Development of ICNP-based inpatient falls prevention catalogue

Evaluating the validity of the nursing statements algorithmically generated based on the International Classifications of Nursing Practice for respiratory nursing care using large language models

OBJECTIVE

This study aims to facilitate the creation of quality standardized nursing statements in South Korea's hospitals using algorithmic generation based on the International Classifications of Nursing Practice (ICNP) and evaluation through Large Language Models.

MATERIALS AND METHODS

We algorithmically generated 15 972 statements related to acute respiratory care using 117 concepts and concept composition models of ICNP. Human reviewers, Generative Pre-trained Transformers 4.0 (GPT-4.0), and Bio_Clinical Bidirectional Encoder Representations from Transformers (BERT) evaluated the generated statements for validity. The evaluation by GPT-4.0 and Bio_ClinicalBERT was conducted with and without contextual information and training.

RESULTS

Of the generated statements, 2207 were deemed valid by expert reviewers. GPT-4.0 showed a zero-shot  AUC of 0.857, which aggravated with contextual information. Bio_ClinicalBERT, after training, significantly improved, reaching an AUC of 0.998.

CONCLUSION

Bio_ClinicalBERT effectively validates auto-generated nursing statements, offering a promising solution to enhance and streamline healthcare documentation processes.

ICNP® terminological subset for preventing falls in the elderly in primary care

OBJECTIVE

Build and validate a terminological subset of ICNP® for the prevention of falls in the elderly in the context of primary health care, in light of the Self-Care Deficit Theory.

METHOD

Methodological study developed in accordance with ICN recommendations and the Brazilian method for constructing terminological subsets, in two stages: 1) construction of ICNP® statements of nursing diagnoses, outcomes, and interventions; 2) content validation of statements by specialist nurses.

RESULTS

A total of 182 diagnoses/outcomes and 321 nursing interventions were constructed, which were subjected to content validation by 28 experts, being validated with a Content Validity Index ≥ 0.80. After validation, the statements were organized according to self-care requirements and the majority of diagnoses/outcomes (51.6%) and interventions (52.7%) were classified under health deviation requirements.

CONCLUSION

It was possible to construct and validate a terminological subset of ICNP® with a predominance of statements related to health deviation requirements, standing out for being the first terminological subset for the prevention of falls in the elderly in the context of primary care.

Creating Subsets of International Classification for Nursing Practice Precoordinated Concepts: Diagnoses/Outcomes and Interventions Categorized Into Areas of Nursing Practice

The International Classification for Nursing Practice is a comprehensive terminology representing the domain of nursing practice. A categorization of the diagnoses/outcomes and interventions may further increase the usefulness of the terminology in clinical practice. The aim of this study was to categorize the precoordinated concepts of the International Classification for Nursing Practice into subsets for nursing diagnoses/outcomes and interventions using the structure of an established documentation model. The aim was also to investigate the distribution of the precoordinated concepts of the International Classification for Nursing Practice across the different areas of nursing practice. The method was a descriptive content analysis using a deductive approach. The VIPS model was used as a theoretical framework for categorization. The results showed that all the precoordinated concepts of the International Classification for Nursing Practice could be categorized according to the keywords in the VIPS model. It also revealed the parts of nursing practice covered by the concepts of the International Classification for Nursing Practice as well as the parts that needed to be added to the International Classification for Nursing Practice. This has not been identified in earlier subsets as they covered only one specific area of nursing.

Utilizing standardized nursing terminologies in implementing an AI-powered fall-prevention tool to improve patient outcomes: a multihospital study

OBJECTIVES

Standardized nursing terminologies (SNTs) are necessary to ensure consistent knowledge expression and compare the effectiveness of nursing practice across settings. This study investigated whether SNTs can support semantic interoperability and outcoming tracking over time by implementing an AI-powered CDS tool for fall prevention across multiple EMR systems.

MATERIALS AND METHODS

The study involved 3 tertiary academic hospitals and 1 public hospital with different EMR systems and nursing terms, and employed an AI-powered CDS tool that determines the fall risk within the next hour (prediction model) and recommends tailored care plans (CDS functions; represented by SNTs). The prediction model was mapped to local data elements and optimized using local data sets. The local nursing statements in CDS functions were mapped using an ICNP-based inpatient fall-prevention catalog. Four implementation models were compared, and patient outcomes and nursing activities were observed longitudinally at one site.

RESULTS

The postimplementation approach was practical for disseminating the AI-powered CDS tool for nursing. The 4 hospitals successfully implemented prediction models with little performance variation; the AUROCs were 0.8051-0.9581. The nursing process data contributed markedly to fall-risk predictions. The local nursing statements on preventing falls covered 48.0%-86.7% of statements. There was no significant longitudinal decrease in the fall rate (P = .160, 95% CI = -1.21 to 0.21 per 1000 hospital days), but rates of interventions provided by nurses were notably increased.

CONCLUSION

SNTs contributed to achieving semantic interoperability among multiple EMR systems to disseminate AI-powered CDS tools and automatically track nursing and patient outcomes.

Use of the clinical care classification in South Korean nursing practice: Challenges and opportunities

BACKGROUND AND OBJECTIVES

A government-driven standardization of nursing terminology including the Clinical Care Classification (CCC) was endorsed in South Korea in 2015, but the number of hospitals who have adopted this standard terminology remains unknown. This study aimed to determine the CCC awareness, adoption, and utilization statuses and its association with patient experience in South Korea.

