Development of a predictive inpatient falls risk model using machine learning

Transforming outcome expectations into retention among hospital nurses: A cross-sectional study

AIM

To examine the main effects and interaction effects of outcome expectations (e.g., anticipated satisfactory salary and benefits), nurse identity (a sense of membership in the nursing profession), and information-access efficiency of the electronic medical record system (how the system enables nurses to quickly retrieve the needed information) on nurses' retention.

DESIGN

This study uses a cross-sectional survey and adopts proportionate random sampling to recruit a representative sample of nurses of a medical centre in Taiwan.

METHODS

This study successfully obtained completed questionnaires from 430 nurses during December 2021 to January 2022. Data are analysed by using hierarchical regressions.

RESULTS

Positive outcome expectations and identification as a member in the nursing profession are associated with retention. Information-access efficiency strengthens the link between outcome expectations and retention, while nurse identity weakens this link.

CONCLUSION

Outcome expectations can help retain nurses, particularly those who perceive high levels of information-access efficiency and possess weak nurse identity. That is, outcome expectations have a complementary role with nurse identity in retaining nurses.

IMPLICATIONS FOR THE PROFESSION

Nurse managers should devise means to build positive outcome expectations for nurses. In addition, either strengthening nurses' identification with the nursing profession or improving the information-access efficiency of the electronic medical system may also help retain nurses.

IMPACT

This study examined how to transform outcome expectation to nurse retention, offering nurse managers to devise new means to retain nurses.

REPORTING METHOD

STROBE statement was chosen as EQUATOR checklist.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution.

Artificial Intelligence in the Organization of Nursing Care: A Scoping Review

BACKGROUND

The integration of artificial intelligence (AI) in the organization of nursing care has continually evolved, driven by the need for innovative solutions to ensure quality of care. The aim is to synthesize the evidence on the use of artificial intelligence in the organization of nursing care.

METHODS

A scoping review was carried out based on the Joanna Briggs Institute methodology, following the PRISMA-ScR guidelines, in the MEDLINE, CINAHL Complete, Business Source Ultimate and Scopus® databases. We used ProQuest-Dissertations and Theses to search gray literature.

RESULTS

Ten studies were evaluated, identifying AI-mediated tools used in the organization of nursing care, and synthesized into three tool models, namely monitoring and prediction, decision support, and interaction and communication technologies. The contributions of using these tools in the organization of nursing care include improvements in operational efficiency, decision support and diagnostic accuracy, advanced interaction and efficient communication, logistical support, workload relief, and ongoing professional development.

CONCLUSIONS

AI tools such as automated alert systems, predictive algorithms, and decision support transform nursing by increasing efficiency, accuracy, and patient-centered care, improving communication, reducing errors, and enabling earlier interventions with safer and more efficient quality care.

Transforming Hospital Quality Improvement Through Harnessing the Power of Artificial Intelligence

This policy analysis focuses on harnessing the power of artificial intelligence (AI) in hospital quality improvement to transform quality and patient safety. It examines the application of AI at the two following fundamental levels: (1) diagnostic and treatment and (2) clinical operations. AI applications in diagnostics directly impact patient care and safety. At the same time, AI indirectly influences patient safety at the clinical operations level by streamlining (1) operational efficiency, (2) risk assessment, (3) predictive analytics, (4) quality indicators reporting, and (5) staff training and education. The challenges and future perspectives of AI application in healthcare, encompassing technological, ethical, and other considerations, are also critically analyzed.

Development and validation of meta-measurement instruments: A methodological approach

A valid and reliable nursing assessment is essential for identifying required care and ensuring patient safety. The convenience of conducting a comprehensive assessment of the patient has led to a significant increase in assessment tools that may slow down the process. Nevertheless, the possibility of consolidating various instruments that measure common or similar constructs into a meta-instrument is considered an alternative that could enhance assessment efficiency. A meta-instrument can be defined as a measurement tool that consolidates other instruments based on measuring related constructs and sharing dimensions or items, aiming to achieve a more parsimonious measurement. Literature on such assessment tools is scarce, and there are numerous options for their construction and initial validation. Additionally, it is advisable to confirm their psychometric properties and ensure that they maintain, at the very least, the same diagnostic capacity as the original instruments. This article presents a proposal for the phases to follow in constructing meta-instruments, along with various methodological alternatives that can be employed based on the characteristics of the original instruments and the purpose of creating the meta-instrument. Furthermore, special attention is given to the checklists that should be used to study the psychometric properties and diagnostic capacity of the meta-instruments. Finally, future lines of research and challenges in the development of nursing assessment meta-instruments are discussed.

