Development of a risk assessment tool to predict fall-related severe injuries occurring in a hospital

Risk Factors for Fall-Related Serious Injury among Korean Adults: A Cross-Sectional Retrospective Analysis

The purpose of this study was to identify the risk factors of serious fall-related injuries by analyzing the differences between two fall groups: one with serious fall-related injuries and one without such injuries. Applying a retrospective, descriptive investigation study design, we analyzed the degree of fall-related injury and the risk factors related to serious falls by conducting a complete survey of the medical records of fall patients reported throughout one full year, 2017, at a tertiary hospital in Seoul, Korea. Among the patients with reported falls, 188 sustained no injury (63.1%), 72 sustained minor injury (24.2%), and 38 patients sustained serious injury (12.8%). The serious fall-related injuries included eight lacerations requiring suture (2.7%), 23 fractures (7.7%), five brain injuries (1.7%), and two deaths (0.7%). Analysis results indicated that taking anticoagulants/antiplatelet drugs (p = 0.016) and having a fall history (p = 0.038) were statistically significant in the differences between the group with serious injury related to falls and the group without serious injury. Logistic regression revealed that taking anticoagulant/antiplatelet drugs was the factor most significantly correlated with serious injuries related to falls (OR = 2.299, p = 0.022). Results show that it is necessary to develop a patient-tailored fall prevention activity program.

An eight-camera fall detection system using human fall pattern recognition via machine learning by a low-cost android box

Falls are a leading cause of unintentional injuries and can result in devastating disabilities and fatalities when left undetected and not treated in time. Current detection methods have one or more of the following problems: frequent battery replacements, wearer discomfort, high costs, complicated setup, furniture occlusion, and intensive computation. In fact, all non-wearable methods fail to detect falls beyond ten meters. Here, we design a house-wide fall detection system capable of detecting stumbling, slipping, fainting, and various other types of falls at 60 m and beyond, including through transparent glasses, screens, and rain. By analyzing the fall pattern using machine learning and crafted rules via a local, low-cost single-board computer, true falls can be differentiated from daily activities and monitored through conventionally available surveillance systems. Either a multi-camera setup in one room or single cameras installed at high altitudes can avoid occlusion. This system's flexibility enables a wide-coverage set-up, ensuring safety in senior homes, rehab centers, and nursing facilities. It can also be configured into high-precision and high-recall application to capture every single fall in high-risk zones.

Analysis of Inpatient Hospital Falls with Serious Injury

Fall-related serious injuries pose risks to patients and healthcare organizations. This retrospective, single-hospital study used a 38 variable instrument to understand characteristics of those who sustained a fall with serious injury. Analyses included descriptive statistics, frequency, and Chi-square tests of associations between key variables and outcomes of moderate versus major injury. Age range 25-91 years, predominantly 60-69 years (23.3%), and mostly male (50.9%). Highest percentage occurred between 0:00 and 06:59 (39.6%), and on Oncology service (28.3%). Fallers were in the room, (81.1%), sustained major injury (73.6%), fractured a major bone (43.4%), had altered mobility prior to the fall (67.9%), and had received at least one narcotic dose within 24 hours before the fall (43.2%). The associations between injury severity and age, gender, altered mobility, fall risk assessment pre-fall, and unit service line are not statistically significant, however have small-to-moderate clinical significance. This study adds to the literature in identifying characteristics of patients who sustain a fall-related serious injury.

A hospitalist's role in preventing patient falls

Despite decades of fall prevention efforts, patient falls remain a common cause of harm in hospitalized older adults. While fall prevention strategies have been historically championed by nurses, hospitalist physicians, nurse practitioners, and physician assistants play a vital role in the multidisciplinary care team in ensuring the safety of our patients. Multiple fall risk assessment tools exist, but no one tool has demonstrated excellence in predicting patient falls in the hospital. Any fall risk assessment tool should be complemented by a clinician's individualized evaluation of patient-specific, situational, and environmental risk factors. A particular emphasis on medication review is critical, as numerous medication classes can increase the risk of falls, and medications are a potentially modifiable risk factor. Multiple studies of individual and multicomponent nursing-based interventions have failed to demonstrate success in reducing falls or fall injuries. Promising strategies for fall prevention include tailoring interventions to patient risk factors and individualized patient education. In addition to nursing-based interventions, the hospitalist's role in fall prevention is to (1) identify and address potentially modifiable risk factors, (2) reinforce individualized education to patients, and (3) advise behavior choices that promote safe mobility. If a patient does sustain a fall, the hospitalist should partner with the multidisciplinary care team in post fall care to assess for injury, evaluate underlying causes of the fall, and determine plans for secondary prevention.

