Falls as the result of interplay between nurses, patient and the environment: Using text-mining to uncover how and why falls happen

Takase, Miyuki

doi:10.1016/j.ijnss.2022.12.003

Cited by 11 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar example is seen by Takase et al. [ 31 ] who examined the perceptions of nursing staff and their role within fall events. Through the analysis of nursing reports and the development of a co-occurrence term network, they discovered three clusters of commonly recurring topics pertaining to patient, nursing, and environmental falls risk factors.…”

Section: Resultssupporting

confidence: 58%

The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review

Trinh,

Zhang,

Kovoor

et al. 2023

International Journal for Quality in Health Care

View full text Add to dashboard Cite

Background Falls are a common problem associated with significant morbidity, mortality, and economic costs. Current fall prevention policies in local healthcare settings are often guided by information provided by fall risk assessment tools, incident reporting and coding data. This review was conducted with the aim of identifying studies which utilised Natural Language Processing (NLP) for the automated detection and prediction of falls in the healthcare setting. Methods The databases Ovid Medline, Ovid Embase, Ovid Emcare, PubMed, CINAHL, IEEE Xplore and Ei Compendex were searched from 2012 until April 2023. Retrospective derivation, validation and implementation studies wherein patients experienced falls within a healthcare setting were identified for inclusion. Results The initial search yielded 2,611 publications for title and abstract screening. Full-text screening was conducted on 105 publications, resulting in 26 unique studies that underwent qualitative analyses. Studies applied NLP towards falls risk factor identification, known falls detection, future falls prediction and falls severity stratification with reasonable success. The NLP pipeline was reviewed in detail between studies and models utilising rule-based, machine learning (ML), deep learning (DL) and hybrid approaches were examined. Conclusion With a growing literature surrounding falls prediction in both inpatient and outpatient environments, the absence of studies examining the impact of these models on patient and system outcomes highlights the need for further implementation studies. Through an exploration of the application of natural language processing (NLP) techniques, it may be possible to develop models with higher performance in automated falls prediction and detection.

show abstract

Section: Resultssupporting

confidence: 58%

The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review

Trinh,

Zhang,

Kovoor

et al. 2023

International Journal for Quality in Health Care

View full text Add to dashboard Cite

show abstract

“…In recent years, text mining has increasingly needed to be used for data mining on text data. The use of text mining is increasing in academic research, speci cally as a method that can quantitatively visualize patient evaluations of psychiatrists' attitudes [11], newspaper editorials on the COVID-19 pandemic [12], and incident reports on falls [13], Text data is one type of unstructured data and has been considered less convenient for computer-based analysis because it requires preprocessing such as data conversion and processing. Even in questionnaire surveys, there is little attention paid to text data such as free responses and descriptions, and in many cases, speci c examples are only taken up depending on the author.…”

Section: Introductionmentioning

confidence: 99%

A text mining to nutritional counseling and instruction provided by registered dietitians

Komiya,

Yoshida,

Oshima

et al. 2024

Preprint

View full text Add to dashboard Cite

Objective The study aimed to conduct a comprehensive analysis of medical records, that specifically focused on nutritional consultations with dietitians within community pharmacies. This was done to gain insights into patient nutrition-related issues, concerns, and responses. That can be used to acquire precise health support information. Methods Text mining was used to conduct a quantitative analysis of nutritional consultation records. These records were documented in a Subjective-Objective-Assessment-Plan (SOAP) format, provided by eight dietitians, and involved 136 individuals of varying gender identities (male: 32, female: 101, gender non-response: 3). The consultations took place in a city pharmacy over the period from December 2020 to September 2022. Results The frequency analysis revealed that the Subjective-Objective (S/O) items were associated with behaviors such as 'eat', 'exercise', and 'drink', as well as terms associated with health indicators such as 'cholesterol', 'blood pressure', and hemoglobin A1c'. Additionally, S/O items also included words that correlate to specific laboratory values such as 'cholesterol', 'blood pressure', and hemoglobin A1c'. On the other hand, the Assessment-Plan (A/P) items identified words associated with behaviors, such as 'eat', 'diet', and 'exercise’ and with terms that are associated with laboratory values like, 'cholesterol', 'blood glucose', and 'blood pressure'. Furthermore, A/P items included words connected to nutrients, such as 'food', 'vegetables', and 'rehydration'. Through a co-occurrence network analysis, it was observed that certain associations emerged within the S/O terms are blood pressure, 'HDL - TG - LDL', 'quantity - BMI', and 'like - sweet - abstain'. While A/P associations included 'number - test', 'upper limit - potassium', 'oil - type', and 'yogurt - fat'. Conclusion The text mining method enabled visually analyzing keywords. It became comprehensively clear that nutritional consultations by dietitians often include assessing the lifestyle and related risk factors for chronic diseases such as hypertension, lipid disorders, and hyperglycemia as shown by the frequent occurrence of words for instance blood pressure, cholesterol, and blood glucose. It may help to determine priorities for action and may be the starting point for deciding which health issues should be prioritized in the information sharing for collaboration among inter-professions in the future.

show abstract

Exploring nurses' clinical judgment concerning the relative importance of fall risk factors: A mixed method approach using the Q Methodology

Takase,

Kisanuki,

Nakayoshi

et al. 2024

International Journal of Nursing Studies

View full text Add to dashboard Cite

Falls as the result of interplay between nurses, patient and the environment: Using text-mining to uncover how and why falls happen

Cited by 11 publications

References 43 publications

The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review

The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review

A text mining to nutritional counseling and instruction provided by registered dietitians

Exploring nurses' clinical judgment concerning the relative importance of fall risk factors: A mixed method approach using the Q Methodology

Contact Info

Product

Resources

About