Search

Nursing staff record observations about older people under their care in free-text nursing notes. These notes contain older people's care needs, disease symptoms, frequency of symptom occurrence, nursing actions, etc. Therefore, it is vital to develop a technique to uncover important data from these notes. This study developed and evaluated a deep learning and transfer learning-based named entity recognition (NER) model for extracting symptoms of agitation in dementia from the nursing notes. We employed a Clinical BioBERT model for word embedding. Then we applied bidirectional long-short-term memory (BiLSTM) and conditional random field (CRF) models for NER on nursing notes from Australian residential aged care facilities. The proposed NER model achieves satisfactory performance in extracting symptoms of agitation in dementia with a 75% F1 score and 78% accuracy. We will further develop machine learning models to recommend the optimal nursing actions to manage agitation. [ABSTRACT FROM AUTHOR]

This study aimed to develop a mapping table that connects nursing notes with standard terminology, focusing on nurses' concerns for ICU patients. After extracting nursing notes from a publicly accessible database, a research team, including a nursing informatics professor and researchers with ICU experience, developed a mapping table through a four-step process: initially reviewing literature on nurses' concerns, then extracting nursing notes from MIMIC IV and filtering the duplicate notes, subsequently defining and coding these concerns, and finally mapping them according to the CCC. Of 11,430,637 unstructured nursing notes from MIMIC IV, 265 unique notes remained after deduplication, with 208 notes reflecting nurses' concerns and categorized into 15 groups aligned with CCC. This mapping table will be a fundamental tool for predicting clinical deterioration in ICU patients by identifying important lexicons through natural language processing. [ABSTRACT FROM AUTHOR]

This study examined the effects of language differences between Korean and English on the performance of natural language processing in the classification task of identifying inpatient falls from unstructured nursing notes. [ABSTRACT FROM AUTHOR]

This study analyzed what nurses wrote in narrative nursing notes for nursing outcome of cardiac-surgery patients. The nursing notes of 46 patients were decomposed into phrases and analyzed based on the nursing process. Eight patterns were extracted according to different combinations of nursing-process components, of which 29.2% have nursing outcome phrases. The content of the nursing notes was also classified into 15 categories, of which nursing outcomes were recorded more frequently in nursing care driven mainly by physician's order, such as disease-related symptom management, insomnia care, respiratory care, and pain control, than in independent nursing care such as education and emotional care. A survey on the attitudes of nurses toward the nursing record revealed that they do not document nursing outcomes as much as they think they do. The main reasons for this discrepancy were insufficient time for recording and lack of knowledge about why, how, and what to evaluate. Even though there is room for improvement, nursing notes represent a useful resource for determining nursing contributions to patient outcomes. [ABSTRACT FROM AUTHOR]

This study investigated the human-computer interfaces used for entering narrative nursing notes in the electronic medical record systems at six Korean hospitals. Using a criteria-based evaluation tool consisting of 17 elements revealed scores of 3.5-6.5. This implies that many criteria were not fulfilled and that considerable improvement is needed. [ABSTRACT FROM AUTHOR]

The ENR System of Seoul National University Bundang Hospital was made after analyzing paper-based narrative nursing records with ICNP, a combinatorial nursing terminology. In this study, we analyzed paper-based narrative nursing records with ICNP on surgical patients and evaluated practical use of the terminology and the system after building and applying ENR System. We found that we need to add new concepts to the ICNP to improve expression of nursing records especially in describing nursing actions. [ABSTRACT FROM AUTHOR]