Preventing inpatient falls with injuries using integrative machine learning prediction: a cohort study

Patient falls during hospitalization can lead to severe injuries and remain one of the most vexing patient-safety problems facing hospitals. They lead to increased medical care costs, lengthened hospital stays, more litigation, and even death. Existing methods and technology to address this problem mostly focus on stratifying inpatients at risk, without predicting fall severity or injuries. Here, a retrospective cohort study was designed and performed to predict the severity of inpatient falls, based on a machine learning classifier integrating multi-view ensemble learning and model-based missing data imputation method. As input, over two thousand inpatient fall patients’ demographic characteristics, diagnoses, procedural data, and bone density measurements were retrieved from the HMH clinical data warehouse from two separate time periods. The predictive classifier developed based on multi-view ensemble learning with missing values (MELMV) outperformed other three baseline models; achieved a cross-validated AUC of 0.713 (95% CI, 0.701–0.725), an AUC of 0.808 (95% CI, 0.740–0.876) on the separate testing set. Our studies show the efficacy of integrative machine-learning based classifier model in dealing with multi-source patient data, which in this case delivers robust predictive performance on the severity of patient falls. The severe fall index provided by the MELMV classifier is calculated to identify inpatients who are at risk of having severe injuries if they fall, thus triggering additional steps of intervention to prevent a harmful fall, beyond the standard-of-care procedure for all high-risk fall patients.

[The Actual Condition of Fall Accident and Suggestion of Improvement for Accident Prevention in the Department of Radiology]

We conducted a questionnaire survey (situation, patient factor, environmental factor, operator factor, degree of disability, countermeasure etc.) on cases that occurred up to the present to investigate the actual situation of the medical accidents that occur in the radiological examination department of medical institutions. There were 373 questionnaires collected. Among them, there were 197 cases of falls. In this study, we examined the age of patients who fell, the background of the accident, and factors. As for the accident, 11.7% of accidents with risk impact level 3b or higher occurred including the fatal accident. Of the accidents, 44.2% were foreseeable and 55.8% were unforeseeable. The most accident-prone age was elderly in their 60s to 80s. As the causative factor for the accident, the patient factor was the largest at 63.5%. We can prevent about 30% of the accident by improving the operator factor and the environmental factor which are parts other than patient factor. It is important for us to understand what kind of people tend to fall. Among foreseeable accidents, the causes of patient factors can be reduced.

Validity of the Falls Risk for Older People in the Community (FROP-Com) tool to predict falls and fall injuries for older people presenting to the emergency department after falling

The aims of this study were to (1) externally validate the accuracy of the Falls Risk for Older People in the Community (FROP-Com) falls risk assessment tool in predicting falls and (2) undertake initial validation of the accuracy of the FROP-Com to predict injurious falls (requiring medical attention) in people aged ≥ 60 years presenting to emergency departments (EDs) after falling. Two hundred and thirteen participants (mean age = 72.4 years; 59.2% women) were recruited (control group of a randomised controlled trial). A FROP-Com assessment was completed at a home visit within 2 weeks of ED discharge. Data on falls and injurious falls requiring medical attention were collected via monthly falls calendars for the next 12 months. Predictive accuracy was evaluated using sensitivity and specificity of a high-risk FROP-Com classification (score ≥ 19) in predicting a fall and injurious falls requiring medical attention. Fifty per cent of participants fell, with 60.4% of falls requiring medical attention. Thirty-two per cent were classified as high, 49% as moderate and 19% low falls risk. Low sensitivity was achieved for the FROP-Com high-risk classification for predicting falls (43.4%) and injurious falls (34.4%), although specificity was high (79.4% and 78.6%, respectively). Despite the FROP-Com's low predictive accuracy, the high fall rate and high falls risk of the sample suggest that older people who fall, present to ED and are discharged home are at high risk of future falls. In high-falls-risk populations such as in this study, the FROP-Com is not a valid tool for classifying risk of falls or injurious falls. Its potential value may instead be in identifying risk factors for falling to direct tailoring of falls prevention interventions to reduce future falls.

The Applicability of New Orleans Criteria for Head Computed Tomography in Inpatient Falls With Injury

Background

Inpatient falls are a patient safety concern. Limited data exist on the utility of head computed tomography (CT) for inpatient falls. The New Orleans Criteria (NOC) is a validated tool to determine the appropriateness of neuroimaging in the emergency department for falls with minor head injury. This study aimed to evaluate whether the NOC could be applied to inpatient falls.

Methods

This retrospective cohort study assessed 1 year of inpatient falls with injury at 5 inpatient facilities. Records were reviewed for demographic data, fall circumstances, laboratory results, components of the NOC, and head CT results. Cohorts included positive NOC (≥1 NOC finding) and negative NOC. Sensitivity and specificity were calculated for the NOC alone, NOC plus coagulopathy, and NOC or coagulopathy for acute intracranial process.

