Nursing researchers' concern about research activities during the COVID-19 pandemic: A secondary analysis of longitudinal survey data in Japan.

The coronavirus disease (COVID-19) pandemic has negatively affected research activities across various fields. This study aimed to determine nursing researchers' concerns about research activities during the COVID-19 pandemic in Japan and subsequent changes brought on by it. For this study, we conducted descriptive statistics and text mining analyses using data from two surveys conducted by the Japan Academy of Nursing Science (JANS) in the early days of the pandemic (first survey: mid-2020) and after 2 years (second survey: early 2022). Concerns about research activities were observed in 89% and 80% of the nursing researchers in the first and second surveys, respectively. Furthermore, concerns about "Difficulty in collecting research data" and "Content and quality of your research" were stronger in the second survey. Text mining analyses revealed that in the first survey, they were concerned about environmental changes and restrictions when proceeding with research during the COVID-19 pandemic, which was unfamiliar at the time. In the second survey, after overcoming environmental changes in the early stages of the pandemic, nursing researchers' concerns shifted to anxiety about the future, such as concerns about degree acquisition, employment and career advancement, and research results. The current study highlights various concerns among nursing researchers regarding research activities that have evolved over time during the pandemic. Academic societies must flexibly construct support measures for nursing researchers when a new infectious disease occurs. Such measures should be sensitive to the prevailing social circumstances and the evolving needs of researchers.

Causality Assessment Between Drugs and Fatal Cerebral Haemorrhage Using Electronic Medical Records: Comparative Evaluation of Disease-Specific and Conventional Methods.

INTRODUCTION: A new algorithm for causality assessment of drugs and fatal cerebral haemorrhage (ACAD-FCH) was published in 2021. However, its use in clinical practice has not been verified. OBJECTIVES: This study aimed to explore the practical value of the ACAD-FCH when applying information available in clinical practice. METHODS: The medical records of patients who died at the University of Tokyo Hospital in 2020 were reviewed, and cases with intracranial haemorrhage were selected. Two evaluators independently assessed these cases using three methods (the ACAD-FCH, Naranjo algorithm, and WHO-UMC scale). The number of 'Yes', 'No', and 'No information/Do not know' responses to each question by both evaluators were summed and compared. Inter-rater reliability was evaluated for each method using agreement rates and kappa coefficients with 95% confidence intervals (CI). RESULTS: Among 316 deaths, 24 cases with intracranial haemorrhage were evaluated. The proportion of ?No information/Do not know' responses for each question was 35.6% (95% CI 31.4-40.6%) for the ACAD-FCH and 66.9% (95% CI 62.5-71.1%) for the Naranjo algorithm. The respective agreement rates and kappa coefficients were 0.917 (0.798-1.00) and 0.867 (0.675-1.00) for the ACAD-FCH, 0.708 (0.512-0.904) and 0.139 (-0.236 to 0.513) for the Naranjo algorithm, and 0.50 (0.284-0.716) and 0.326 (0.110-0.541) for the WHO-UMC scale, respectively. CONCLUSION: Our findings suggest the utility of the ACAD-FCH when assessing death cases with intracranial haemorrhage. However, larger studies including intra-rater assessments are warranted for further validation of this algorithm.

Mapping Injection Order Messages to Health Level 7 Fast Healthcare Interoperability Resources to Collate Infusion Pump Data.

BACKGROUND: When administering an infusion to a patient, it is necessary to verify that the infusion pump settings are in accordance with the injection orders provided by the physician. However, the infusion rate entered into the infusion pump by the health care provider cannot be automatically reconciled with the injection order information entered into the electronic medical records (EMRs). This is because of the difficulty in linking the infusion rate entered into the infusion pump by the health care provider with the injection order information entered into the EMRs. OBJECTIVES: This study investigated a data linkage method for reconciling infusion pump settings with injection orders in the EMRs. METHODS: We devised and implemented a mechanism to convert injection order information into the Health Level 7 Fast Healthcare Interoperability Resources (FHIR), a new health information exchange standard, and match it with an infusion pump management system in a standard and simple manner using a REpresentational State Transfer (REST) application programming interface (API). The injection order information was extracted from Standardized Structured Medical Record Information Exchange version 2 International Organization for Standardization/technical specification 24289:2021 and was converted to the FHIR format using a commercially supplied FHIR conversion module and our own mapping definition. Data were also sent to the infusion pump management system using the REST Web API. RESULTS: Information necessary for injection implementation in hospital wards can be transferred to FHIR and linked. The infusion pump management system application screen allowed the confirmation that the two pieces of information matched, and it displayed an error message if they did not. CONCLUSION: Using FHIR, the data linkage between EMRs and infusion pump management systems can be smoothly implemented. We plan to develop a new mechanism that contributes to medical safety through the actual implementation and verification of this matching system.

