Abstract:Introduction.Although falls occur extremely frequently, they are still one of the least investigated causes of death. According to the World Health Organization, around 37.3 million falls occur globally every year resulting in the deaths of over 660,000 adults and almost 30,000 children.Objective. The aim of this review is to evaluate the most up-to-date and comprehensive knowledge on falls and their consequences, especially in populations at the highest risk of fatal falls. Brief description of state of knowl… Show more
“…Previous studies have reported low albumin levels and anemia as risk factors for falls in patients hospitalized in the acute phase, and these could be equally applied to patients with acute stroke. Finally, socioeconomic status, a well-known risk factor, was found to be unrelated to the in-hospital falls in this study [ 41 , 42 ]. These results were attributed to the reason that this study was conducted in a single region and incorporated only patients with acute stroke.…”
Background
Falls are one of the most common accidents in medical institutions, which can threaten the safety of inpatients and negatively affect their prognosis. Herein, we developed a machine learning (ML) model for fall prediction in patients with acute stroke and compared its accuracy with that of the existing fall risk prediction tool, the Morse Fall Scale (MFS).
Methods
This is a retrospective nested case-control study. The initial sample size was 8462 admitted to a single cerebrovascular specialty hospital with acute stroke. A total of 156 fall events occurred, and each fall case was randomly matched with six control cases. Six ML algorithms were used, namely, regularized logistic regression, support vector machine, naïve Bayes (NB), k-nearest neighbors, random forest, and extreme-gradient boosting (XGB).
Results
We included 156 in the fall group and 934 in the non-fall group. The mean ages of the fall and non-fall groups were 68.3 (± 12.2) and 65.3 (± 12.9) years old, respectively. The MFS total score was significantly higher in the fall group (54.3 ± 18.3) than in the non-fall group (37.7 ± 14.7). The area under the receiver operating curve (AUROC) of the MFS in predicting falls was 0.76 (0.73–0.79). XGB had the highest AUROC of 0.85 (0.78–0.92), and XGB and NB had the highest F1 score of 0.44.
Conclusions
The AUROC values of all of ML algorithms were similar to those of the MFS in predicting fall risk in patients with acute stroke, allowing for accurate and efficient fall screening.
“…Previous studies have reported low albumin levels and anemia as risk factors for falls in patients hospitalized in the acute phase, and these could be equally applied to patients with acute stroke. Finally, socioeconomic status, a well-known risk factor, was found to be unrelated to the in-hospital falls in this study [ 41 , 42 ]. These results were attributed to the reason that this study was conducted in a single region and incorporated only patients with acute stroke.…”
Background
Falls are one of the most common accidents in medical institutions, which can threaten the safety of inpatients and negatively affect their prognosis. Herein, we developed a machine learning (ML) model for fall prediction in patients with acute stroke and compared its accuracy with that of the existing fall risk prediction tool, the Morse Fall Scale (MFS).
Methods
This is a retrospective nested case-control study. The initial sample size was 8462 admitted to a single cerebrovascular specialty hospital with acute stroke. A total of 156 fall events occurred, and each fall case was randomly matched with six control cases. Six ML algorithms were used, namely, regularized logistic regression, support vector machine, naïve Bayes (NB), k-nearest neighbors, random forest, and extreme-gradient boosting (XGB).
Results
We included 156 in the fall group and 934 in the non-fall group. The mean ages of the fall and non-fall groups were 68.3 (± 12.2) and 65.3 (± 12.9) years old, respectively. The MFS total score was significantly higher in the fall group (54.3 ± 18.3) than in the non-fall group (37.7 ± 14.7). The area under the receiver operating curve (AUROC) of the MFS in predicting falls was 0.76 (0.73–0.79). XGB had the highest AUROC of 0.85 (0.78–0.92), and XGB and NB had the highest F1 score of 0.44.
Conclusions
The AUROC values of all of ML algorithms were similar to those of the MFS in predicting fall risk in patients with acute stroke, allowing for accurate and efficient fall screening.
“…According to the World Health Organization (WHO), a fall can be understood as an event characterized by the sudden descent of the body to a level lower than the initial position [8]. 2 Additionally, patient falls contribute to prolonging the length of hospital stay, resulting in additional care costs and potentially having consequences for the institution's credibility and legal issues [9].…”
This study analyzed the risk of falls in the elderly and the safety of the environment in a teaching hospital in Brazil. The Morse Falls Scale was used to stratify the risk of falls in 45 hospitalized elderly individuals, and a checklist was used to analyze the hospital environment. The analysis was based on the chi-square test and multiple regression. The moderate risk of falls was predominant (51.1%). The variable age group (p-value = 0.024) showed statistical evidence of association with the risk of falls. However, the multiple regression analysis showed no difference between the age groups and the risk situation for falls. The hospital wards showed an adequate arrangement of furniture, but some aspects had inadequacies, such as objects in the corridors, non-functional bells in some beds, and inadequacy of the toilet bowls in terms of the recommended height, the absence of non-slip flooring and the support bar in some bathrooms. In conclusion, the moderate risk of falls among the elderly and the adequacy of the hospital environment to technical standards were evident, with the exception of failures in the emergency communication system and sanitary installation.
“…Moreover, fall history generates fear of a second fall, reducing progressively all the ADL resulting in social isolation, anxiety, and depression. This brings a substantial weakening of physical fitness that increases the fall risk, disability and hospitalization or institutionalization [4]. Fall events are also involved in driving up medical costs worldwide.…”
Prevention strategies should be constantly improved to manage falls and frailty in the elderly. Therefore, we aimed at creating a screening and predictive protocol as a replicable model in clinical settings. Bioimpedance analysis was conducted on fifty subjects (mean age 76.9 ± 3.69 years) to obtain body composition; then, posture was analysed with a stabilometric platform. Gait performance was recorded by a 10 m walking test, six-minute walking test, and timed up and go test. After 12 months, subjects were interviewed to check for fall events. Non-parametric analysis was used for comparisons between fallers and non-fallers and between able and frail subjects. ROC curves were obtained to identify the predictive value of falling risk and frailty. Path length (area under the curve, AUC = 0.678), sway area (AUC = 0.727), and sway speed (AUC = 0.778) resulted predictive factors of fall events (p < 0.05). The six-minute walking test predicted frailty condition (AUC = 0.840). Timed up and go test was predictive of both frailty (AUC = 0.702) and fall events (AUC = 0.681). Stabilometry and gait tests should be, therefore, included in a screening protocol for the elderly to prevent fall events and recognize the condition of frailty at an early stage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.