Results

Of 332 inpatient falls with injury, 188 (57%) received a head CT. Of the 250 (75.3%) NOC-positive cases, 159 (63.6%) received a head CT. Of all patients who received a head CT, 7 (2.1%) showed a significant acute intracranial process. The NOC was positive in 6 of the 7 cases (sensitivity 85.7% and specificity 23.8%); the other case had a significant coagulopathy. New Orleans Criteria or coagulopathy had 100% sensitivity and 23.4% specificity.

Conclusions

Our findings show that use of the NOC to evaluate potential intracranial injury in inpatient falls is limited. Adding criteria to the NOC may improve its test characteristics, with a sensitivity of 100% for the NOC or coagulopathy, suggesting potential clinical utility.

Characteristics of awareness and behavior of medical staff for prevention of falling accidents among inpatients

The purpose of this study is to clarify the characteristics of awareness and behavior for falling accident prevention according to medical profession. We used a questionnaire called "Self-Evaluation of Awareness and Behavior for Falling Accident Prevention," which was originally designed for nurses. In October and November 2016, the questionnaire was administered to 1,670 medical staff (nurses, doctors, lab technicians, nursing assistants, radiological technicians, pharmacists, physical therapists, nutritionists, and occupational therapists, among others) at a hospital in Japan, using a 5-step scale and a not applicable (N/A) option. Valid responses were obtained from 923 (55.3%) participants, and all seven factors extracted by factor analysis had Cronbach's α coefficients of greater than 0.9. Using cluster analysis based on principal component analysis, four categories were identified. According to the results of the N/A χ2 (chi-square) test question item and occupation, nurses answered N/A the least, followed by doctors, physical therapists, and occupational therapists. Nursing assistants' awareness and behavior were both low, suggesting the necessity of education on preventing falling accidents. By applying the "Self-Evaluation of Awareness and Behavior for Falling Accident Prevention" to all medical staff, we succeeded in clarifying their characteristics of awareness and behavior for falling accident prevention.

Identifying protective and risk factors for injurious falls in patients hospitalized for acute care: a retrospective case-control study

Background

Admitted patients who fall and injure themselves during an acute hospitalization incur increased costs, morbidity, and mortality, but little research has been conducted on identifying inpatients at high risk to injure themselves in a fall. Falls risk assessment tools have been unsuccessful due to their low positive predictive value when applied broadly to entire hospital populations. We aimed to identify variables associated with the risk of or protection against injurious fall in the inpatient setting. We also aimed to test the variables in the ABCs mnemonic (Age > 85, Bones-orthopedic conditions, anti-Coagulation and recent surgery) for correlation with injurious fall.

Methods

We performed a retrospective case-control study at an academic tertiary care center comparing admitted patients with injurious fall to admitted patients without fall. We collected data on the demographics, medical and fall history, outcomes, and discharge disposition of injured fallers and control patients. We performed multivariate analysis of potential risk factors for injurious fall with logistic regression to calculate adjusted odds ratios.

Results

We identified 117 injured fallers and 320 controls. There were no differences in age, anti-coagulation use or fragility fractures between cases and controls. In multivariate analysis, recent surgery (OR 0.46, p = 0.003) was protective; joint replacement (OR 5.58, P = 0.002), psychotropic agents (OR 2.23, p = 0.001), the male sex (OR 2.08, p = 0.003) and history of fall (OR 2.08, p = 0.02) were significantly associated with injurious fall.

Conclusion

In this study, the variables in the ABCs parameters were among the variables not useful for identifying inpatients at risk of injuring themselves in a fall, while other non-ABCs variables demonstrated a significant association with injurious fall. Recent surgery was a protective factor, and practices around the care of surgical patients could be extrapolated to reduce the in-hospital fall rates.

Risk Factors for In-Hospital Complications of Fall-Related Fractures among Older Chinese: A Retrospective Study

Purpose. The aim of this study was to investigate the risk factors and the efficacy of the preventive measurements for the in-hospital complications of fall-related fractures. Methods. The data on older Chinese patients with fall-related fractures were collected, including information on the patients, diseases, and preventive measurements. The potential risk factors for the in-hospital complications included health status on admission, comorbidity, fractures, preventive measures of the complications, and drugs use for the comorbidity. After univariate analyses, multivariate logistic regression analyses were applied to investigate the impact of the potential risk factors on the number of the complications and each individual complication, respectively, and the efficacy of the preventive measurements. Results. A total of 525 male and 1367 female were included in this study. After univariate analyses, multiple logistic regression showed that dementia, pneumonia, antidepressant, postural hypotension, and cerebral infarction could increase the incidence and number of comorbidities. Meanwhile, dementia has shown the strongest association with each individual complication. Conclusions. Different combinations of comorbidity, medication use, and preventive measurements were related to the in-hospital complications of fall-related fractures. Dementia emerged as the most important risk factor for these complications, while most of the preventive measurements could not reduce their incidences.