Relationship between research activities and individual factors among Japanese nursing researchers during the COVID-19 pandemic.

AIM: To explore the individual factors (such as gender, division of household labor, childcare and elder care) and their impact on research activities in the Japanese nursing research community during the early stage of the COVID-19 pandemic from April to June in 2020. DESIGN: Cross-sectional study. METHODS: An online survey with a self-reported questionnaire was conducted on Japan Academy of Nursing Science members to explore the impacts of individual factors among Japanese nursing researchers from April to June 2020. A multivariate logistic regression model was used for data analysis. RESULTS: A total of 1,273 participants (90.7% female, 85.8% university faculty) were included in the analysis. This survey showed that no evidence of a significant gender gap was found in research activities in Japanese nursing researchers during the COVID-19 pandemic. Research activities during the pandemic were associated with time and motivation.

Research Types and New Trends on the Omaha System Published From 2012 to 2019: A Scoping Review.

The Omaha System is a popular and standard term used in community health. This scoping review aimed to update the research types and identify new usage trends for the Omaha System through articles published between 2012 and 2019. The bibliography databases PubMed, CINAHL, Scopus, PsycInfo, Ovid, and ICHUSHI and the Omaha System's Web site were used to search for publications. Research articles published between 2012 and 2019 that included "Omaha System" in the title or abstract and were written in English or Japanese were included in this review. After excluding duplicate articles, 305 articles were screened and 82 were included in our analysis. There was a median of 10.3 articles per year. The percentages for each type of use of the Omaha System to "analyze client problem," "analyze clinical process," "analyze client outcomes," and "advanced classification research" were 18.3%, 12.2%, 23.2%, and 4.9%, respectively. The reclassification of the type "others" (41.5%) included "use the Omaha System data for assessment for other than clients," "use the Omaha System data as structured data," "encode by the Omaha System code," "adopt the OS framework," "clinical information system," and "literature review." This newly reclassified category will help capture future research trends using the Omaha System.

Machine learning models to detect social distress, spiritual pain, and severe physical psychological symptoms in terminally ill patients with cancer from unstructured text data in electronic medical records.

BACKGROUND: Few studies have developed automatic systems for identifying social distress, spiritual pain, and severe physical and phycological symptoms from text data in electronic medical records. AIM: To develop models to detect social distress, spiritual pain, and severe physical and psychological symptoms in terminally ill patients with cancer from unstructured text data contained in electronic medical records. DESIGN: A retrospective study of 1,554,736 narrative clinical records was analyzed 1 month before patients died. Supervised machine learning models were trained to detect comprehensive symptoms, and the performance of the models was tested using the area under the receiver operating characteristic curve (AUROC) and precision recall curve (AUPRC). SETTING/PARTICIPANTS: A total of 808 patients was included in the study using records obtained from a university hospital in Japan between January 1, 2018 and December 31, 2019. As training data, we used medical records labeled for detecting social distress (n = 10,000) and spiritual pain (n = 10,000), and records that could be combined with the Support Team Assessment Schedule (based on date) for detecting severe physical/psychological symptoms (n = 5409). RESULTS: Machine learning models for detecting social distress had AUROC and AUPRC values of 0.98 and 0.61, respectively; values for spiritual pain, were 0.90 and 0.58, respectively. The machine learning models accurately identified severe symptoms (pain, dyspnea, nausea, insomnia, and anxiety) with a high level of discrimination (AUROC > 0.8). CONCLUSION: The machine learning models could detect social distress, spiritual pain, and severe symptoms in terminally ill patients with cancer from text data contained in electronic medical records.

