Fall predictors in hospitalized patients living with cancer: a case–control study

Zeneli, Anita; Montalti, Sandra; Masciangelo, Itria; Manieri, Gloria; Golinucci, Monica; Nanni, Oriana; Montella, Maria Teresa; Martinelli, Giovanni; Petracci, Elisabetta

doi:10.1007/s00520-022-07208-x

Cited by 4 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This scale has strong operability and high practicability in all adult patients in the clinic. Studies have shown that its sensitivity and specificity for predicting fall-induced injuries are 100% and 65.9%, respectively [7][8][9][10]. However, this scale has not been validated in patients with AMI after PCI.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Reliability and Validity of the Johns Hopkins Fall Risk Assessment Scale in Patients with Acute Myocardial Infarction after Percutaneous Coronary Intervention

Yang,

Zhou

2024

HSF

View full text Add to dashboard Cite

Objective: To analyze the reliability and validity of the Johns Hopkins Fall Risk Assessment Scale (JHFRAS) for out-of-bed fall risk in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI). Methods: This study adopted continuity inclusion with the Chinese version of JHFRAS to test patients with AMI after PCI who were admitted to our hospital from January 2021 to December 2022. The occurrence of falls during out-of-bed activities was counted through follow-up, and the predictive value of the scale was assessed by using the area under the curve (AUC) of the receiver operator characteristic curve and determining sensitivity, specificity, Jordon's index, and critical value. The internal consistency reliability (Cronbach's α coefficient), interrater reliability (Spearman correlation analysis was conducted to analyze the scores obtained through the independent and simultaneous assessment of two reviewers who were unaware of the content and results of the scale), content validity (expert evaluation involving four experts), and criterion-related validity (the score of the Morse fall assessment scale [rMFS] was used as an indicator of criterion-related validity) were determined. Results: Through follow-up, this study found that 11 cases experienced falls during out-of-bed activities and 69 cases did not experience falls. The JHFRAS scores of the nonfall and fall groups were significantly different (p < 0.05). JHFRAS, which was designed to predict the risk of falls during out-of-bed activities in post-PCI patients with AMI, had an AUC of 0.880, a sensitivity of 0.937, a specificity of 0.824, a Jordon's index of 0.760, and a critical value of 9 points. Its Cronbach's α coefficient was 0.803. The assessment data from two reviewers were analyzed via intragroup coefficient analysis and yielded a Spearman's rank correlation coefficient of 0.948. The overall content validity of the scale was 0.968. The content validity indices of age, fall history, urine and defecation excretion amount, high-risk drug use, stent number, action capability, and cognitive ability were 0.915, 0.924, 0.938, 0.920, 0.954, 0.960 and 0.972, respectively. All correlation coefficients were significant at the 0.01 level. The scores of each dimension of rMFS and JHFRAS showed positive correlations. Conclusions: JHFRAS has good reliability and validity and can be used to assess the fall risk of out-of-bed activities in patients with AMI after PCI.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of the Reliability and Validity of the Johns Hopkins Fall Risk Assessment Scale in Patients with Acute Myocardial Infarction after Percutaneous Coronary Intervention

Yang,

Zhou

2024

HSF

View full text Add to dashboard Cite

show abstract

“…Inpatient falls detrimentally impact patients, leading to extended hospital stays and distress among families and caregivers [1][2][3][4][5]. Studies reflect a varying incidence rate of such falls, with 250,000 annually in England and Wales alone [1], and evidence showing 7.5% of patients experience at least 1 fall during hospitalization [2].…”

Section: Introductionmentioning

confidence: 99%

BERT-Based Neural Network for Inpatient Fall Detection From Electronic Medical Records: Retrospective Cohort Study

Cheligeer,

Wu,

Lee

et al. 2024

JMIR Med Inform

View full text Add to dashboard Cite

Background Inpatient falls are a substantial concern for health care providers and are associated with negative outcomes for patients. Automated detection of falls using machine learning (ML) algorithms may aid in improving patient safety and reducing the occurrence of falls. Objective This study aims to develop and evaluate an ML algorithm for inpatient fall detection using multidisciplinary progress record notes and a pretrained Bidirectional Encoder Representation from Transformers (BERT) language model. Methods A cohort of 4323 adult patients admitted to 3 acute care hospitals in Calgary, Alberta, Canada from 2016 to 2021 were randomly sampled. Trained reviewers determined falls from patient charts, which were linked to electronic medical records and administrative data. The BERT-based language model was pretrained on clinical notes, and a fall detection algorithm was developed based on a neural network binary classification architecture. Results To address various use scenarios, we developed 3 different Alberta hospital notes-specific BERT models: a high sensitivity model (sensitivity 97.7, IQR 87.7-99.9), a high positive predictive value model (positive predictive value 85.7, IQR 57.2-98.2), and the high F1-score model (F1=64.4). Our proposed method outperformed 3 classical ML algorithms and an International Classification of Diseases code–based algorithm for fall detection, showing its potential for improved performance in diverse clinical settings. Conclusions The developed algorithm provides an automated and accurate method for inpatient fall detection using multidisciplinary progress record notes and a pretrained BERT language model. This method could be implemented in clinical practice to improve patient safety and reduce the occurrence of falls in hospitals.

show abstract

Using machine learning models to predict falls in hospitalised adults

Jahandideh,

Hutchinson,

Bucknall

et al. 2024

International Journal of Medical Informatics

View full text Add to dashboard Cite

Fall predictors in hospitalized patients living with cancer: a case–control study

Cited by 4 publications

References 28 publications

Analysis of the Reliability and Validity of the Johns Hopkins Fall Risk Assessment Scale in Patients with Acute Myocardial Infarction after Percutaneous Coronary Intervention

Analysis of the Reliability and Validity of the Johns Hopkins Fall Risk Assessment Scale in Patients with Acute Myocardial Infarction after Percutaneous Coronary Intervention

BERT-Based Neural Network for Inpatient Fall Detection From Electronic Medical Records: Retrospective Cohort Study

Using machine learning models to predict falls in hospitalised adults

Contact Info

Product

Resources

About