The Applications of Artificial Intelligence for Assessing Fall Risk: Systematic Review

BACKGROUND

Falls and their consequences are a serious public health problem worldwide. Each year, 37.3 million falls requiring medical attention occur. Therefore, the analysis of fall risk is of great importance for prevention. Artificial intelligence (AI) represents an innovative tool for creating predictive statistical models of fall risk through data analysis.

OBJECTIVE

The aim of this review was to analyze the available evidence on the applications of AI in the analysis of data related to postural control and fall risk.

METHODS

A literature search was conducted in 6 databases with the following inclusion criteria: the articles had to be published within the last 5 years (from 2018 to 2024), they had to apply some method of AI, AI analyses had to be applied to data from samples consisting of humans, and the analyzed sample had to consist of individuals with independent walking with or without the assistance of external orthopedic devices.

RESULTS

We obtained a total of 3858 articles, of which 22 were finally selected. Data extraction for subsequent analysis varied in the different studies: 82% (18/22) of them extracted data through tests or functional assessments, and the remaining 18% (4/22) of them extracted through existing medical records. Different AI techniques were used throughout the articles. All the research included in the review obtained accuracy values of >70% in the predictive models obtained through AI.

CONCLUSIONS

The use of AI proves to be a valuable tool for creating predictive models of fall risk. The use of this tool could have a significant socioeconomic impact as it enables the development of low-cost predictive models with a high level of accuracy.

TRIAL REGISTRATION

PROSPERO CRD42023443277; https://tinyurl.com/4sb72ssv.

Development and Validation of a Meta-Instrument for the Assessment of Functional Capacity, the Risk of Falls and Pressure Injuries in Adult Hospitalization Units (VALENF Instrument) (Part II)

The nursing assessment is the first step of the nursing process and fundamental to detecting patients' care needs and at-risk situations. This article presents the psychometric properties of the VALENF Instrument, a recently developed meta-instrument with only seven items that integrates the assessment of functional capacity, risk of pressure injuries and risk of falls with a more parsimonious approach to nursing assessment in adult hospitalization units. A cross-sectional study based on recorded data in a sample of 1352 nursing assessments was conducted. Sociodemographic variables and assessments of the Barthel, Braden and Downton instruments were included at the time of admission through the electronic health history. Thus, the VALENF Instrument obtained high content validity (S-CVI = 0.961), construct validity (RMSEA = 0.072; TLI = 0.968) and internal consistency (Ω = 0.864). However, the inter-observer reliability results were not conclusive, with Kappa values ranging between 0.213 and 0.902 points. The VALENF Instrument has adequate psychometric properties (content validity, construct validity, internal consistency and inter-observer reliability) for assessing the level of functional capacity, risk of pressure injuries and risk of falls. Future studies are necessary to establish its diagnostic accuracy.

Development and Validation of a Meta-Instrument for Nursing Assessment in Adult Hospitalization Units (VALENF Instrument) (Part I)

Nursing assessment is the basis for performing interventions that match patient needs, but nurses perceive it as an administrative load. This research aims to develop and validate a meta-instrument that integrates the assessment of functional capacity, risk of pressure ulcers and risk of falling with a more parsimonious approach to nursing assessment in adult hospitalization units. Specifically, this manuscript presents the results of the development of this meta-instrument (VALENF instrument). A cross-sectional study based on recorded data was carried out in a sample of 1352 nursing assessments. Socio-demographic variables and assessments of Barthel, Braden and Downton indices at the time of admission were included. The meta-instrument's development process includes: (i) nominal group; (ii) correlation analysis; (iii) multiple linear regressions models; (iv) reliability analysis. A seven-item solution showed a high predictive capacity with Barthel (R2adj = 0.938), Braden (R2adj = 0.926) and Downton (R2adj = 0.921) indices. Likewise, reliability was significant (p < 0.001) for Barthel (ICC = 0.969; τ-b = 0.850), Braden (ICC = 0.943; τ-b = 0.842) and Downton (ICC = 0.905; κ = 7.17) indices. VALENF instrument has an adequate predictive capacity and reliability to assess the level of functional capacity, risk of pressure injuries and risk of falls.