Supervised machine learning-based prediction for in-hospital pressure injury development using electronic health records: A retrospective observational cohort study in a university hospital in Japan.

BACKGROUND: In hospitals, nurses are responsible for pressure injury risk assessment using several kinds of risk assessment scales. However, their predictive validity is insufficient to initiate targeted preventive strategy for each patient. The use of electronic health records with machine learning technique is a promising strategy to provide automated clinical decision-making aid. OBJECTIVE: The purpose of this study was to construct a predictive model for pressure injury development which included feature variables that can be collected on the first day of hospitalization by nurses who routinely input the data to electronic health records. DESIGN: Retrospective observational cohort study. SETTING: This study was conducted at a university hospital in Japan. PARTICIPANTS: This study used electronic health records, which include entry/discharge records, basic nursing records, and pressure injury management documents (N = 75,353). METHODS: The outcome measure was the pressure injuries which developed outside of an operation theatre and frequently appeared on the specific body parts at high risk of pressure injury development. We utilized four major classifiers: logistic regression, random forest, linear support vector machine, and extreme gradient boosting (XGBoost) with 5-fold cross-validation technique. The area under the receiver operating characteristic curve (AUC) was used for evaluating predictive performance. RESULTS: The proportion of hospital-acquired pressure injuries was 0.52%. The receiver operating characteristic curves revealed the best predictive performance for the XGBoost model, achieving the highest sensitivity of 0.78±0.03 and AUC of 0.80±0.02 amongst four types of classifiers. Variables related to difficulty in activities of daily living, anorexia, and respiratory or cardiac disorders were extracted as important features. CONCLUSIONS: Our findings suggest that routinely collected health data by nurses on the first day of patient admission have the potential to help determine high-risk patients for pressure injury development. Tweetable abstract: Machine learning models on routinely collected electronic health records data successfully predict pressure injury development during hospitalization. FUNDING: This work was supported by a JSPS KAKENHI Grant-in-Aid for Exploratory Research (16K15865).

Automatic Classification of Electronic Nursing Narrative Records Based on Japanese Standard Terminology for Nursing.

In Japan, nursing records are not easily put to secondary use because nursing documentation is not standardized. In recent years, electronic health records have necessitated the creation of Japanese nursing terminology. The purpose of this study was to develop and evaluate an automatic classification system for narrative nursing records using natural language processing technology and machine learning. We collected a week's worth of narrative nursing records from an academic hospital. The authors independently annotated the text data, dividing it into morphemes, the smallest meaningful unit in a language. During preprocessing when creating feature quantities, we used a Japanese tokenizer, MeCab, an open-source morphological parser, and the bag-of-words model. A support vector machine was adopted as a classifier for machine learning. The accuracy was 0.96 and 0.86 on the training set and test set, respectively, and the F value was 0.82. Our findings provide useful information regarding the development of an automatic classification system for Japanese nursing records using nursing terminology and natural language processing techniques.

Highly accurate and explainable detection of specimen mix-up using a machine learning model.

Background Delta check is widely used for detecting specimen mix-ups. Owing to the inadequate specificity and sparseness of the absolute incidence of mix-ups, the positive predictive value (PPV) of delta check is considerably low as it is labor consuming to identify true mix-up errors among a large number of false alerts. To overcome this problem, we developed a new accurate detection model through machine learning. Methods Inspired by delta check, we decided to conduct comparisons with the past examinations and broaden the time range. Fifteen common items were selected from complete blood cell counts and biochemical tests. We considered examinations in which ≥11 among the 15 items were measured simultaneously in our hospital; we created individual partial time-series data of the consecutive examinations with a sliding window size of 4. The last examinations of the partial time-series data were shuffled to generate artificial mix-up cases. After splitting the dataset into development and validation sets, we allowed a gradient-boosting-decision-tree (GBDT) model to learn using the development set to detect whether the last examination results of the partial time-series data were artificial mixed-up results. The model's performance was evaluated on the validation set. Results The area under the receiver operating characteristic curve (ROC AUC) of our model was 0.9983 (bootstrap confidence interval [bsCI]: 0.9983-0.9985). Conclusions The GBDT model was more effective in detecting specimen mix-up. The improved accuracy will enable more facilities to perform more efficient and centralized mix-up detection, leading to improved patient safety.

