis was performed to identify engagement and autonomy predictors. RESULTS: Of the respondents, 9% were engaged, 28% content, 29% ambivalent, and 34% disengaged. Respondents' separate background variables were not significant predictors in multivariate models, whereas the leadership- and autonomy-related variables were. CONCLUSIONS: A manager's responsiveness, an organization's readiness to follow nurse suggestions for performance improvement, and receiving recognition and regular feedback promote engagement. Furthermore, engagement is enhanced when nurses have an active role in decision-making and their contributions are respected. Visible nurse managers and leaders who are effective advocates for nurses strengthen nurses' autonomy.

Theoretical considerations of ethics in text mining of nursing documents.

This paper discusses theoretical considerations of ethics in building and using a text mining application in nursing documentation. Nursing documentation is based on the process of gathering information from the patient, setting goals for care, documenting nursing interventions and evaluating delivered nursing care. Privacy-sensitive health care documentation brings specific ethical concerns and difficulties that one needs to be aware of and conform to when developing and using text mining tools in electronic patient records. We discuss how patient confidentiality can be ensured in this domain and how text mining might support nurses to give better and more efficient care for their patients. Our conclusion is that text mining of nursing documents holds the promise of great benefits when the potential risks are taken into consideration.

Towards automated classification of intensive care nursing narratives.

Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's kappa, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of kappa were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.

Need for change in patient education: a Finnish survey from the patient's perspective.

This study aims to find out how hospital patients in Finland perceive and evaluate the education they receive. It represents the first part of a patient education project at one university hospital in which the ultimate goal is to support patients' decision-making and self-care and in this way to facilitate the independent empowerment with health problems. The survey comprised of 754 patients from 63 of the hospital's 100 wards during a randomly selected week in spring 2001. The results show that most patients described the patient education they had received as sufficient, although some did indicate they had not learned enough about the possible side effects of care, problems of care and future care. Patients were not content with the education they received in support of social, experiential, ethical and financial aspects. The methods used in patient education should also be more diversified and patient-centred.

Applying language technology to nursing documents: pros and cons with a focus on ethics.

OBJECTIVES: The present study discusses ethics in building and using applications based on natural language processing in electronic nursing documentation. Specifically, we first focus on the question of how patient confidentiality can be ensured in developing language technology for the nursing documentation domain. Then, we identify and theoretically analyze the ethical outcomes which arise when using natural language processing to support clinical judgement and decision-making. In total, we put forward and justify 10 claims related to ethics in applying language technology to nursing documents. METHODS: A review of recent scientific articles related to ethics in electronic patient records or in the utilization of large databases was conducted. Then, the results were compared with ethical guidelines for nurses and the Finnish legislation covering health care and processing of personal data. Finally, the practical experiences of the authors in applying the methods of natural language processing to nursing documents were appended. RESULTS: Patient records supplemented with natural language processing capabilities may help nurses give better, more efficient and more individualized care for their patients. In addition, language technology may facilitate patients' possibility to receive truthful information about their health and improve the nature of narratives. Because of these benefits, research about the use of language technology in narratives should be encouraged. In contrast, privacy-sensitive health care documentation brings specific ethical concerns and difficulties to the natural language processing of nursing documents. Therefore, when developing natural language processing tools, patient confidentiality must be ensured. While using the tools, health care personnel should always be responsible for the clinical judgement and decision-making. One should also consider that the use of language technology in nursing narratives may threaten patients' rights by using documentation collected for other purposes. CONCLUSIONS: Applying language technology to nursing documents may, on the one hand, contribute to the quality of care, but, on the other hand, threaten patient confidentiality. As an overall conclusion, natural language processing of nursing documents holds the promise of great benefits if the potential risks are taken into consideration.

Towards automated classification of intensive care nursing narratives.

BACKGROUND: Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. OBJECTIVES: Our objective is to address two issues related to designing an automated classifier: domain experts' agreement on the content of classes Breathing, Blood Circulation and Pain, as well as the ability of a machine-learning-based classifier to learn the classification patterns of the nurses. METHODS: The data we used were a set of Finnish intensive care nursing narratives, and we used the regularized least-squares (RLS) algorithm for the automatic classification. The agreement of the nurses was assessed by using Cohen's kappa, and the performance of the algorithm was measured using area under ROC curve (AUC). RESULTS: On average, the values of kappa were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The RLS algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. CONCLUSIONS: Our results indicate that the free text in nursing documentation can be automatically classified and this can offer a way to develop electronic patient records.