Use of Standardized and Non-Standardized Tools for Measuring the Risk of Falls and Independence in Clinical Practice

Neugebauer, Jan; Tóthová, Valérie; Doležalová, Jitka

doi:10.3390/ijerph18063226

Cited by 12 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data related to patients' consultation questions has been collected and presented in the form of natural language. Pre-processing of these unstructured data is crucial in machine learning framework [21] to remove unnecessary, duplicated, irrelevant, and noisy data [22]. This study involved several steps to process these consultation questions, including normalization, tokenization, part-of-speech tagging, and stop-word removal, thereby forming a reliable corpus.…”

Section: Data Pre-processingmentioning

confidence: 99%

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

Zheng,

Cai,

Yan

et al. 2024

JMIR Hum Factors

View full text Add to dashboard Cite

Background The rapid growth of web-based medical services has highlighted the significance of smart triage systems in helping patients find the most appropriate physicians. However, traditional triage methods often rely on department recommendations and are insufficient to accurately match patients’ textual questions with physicians’ specialties. Therefore, there is an urgent need to develop algorithms for recommending physicians. Objective This study aims to develop and validate a patient-physician hybrid recommendation (PPHR) model with response metrics for better triage performance. Methods A total of 646,383 web-based medical consultation records from the Internet Hospital of the First Affiliated Hospital of Xiamen University were collected. Semantic features representing patients and physicians were developed to identify the set of most similar questions and semantically expand the pool of recommended physician candidates, respectively. The physicians’ response rate feature was designed to improve candidate rankings. These 3 characteristics combine to create the PPHR model. Overall, 5 physicians participated in the evaluation of the efficiency of the PPHR model through multiple metrics and questionnaires as well as the performance of Sentence Bidirectional Encoder Representations from Transformers and Doc2Vec in text embedding. Results The PPHR model reaches the best recommendation performance when the number of recommended physicians is 14. At this point, the model has an F1-score of 76.25%, a proportion of high-quality services of 41.05%, and a rating of 3.90. After removing physicians’ characteristics and response rates from the PPHR model, the F1-score decreased by 12.05%, the proportion of high-quality services fell by 10.87%, the average hit ratio dropped by 1.06%, and the rating declined by 11.43%. According to whether those 5 physicians were recommended by the PPHR model, Sentence Bidirectional Encoder Representations from Transformers achieved an average hit ratio of 88.6%, while Doc2Vec achieved an average hit ratio of 53.4%. Conclusions The PPHR model uses semantic features and response metrics to enable patients to accurately find the physician who best suits their needs.

show abstract

Section: Data Pre-processingmentioning

confidence: 99%

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

Zheng,

Cai,

Yan

et al. 2024

JMIR Hum Factors

View full text Add to dashboard Cite

show abstract

“…они не станут себя расценивать как людей с высоким рисом падений. Предпочтительно говорить с ними о «здоровом старении», а не о профилактике падений [6,7].…”

Section: этиология паденийunclassified

Nursing protocol: fall prevention in elderly and senile patients

Ткачева

Рунихина

Шарашкина

et al. 2021

Rossiiskii zhurnal geriatricheskoi meditsiny

View full text Add to dashboard Cite

The prevalence of in-hospital falls varies depending on medical institution profile and department. According to various sources, the incidence of falls in intensive care units (ICU) is 2.3-7 falls per 1000 bed-days (a day spent by a person in the hospital). Assessment of fall risk in elderly patients shows that especially in case of deteriorating health, after transfer to another department, and when the fall has already happened, according to the protocol nurses will allow quickly identification of the problem and provide timely correction.

show abstract

“…На основании этого осмотра можно выявить один или несколько типов нарушения ходьбы. Для стационара широко используется шкала Морсе независимо от повода и профиля госпитализации с целью разработки плана мер по профилактике падений в период нахождения в стационаре [2,8].…”

Section: оценка риска падений в пожилом возрастеunclassified

Preventive technologies in geriatrics: focus on falls

Шарашкина

Рунихина

2021

Rossiiskii zhurnal geriatricheskoi meditsiny

View full text Add to dashboard Cite

Falls predict functional status declines in old age and institutionalization. Among the causes of the falls are sensory deficits, cognitive impairment, chronic diseases such as cardiovascular, endocrine diseases, musculoskeletal system pathology, the use of sedatives, antihypertensive drugs, neuroleptics and diuretics, as well as external causes, including inappropriate aids. The optimal diagnostic method in this case is a comprehensive geriatric assessment, which allows for focused history taking, detailing the circumstances of the fall, identification of risk factors and assessment of consequences, the gait and balance testing, determination of the lower limbs and joints functions are hold in the course of CGA along with orthostatic test that detects sensory deficits. Additional measures of mandatory recommendations should be a discussion of rational nutrition, with an emphasis on adequate intake of protein with food and fluids as prevention.

show abstract

Use of Standardized and Non-Standardized Tools for Measuring the Risk of Falls and Independence in Clinical Practice

Cited by 12 publications

References 38 publications

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

Nursing protocol: fall prevention in elderly and senile patients

Preventive technologies in geriatrics: focus on falls

Contact Info

Product

Resources

About