Can Staff Distinguish Falls: Experimental Hypothesis Verification Using Japanese Incident Reports and Natural Language Processing.

Falls are generally classified into two groups in clinical settings in Japan: falls from the same level and falls from one level to another. We verified whether clinical staff could distinguish between these two types of falls by comparing 3,078 free-text incident reports about falls using a natural language processing technique and a machine learning technique. Common terms were used in reports for both types of falls, but the similarity score between the two types of reports was low, and the performance of identification based on the classification model constructed by support vector machine and deep learning was low. Although it is possible that adjustment of hyper parameters during construction of the classification model was required, we believe that clinical staff cannot distinguish between the two types of falls and do not record the distinction in incident reports.

Evaluating the Effectiveness of a Fall Risk Screening Tool Implemented in an Electronic Medical Record System.

We investigated the effect of using a fall risk screening tool in an electronic medical record system by using data for 25 039 patients in 24 general wards of a single institution. The probability of the occurrence of falls decreased after the tool was implemented, but using the tool did not reduce the actual occurrence of falls. This indicates that we must improve not only the assessment of the risk of falls but also the interventions to prevent falls.

Establishing a Classification System for High Fall-Risk Among Inpatients Using Support Vector Machines.

We constructed a model using a support vector machine to determine whether an inpatient will suffer a fall on a given day, depending on patient status on the previous day. Using fall report data from our own facility and intensity-of-nursing-care-needs data accumulated through hospital information systems, a dataset comprising approximately 1.2 million patient-days was created. Approximately 50% of the dataset was used as training and testing data. A multistep grid search was conducted using the semicomprehensive combination of three parameters. A discriminant model for the testing data was created for each parameter to identify which parameter had the highest score by calculating the sensitivity and specificity. The score of the model with the highest score had a sensitivity of 64.9% and a specificity of 69.6%. By adopting a method that relies on daily data recorded in the electronic medical record system and accurately predicts unknown data, we were able to overcome issues described in previous studies while simultaneously constructing a discriminant model for patients' fall risk that does not burden nurses and patients with information gathering.

Evaluation of a Fall Risk Prediction Tool Using Large-Scale Data.

To support nursing care for the prevention of falls among inpatients at our institution, we developed and implemented a fall risk prediction tool. To evaluate its effectiveness, we compared the number of falls among inpatients before and after its implementation. The odds ratio for the probability of falling was 0.79 (95% confidence interval: 0.69-0.91) (p < 0.001), which was adjusted based on institutional data comprising 573,216 records from 25,039 patients in 24 general wards. Although whether nurses used the tool completely or whether the dissemination of fall prevention measures led to behavioral changes among the nurses in relation to their care remained unclear, the fall risk of inpatients appeared to be reduced after implementation of the prediction tool.

Construction and evaluation of FiND, a fall risk prediction model of inpatients from nursing data.

AIM: To construct and evaluate an easy-to-use fall risk prediction model based on the daily condition of inpatients from secondary use electronic medical record system data. METHODS: The present authors scrutinized electronic medical record system data and created a dataset for analysis by including inpatient fall report data and Intensity of Nursing Care Needs data. The authors divided the analysis dataset into training data and testing data, then constructed the fall risk prediction model FiND from the training data, and tested the model using the testing data. RESULTS: The dataset for analysis contained 1,230,604 records from 46,241 patients. The sensitivity of the model constructed from the training data was 71.3% and the specificity was 66.0%. The verification result from the testing dataset was almost equivalent to the theoretical value. CONCLUSION: Although the model's accuracy did not surpass that of models developed in previous research, the authors believe FiND will be useful in medical institutions all over Japan because it is composed of few variables (only age, sex, and the Intensity of Nursing Care Needs items), and the accuracy for unknown data was clear.