DESIGN, SETTING, AND PARTICIPANTS

A nationwide telephone survey was conducted from January 13 to February 12, 2022 among 217 tertiary and secondary hospitals participating in the health information exchange network. The survey questionnaire included 22 items in 3 categories: current status of electronic nursing records, awareness and adoption of standard terminology, and open-ended questions regarding standard usage and dissemination. General characteristics and experience scores of the patients of the surveyed hospitals were collected from the publicly available data sources. Data analysis was performed using descriptive statistics, t-test, and generalized linear regression.

MAIN OUTCOMES AND MEASURES

The rates of awareness and adoption in hospitals to the nursing terminology standard of the CCC were calculated, and the current status of electronic nursing records used in practice was examined. The relationships between CCC awareness and the characteristics of hospitals in their patient experiences of health services were also identified.

RESULTS

The survey response rate was 24.9 % (54/217). Two out of three hospitals (68.5 %) were aware of the CCC. These hospitals had 800 beds or more, and higher scores for patient experience. CCC awareness was significantly related to increases in the overall scores for patient experiences (t = 2.70, p =.0103), but no significance with sub-score for nursing service (t = 1.23, p =.1594).

CONCLUSIONS

With a high adoption rate of electronic medical record systems, two-third hospitals acknowledged their CCC awareness, but were still lagged in adoption and usage of it in practice with operational challenges. The CCC awareness has potential relationships with positive patient experience.

Perceived knowledge on the ICNP© in undergraduate nursing students: the development of a scale

OBJECTIVES

To develop and validate an instrument to assess nursing students' perceived knowledge on the International Classification for Nursing Practice.

METHODS

The study design is an initial development of a scale by a longitudinal, prospective, monocentric study. An instrument, including a final pool of 6 items, was developed and through a Content Validity approved by experts. Cronbach's alpha coefficient, Exploratory Factor Analysis and Confirmatory Factor Analysis were calculated in a sample of nursing students.

RESULTS

The instrument demonstrated a CVI of 1.0. Cronbach's alpha coefficient was 0.879. Exploratory Factor Analysis indicated one component, with a saturation of items in the range between 0.594 and 0.856. Confirmatory Factor Analysis confirmed the structure.

CONCLUSIONS

Although further studies are needed, the preliminary analyses of the instrument suggest satisfaction in terms of content validity, factorial structure, and reliability. This instrument may rise interest in international nursing educational context.

Effectiveness of nursing care provided for fall prevention: Survival analysis of nursing records in a tertiary hospital

AIM

This study was carried out to analyze nursing care provided to patients on high and low fall-risk days and to evaluate the effectiveness of nursing care in terms of preventing falls.

METHODS

A retrospective review of medical records was conducted for patients admitted to a tertiary hospital in Korea. General and clinical information, fall occurrences, Hendrich II Fall Risk Model (HFRM II) fall-risk assessment scores, nursing care related to fall prevention, and medications administered were extracted.

RESULTS

Data from 43,267 days of records for 11,718 patients were analyzed. Nursing assessment, intervention, and administration of medication were provided more frequently on high fall-risk days than on low fall-risk days. Analysis performed on the entire cohort days showed fall occurrence was significantly associated with infrequent mobility assessment and greater usage of anti-anxiety agents. On high fall-risk days, fall occurrence was related to less restraint assessment and greater usage of vessel dilatators.

CONCLUSIONS

The implementation of risk-targeted interventions for fall prevention based on fall-risk assessment is needed. For general fall prevention, assessment of patients' mobility should be strengthened. For high fall-risk patients, it may be more effective for nurses to focus on assessing restraints, evaluating medication records, and withdrawing medications related to falls.

Automatic population of eMeasurements from EHR systems for inpatient falls

Objective

Representing nursing data sets in a standard way will help to facilitate sharing relevant information across settings. We aimed to populate nursing process and outcome metrics with electronic health record (EHR) data and then compare the results with event reporting systems.

Methods

We used the "eMeasure" development process of the National Quality Forum adopted by the American Nurses Association. We used operational definitions of quality measures from the American Nurses Association and the US Institute for Healthcare Improvement and employed concept mapping of local data elements to 2 controlled vocabularies to define a standard data dictionary: (1) Logical Observation Identifiers Names and Codes and (2) International Classification for Nursing Practice. We assessed feasibility using the nursing data set of 7829 and 8199 patients from 2 general hospitals with different EHR systems. Using inpatient falls as a use case, we compared the populated measures with results from the event reporting systems.

Results

We identified 17 care components and 118 unique concepts and matched them with data elements in the EHRs. Including suboptimal mapping, 98% of the assessment concepts mapped to Logical Observation Identifiers Names and Codes and 52.9% of intervention concepts mapped to International Classification for Nursing Practice. While not all process indicators were available from event reporting systems, we successfully populated 9 fall prevention process indicators and the fall rate outcome indicator from the 2 EHRs. We were unable to populate the falls with an injury rate indicator.

Conclusions

EHR data can populate fall prevention process measure metrics and at least one inpatient fall prevention outcome metric.